CN109615149B - Method and system for determining beet meteorological yield - Google Patents

Method and system for determining beet meteorological yield Download PDF

Info

Publication number
CN109615149B
CN109615149B CN201811646260.0A CN201811646260A CN109615149B CN 109615149 B CN109615149 B CN 109615149B CN 201811646260 A CN201811646260 A CN 201811646260A CN 109615149 B CN109615149 B CN 109615149B
Authority
CN
China
Prior art keywords
beet
weather
years
biomass
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811646260.0A
Other languages
Chinese (zh)
Other versions
CN109615149A (en
Inventor
刘申
张虎成
董婷婷
彭远
张东晖
杨松松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aisino Corp
Original Assignee
Aisino Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aisino Corp filed Critical Aisino Corp
Priority to CN201811646260.0A priority Critical patent/CN109615149B/en
Publication of CN109615149A publication Critical patent/CN109615149A/en
Application granted granted Critical
Publication of CN109615149B publication Critical patent/CN109615149B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention provides a method and a system for determining beet weather yield. According to the method and the system, according to main weather index information of the current crop in the area affecting the growth of the crop, the method and the system mainly comprise historical data and data of known time in the current year, the weather index information of the beet in the current year is predicted through a weather index prediction model, then weather biomass of each growing period of the beet in the current year is predicted through a weather index-weather biomass prediction model, and the weather yield of the beet in the current year is predicted through a weather biomass-weather yield prediction model. According to the method and the system for determining the beet weather yield, provided by the invention, the weather biomass prediction of the beet in each growth period can be realized by establishing the weather index-weather biomass prediction model of the beet in each growth period, so that the accuracy of beet weather yield prediction is improved, the dynamic release of beet weather yield is realized, and technical support is provided for guaranteeing the supply and demand balance of beet markets in China.

Description

Method and system for determining beet meteorological yield
Technical Field
The present invention relates to the field of cash crop yield prediction, and more particularly, to a method and system for determining beet weather yield.
Background
Beet yield is generally divided into biological yield and economic yield. Biomass refers to the total amount of various organic substances produced and accumulated by photosynthesis and absorption, i.e., by conversion of substances and energy, of sugar beets during each growth cycle, and is usually calculated without the root system. Economic yield refers to the yield of sugar beet granules required for cultivation purposes, i.e. the yield generally referred to. Generally, the economic yield is proportional to the biomass.
The growth period of beet is mainly determined by hereditary property of beet, and is also different due to climate conditions and cultivation technique in cultivation area. For example, the air temperature is low during autumn sowing and winter sowing, the growth and development are slow, and the growth period is long; the air temperature is high during spring sowing and summer sowing, so that the growth and development are fast, and the growth period is short. The same variety is planted in different latitude areas, and the growth period also changes due to the difference of temperature and illumination.
Since the long-time yield fluctuation is closely related to not only the weather index but also the beet variety update, the socioeconomic change, etc., in the observation, statistics and research of the relationship between the crop yield and the weather index in the long-time sequence, the yield of beet is generally decomposed into a trend yield, a weather yield and a random error 3 part, the trend yield is a long-period yield component reflecting the productivity development level in the historical period, and is also called a technical yield, and the weather yield is a fluctuation yield component influenced by a short-period change factor (mainly agricultural climate disaster) mainly comprising climate factors. Therefore beet weather yield is an important point in beet yield prediction.
In the prior art, the weather yield of the beet is predicted by only considering the weather condition change of the whole growth period of the beet, however, the requirements of the beet on the weather conditions in different growth and development processes are different, the key period and weather factors affecting the growth and development of crops in different regions are also different, and the weather yield fluctuation of the beet cannot be predicted accurately in time by only considering the influence of the weather condition of the whole growth period on the weather yield of the beet.
Therefore, there is a need for a technique that can determine the weather output of sugar beets from their weather biomass changes for each growing season, based on the differences in weather biomass that are affected by the weather conditions during the different growing periods.
Disclosure of Invention
In order to solve the technical problem that the influence of the climate conditions of the whole growth period on the beet meteorological yield is only considered in the prior art and the fluctuation of the beet meteorological yield under the climate conditions cannot be timely and accurately predicted, the invention provides a method for determining the beet meteorological yield, which comprises the following steps:
determining data of weather indexes of each growing period of the beet in the current year according to a set weather index prediction model based on data of weather indexes affecting the growth of the beet in the past n years and data of known time of the current year, wherein the weather indexes comprise the lowest day temperature, the highest day temperature, the soil humidity and the wind speed;
Determining the weather biomass of each growing period of the beet in the current year according to the weather index-weather biomass prediction model of each growing period of the beet based on the data of the weather index of each growing period of the beet in the current year;
and determining the weather yield of the beet in the current year according to the weather biomass-weather yield prediction model of the beet based on the weather biomass of each growing period of the beet in the current year.
Further, the method further comprises, before determining the data of the weather indicators of each growing period of the beet in the current year according to the set weather indicator prediction model based on the data of the weather indicators affecting the growth of the beet in the past n years and the data of the known time of the current year:
dividing the growth stage of beet into a plurality of growth stages according to the growth characteristics of beet;
collecting weather indicators affecting beet growth over the past n years and known time of day data, biomass over the past n years for each growing period, economic yield over the past n years data, and historical data of beet start and stop times for each growing period;
determining the starting and stopping time of each growing period in the current year according to the historical data of the starting and stopping time of each growing period of beet;
determining weather biomass data for each growth period of the sugar beet for the past n years based on the biomass data for each growth period for the past n years;
Determining a weather indicator-weather biomass prediction model for each growing period of the beet based on the weather indicator data for the last n years of each growing period of the beet and the weather biomass data for the last n years of each growing period of the beet;
determining data for the past n years of beet weather yield based on the data for the past n years of beet economic yield;
a weather biomass-weather yield prediction model of the beet is determined based on the weather biomass data of the beet over the past n years and the weather yield data of the beet over the past n years for each growing period.
Further, based on the data of the past n years of the weather index affecting the growth of the beet and the data of the known time of the current year, determining the weather index data of each growing period of the beet in the current year according to the set weather index prediction model comprises:
determining weather-indicator data for an unknown time of the year according to a set weather-indicator prediction model based on weather-indicator data for the past n years affecting beet growth, wherein:
the calculation formula of the daily minimum temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmin ＝μ min +σ min ×χ
Figure BDA0001932118770000031
When the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure BDA0001932118770000032
Figure BDA0001932118770000033
wherein T is nmin Is the lowest temperature of the day of the unknown time of the current year, T hmax Is the maximum value, mu, of the highest temperature of the day of the last n years in a certain day of the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the daily highest temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure BDA0001932118770000041
Figure BDA0001932118770000042
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmax ＝μ max +σ max ×χ
Figure BDA0001932118770000043
Wherein T is nmax Is the highest temperature, T, of the day in the unknown time of the year hmin Is the minimum value, mu, of the lowest temperature of the day of the last n years of a certain day in the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the place of the day in the unknown time of the current yearMean value of the day maximum temperature in month over the past n years, σ min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the soil humidity prediction model is as follows:
R HUmon ＝R Hmon +(1-R Hmon )×exp(R Hmon -1)
R HLmon ＝R Hmon ×(1-exp(-R Hmon ))
when (when)
Figure BDA0001932118770000044
When (1):
R H ＝R HLmon +[rnd 1 ×(R HUmon -R HLmon )×(R Hmon -R HLmon )] 0.5
when (when)
Figure BDA0001932118770000045
When (1):
Figure BDA0001932118770000046
wherein R is H Is the daily average relative humidity, rnd, of a day in the unknown time of the year 1 Is a random number, R Hmon Is the average value of the average relative humidity of the month of the day in the unknown time of the year in the past n years, R HUmon Is the maximum value of the average relative humidity of the month of the day in the unknown time of the current year in the day of the past n years, R HLmon Is the minimum value of the average relative humidity of the month of the day of the last n years in the month of the day of the unknown time of the current year;
The calculation formula of the wind speed prediction model is as follows:
Figure BDA0001932118770000051
Figure BDA0001932118770000052
where u is the wind speed, μ at a day of the current year at an unknown time u Is the average value sigma of the day wind speed of the month of the day in the unknown time of the year in the past n years u Is the standard deviation of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, ζ is the skewness coefficient of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, χ is the generated daily standard normal deviation according to two random numbers rnd 1 And rnd 2 Obtaining;
dividing weather index data of known time in the current year and weather index data of unknown time in the current year determined by a weather index prediction model according to the start and stop time of each growing period of the beet, and obtaining the weather index data of each growing period of the beet.
Further, the determining weather biomass data for the last n years of each growing season of the sugar beet based on the biomass data for the last n years of each growing season of the sugar beet comprises:
generating biomass sequence data from the data of the beet biomass in the past n years of each growing period in time sequence;
taking i years as a sliding step length, and carrying out statistical regression analysis on biomass of beet in each year of each growing period by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
Determining simulated values of j biomass per year for each growth period of the beet based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual biomass according to the simulated values of the j biomass of the beet in each growth period and taking the average value as the annual trend biomass of the beet in each growth period;
the annual biomass and trend biomass of beet in each growing period are subtracted to obtain the annual meteorological biomass of beet in each growing period.
Further, the determining the weather indicator-weather biomass prediction model for each growing period of the beet based on the weather indicator data for the last n years and the weather biomass data for the last n years of the beet comprises:
determining a kernel function of each weather index and the weather biomass based on the weather index data of the beet in the past n years and the weather biomass data in the past n years, the weight of each kernel function, and determining a deviation value of the weather biomass according to the kernel function;
determining a weather index-weather biomass prediction model of the beet in each growth period based on a kernel function of each weather index and weather biomass, a weight of each kernel function and a deviation value, wherein the calculation formula is as follows:
Figure BDA0001932118770000061
Wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure BDA0001932118770000062
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure BDA0001932118770000063
And determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year.
Further, the determining the data for the past n years of beet weather yield based on the data for the past n years of beet economic yield comprises:
generating economic yield sequence data according to time sequence of the data of the beet economic yield for the past n years;
taking i years as a sliding step length, and carrying out statistical regression analysis on the economic yield of beet every i years by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
determining simulated values of j economic productions of beet each year based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual economic yield according to the simulated values of the j annual economic yields of the beet, and taking the average value as the annual trend economic yield of the beet;
the annual economic yield and the trend economic yield of the beet are subtracted to obtain the annual meteorological yield of the beet.
Further, determining a predicted model of beet weather biomass-weather yield based on the data of the weather biomass for the past n years and the data of the weather yield for the beet for the past n years for each growth period comprises:
determining a kernel function of the meteorological biomass and the meteorological yield of each growing period based on the data of the meteorological biomass of each growing period and the data of the meteorological yield of the beet for the past n years, the weight of each kernel function, and determining a deviation value of the meteorological yield according to the kernel function;
determining a beet weather biomass-weather yield prediction model based on a kernel function of weather biomass and weather yield of the beet in each growth period, the weight of each kernel function and the deviation value, wherein the calculation formula is as follows:
Figure BDA0001932118770000071
wherein y is the current weather yield of beet,
Figure BDA0001932118770000072
is a kernel function of meteorological biomass in the ith growth period of beet in the current year, omega i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +.>
Figure BDA0001932118770000073
And determining the deviation value of the meteorological yield of the beet in the current year.
According to another aspect of the present invention, there is provided a system for determining beet weather yield, the system comprising:
a beet weather indicator unit for determining data of weather indicators of each growing period of beet in the current year according to a set weather indicator prediction model based on data of weather indicators affecting the growth of beet in the past n years and data of known time of the current year, wherein the weather indicators include a lowest day temperature, a highest day temperature, soil humidity and wind speed;
A beet weather biomass unit for determining weather biomass of each growing period of the beet in the current year according to a weather index-weather biomass prediction model of each growing period of the beet based on data of weather indexes of each growing period of the beet in the current year;
and the beet weather yield unit is used for determining the weather yield of the beet in the current year according to the weather biomass-weather yield prediction model of the beet based on the weather biomass of each growing period of the beet in the current year.
Further, the system further comprises:
the beet growing period dividing unit is used for dividing the growing period of the beet into a plurality of growing periods according to the growing characteristics of the beet;
a data acquisition unit for acquiring data of past n years of weather indicators affecting the growth of sugar beets and data of known time of the year, data of past n years of biomass per growing period, data of past n years of economic yield, and historical data of start and stop time of sugar beets per growing period;
a growth period time determining unit for determining the start-stop time of each growth period in the current year according to the historical data of the start-stop time of each growth period of the beet;
a first data unit for determining weather biomass data for each growing season of the sugar beet over the past n years based on the biomass data for each growing season of the sugar beet over the past n years;
A first model unit for determining a weather indicator-weather biomass prediction model for each growing period of the sugar beet based on the weather indicator data for the last n years of each growing period of the sugar beet and the weather biomass data for the last n years of each growing period of the sugar beet;
a second data unit for determining data of the past n years of beet weather yield based on data of the past n years of beet economic yield;
a second model unit for determining a weather biomass-weather yield prediction model of the sugar beet based on the weather biomass data of the sugar beet for the past n years and the weather yield data of the sugar beet for the past n years for each growing period.
Further, the beet weather indicator unit includes:
the unknown weather indicator unit is used for determining weather indicator data of unknown time in the current year according to the set weather indicator prediction model based on the weather indicator data affecting the growth of the beet for the past n years, wherein the calculation formulas of the weather indicator prediction model of the lowest day temperature, the highest day temperature, the soil humidity and the wind speed are the same as those in the method for determining the weather yield of the beet, and the calculation formulas are not repeated here.
The index determination unit is used for dividing weather index data of known time in the current year and weather index data of unknown time in the current year determined through the weather index prediction model according to the start and stop time of each growing period of the beet, and then the weather index data of each growing period of the beet is obtained.
Further, the first data unit includes:
a first sequence unit for generating biomass sequence data from the data of the last n years of biomass of each growing period of beet in chronological order;
the first equation set unit is used for carrying out statistical regression analysis on biomass of beet in each year of each growing period by taking the year i as a sliding step length and adopting a linear sliding average method to obtain j sets of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
a first analog value unit for determining analog values of j biomass per year for each growth period of the beet based on j sets of unitary linear regression equations;
a first trend value unit for determining an average value of the simulated values of the annual biomass according to the simulated values of the j annual biomass of the beet in each growing period and taking the average value as the annual trend biomass of the beet in each growing period;
a first outcome unit for subtracting the annual biomass and trending biomass of the beets per growing season, i.e. the annual meteorological biomass of the beets per growing season.
Further, the first model unit includes:
a first parameter unit for determining a kernel function of each weather indicator and the weather biomass, a weight of each kernel function, and determining a deviation value of the weather biomass from the kernel function based on the weather indicator data of the last n years and the weather biomass data of the last n years of each growth period of the beet;
A first formula unit for determining a weather index-weather biomass prediction model of each growing period of beet based on a kernel function of each weather index and weather biomass, a weight of each kernel function, and a deviation value, wherein a calculation formula is as follows:
Figure BDA0001932118770000091
wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure BDA0001932118770000092
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure BDA0001932118770000093
And determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year.
Further, the second data unit includes:
a second sequence unit for generating economic yield sequence data from the data of the last n years of economic yield of beet in time sequence;
the second equation set unit is used for carrying out statistical regression analysis on the economic output of the beet every i years by taking i years as a sliding step length and adopting a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
a second simulation value unit for determining simulation values of j economic productivities of beet each year based on j sets of unitary linear regression equations;
A second trend value unit for determining an average value of the analog values of the economic yields per year from the analog values of j economic yields per year of beet, and taking it as the trend economic yield per year of beet;
and a second result unit, namely subtracting the annual economic yield and the trend economic yield of the beet to obtain the annual meteorological yield of the beet.
Further, the second model unit includes:
a second parameter unit for determining a kernel function of the meteorological biomass and the meteorological yield of each growing period, a weight of each kernel function, and determining a deviation value of the meteorological yield according to the kernel function based on the meteorological biomass data of each growing period and the meteorological yield data of the beet for the past n years;
a second formula unit for determining a beet weather biomass-weather yield prediction model based on a kernel function of weather biomass and weather yield for each growth period of the beet, a weight of each kernel function, and a deviation value, the calculation formula of which is:
Figure BDA0001932118770000101
wherein y is the current weather yield of beet,
Figure BDA0001932118770000102
is the ith birth of beet in the current yearKernel function, ω, of the period meteorological biomass i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +. >
Figure BDA0001932118770000103
And determining the deviation value of the meteorological yield of the beet in the current year.
According to the method and the system for determining the beet weather output, provided by the technical scheme, the beet is firstly divided into a plurality of growth periods according to growth characteristics, weather index information of main influence factors in history is combined in different growth periods, a weather index-weather biomass prediction model is respectively built with biomass in the same growth period in history, and a weather biomass-weather output prediction model is built by applying biomass in the same growth period in history and weather output in history; then, according to main weather index information which influences the growth of crops in the current crop area and mainly comprises historical data and data of known time in the current year, predicting the weather index information of the beet in the current year through a weather index prediction model, finally predicting the weather biomass of the beet in each growth period in the current year through a weather index-weather biomass prediction model, and predicting the weather yield of the beet in the current year through a weather biomass-weather yield prediction model. The method and the system for determining the beet meteorological yield have the following beneficial effects:
1. the weather biomass prediction of the beet in each growth period can be realized by establishing a weather index-weather biomass prediction model of the beet in each growth period, so that the accuracy of the weather yield prediction of the beet is improved;
2. According to the real-time update of the data such as the weather information and the weather biomass of the beet in the current year, the results of the weather index prediction model, the weather index-weather biomass prediction model and the weather biomass-weather yield prediction model can be dynamically adjusted, so that the dynamic release of the beet weather yield is realized;
3. the method can comprehensively, systematically and timely provide the beet weather yield fluctuation process in China, provide visual and accurate beet weather yield prediction results, and provide technical support for guaranteeing the beet market supply and demand balance in China.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a flow chart of a method for determining beet weather yield in accordance with a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for determining beet weather yield in accordance with a preferred embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
FIG. 1 is a flow chart of a method for determining beet weather yield in accordance with a preferred embodiment of the present invention. As shown in FIG. 1, a method 100 for determining beet weather yield according to the present preferred embodiment begins at step 101.
In step 101, the growth phase of the beet is divided into a number of growth phases according to the growth characteristics of the beet. In the preferred embodiment, the growth stage of beet is divided into 4 growth stages of seeding seedling stage, stem and leaf luxuriant stage, tuber swelling growth stage and sugar accumulation stage.
In step 102, data is collected for the past n years of weather indicators affecting beet growth and known times of the year, biomass for each growing period for the past n years, economic yield for the past n years, and historical data for the start and stop times of each growing period for the beet.
In the preferred embodiment, the historical data are mainly obtained from a database of each large crop monitoring platform, the data of known time in the year are mainly obtained through sensor monitoring, wherein the temperature is obtained through temperature sensor monitoring, the daily average temperature is obtained through calculation, the soil humidity is obtained through humidity sensor monitoring, and the wind speed is obtained through wind speed sensor monitoring. In practice, the beet biomass refers to the constant weight reached by the growths of the beet during each growth phase, which are dried at low temperature.
In step 103, the start-stop time of each growing period in the current year is determined according to the historical data of the start-stop time of each growing period of the beet. In a preferred embodiment, the time of the greatest number of times of the start and stop time of each growing period of beet is taken as the start and stop time of the growing period of the current year. When there are two or more dates the same number of times, one of the dates is randomly selected.
At step 104, weather biomass data for each growth period of the sugar beet is determined based on the biomass data for the last n years for each growth period of the sugar beet.
In step 105, a weather indicator-weather biomass prediction model for each growing season of the sugar beet is determined based on the weather indicator data for the last n years of each growing season of the sugar beet and the weather biomass data for the last n years of each growing season of the sugar beet.
At step 106, data for the past n years of beet weather yield is determined based on the data for the past n years of beet economic yield. In practice, the economic yield of sugar beet refers to the dry matter weight of the main product sugar beet harvested for the purpose of cultivation of the sugar beet.
In step 107, a weather biomass-weather yield prediction model of the sugar beet is determined based on the weather biomass data for the last n years of each growing period of the sugar beet and the weather yield data for the last n years of the sugar beet.
In step 108, based on the data of the weather index affecting the growth of sugar beets over the past n years and the data of the known time of the current year, the data of the weather index of each growing period of sugar beets in the current year are determined according to the set weather index prediction model, wherein the weather index comprises the lowest day temperature, the highest day temperature, the soil humidity and the wind speed.
In step 109, the weather biomass of each growing season of the beet in the current year is determined based on the data of the weather indicators of each growing season of the beet in accordance with the weather indicator-weather biomass prediction model of each growing season of the beet.
At step 110, the weather output of the beet in the current year is determined based on the weather biomass of each growing period of the beet in the current year according to the weather biomass-weather output prediction model of the beet.
Preferably, determining weather-indicating data for each growth period of the beet in the current year based on the weather-indicating data for the last n years affecting the growth of the beet and the data for the known time of the current year according to the set weather-indicating prediction model comprises:
determining weather-indicator data for an unknown time of the year according to a set weather-indicator prediction model based on weather-indicator data for the past n years affecting beet growth, wherein:
the calculation formula of the daily minimum temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmin ＝μ min +σ min ×χ
Figure BDA0001932118770000131
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure BDA0001932118770000132
Figure BDA0001932118770000133
wherein T is nmin Is the lowest temperature of the day of the unknown time of the current year, T hmax Is the maximum value, mu, of the highest temperature of the day of the last n years in a certain day of the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the daily highest temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure BDA0001932118770000134
Figure BDA0001932118770000135
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmax ＝μ max +σ max ×χ
Figure BDA0001932118770000141
wherein T is nmax Is the highest temperature, T, of the day in the unknown time of the year hmin Is the minimum value, mu, of the lowest temperature of the day of the last n years of a certain day in the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the soil humidity prediction model is as follows:
R HUmon ＝R Hmon +(1-R Hmon )×exp(R Hmon -1)
R HLmon ＝R Hmon ×(1-exp(-R Hmon ))
when (when)
Figure BDA0001932118770000142
When (1):
R H ＝R HLmon +[rnd 1 ×(R HUmon -R HLmon )×(R Hmon -R HLmon )] 0.5
when (when)
Figure BDA0001932118770000143
When (1):
Figure BDA0001932118770000144
wherein R is H Is the daily average relative humidity, rnd, of a day in the unknown time of the year 1 Is a random number, R Hmon Is the day of the last n years of the month of the day of the unknown time of the current yearAverage value of relative humidity, R HUmon Is the maximum value of the average relative humidity of the month of the day in the unknown time of the current year in the day of the past n years, R HLmon Is the minimum value of the average relative humidity of the month of the day of the last n years in the month of the day of the unknown time of the current year;
the calculation formula of the wind speed prediction model is as follows:
Figure BDA0001932118770000151
Figure BDA0001932118770000152
where u is the wind speed, μ at a day of the current year at an unknown time u Is the average value sigma of the day wind speed of the month of the day in the unknown time of the year in the past n years u Is the standard deviation of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, ζ is the skewness coefficient of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, χ is the generated daily standard normal deviation according to two random numbers rnd 1 And rnd 2 Obtaining;
dividing weather index data of known time in the current year and weather index data of unknown time in the current year determined by a weather index prediction model according to the start and stop time of each growing period of the beet, and obtaining the weather index data of each growing period of the beet.
Preferably, said determining weather biomass data for the last n years of each growing season of beets based on the biomass data for the last n years of each growing season of beets comprises:
generating biomass sequence data from the data of the beet biomass in the past n years of each growing period in time sequence;
taking i years as a sliding step length, and carrying out statistical regression analysis on biomass of beet in each year of each growing period by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
determining simulated values of j biomass per year for each growth period of the beet based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual biomass according to the simulated values of the j biomass of the beet in each growth period and taking the average value as the annual trend biomass of the beet in each growth period;
the annual biomass and trend biomass of beet in each growing period are subtracted to obtain the annual meteorological biomass of beet in each growing period.
Preferably, the weather indicator-weather biomass prediction model for each growing period of the beet based on the weather indicator data for the last n years and the weather biomass data for the last n years comprises:
determining a kernel function of each weather index and the weather biomass based on the weather index data of the beet in the past n years and the weather biomass data in the past n years, the weight of each kernel function, and determining a deviation value of the weather biomass according to the kernel function;
determining a weather index-weather biomass prediction model of the beet in each growth period based on a kernel function of each weather index and weather biomass, a weight of each kernel function and a deviation value, wherein the calculation formula is as follows:
Figure BDA0001932118770000161
wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure BDA0001932118770000162
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure BDA0001932118770000163
And determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year.
In the preferred embodiment, the growing stage of beet is divided into 4 growth stages of seeding and seedling emergence stage, stem and leaf luxuriant stage, tuber swelling and growth stage and sugar accumulation stage. In order to make the weather index-weather biomass prediction model of each growth period more accurate, more specific interval division is performed on the lowest temperature value and the highest temperature value which are set according to historical experience, and the rice field daily water layer height, specifically:
The calculation formula of the weather index-biomass prediction model of the beet seeding seedling stage is as follows:
Figure BDA0001932118770000164
wherein y is bc For seeding seedling stage meteorological biomass, BCTD L 、
Figure BDA0001932118770000165
Respectively weighing the day of which the day minimum temperature is less than 5 ℃ in the seeding seedling stage, the kernel function of the meteorological index and the kernel function of the meteorological index, and BCTD M 、/>
Figure BDA0001932118770000166
Respectively the number of days with the lowest day temperature between 5 ℃ and 12 ℃ in the seeding seedling stage, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and the BCTG M 、/>
Figure BDA0001932118770000167
Respectively the day of 12-14 ℃ of the day maximum temperature in the seeding seedling stage, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and the BCTG H 、/>
Figure BDA0001932118770000168
Respectively the day of which the day maximum temperature is more than 14 ℃ in the seeding seedling stage, the kernel function of the meteorological index and the kernel function weight of the meteorological index，BCSS L 、/>
Figure BDA0001932118770000169
The weight of the day soil humidity less than 21% in the seeding seedling stage, the kernel function of the meteorological index and the kernel function weight of the meteorological index are respectively BCSS M 、/>
Figure BDA0001932118770000171
The weight of the day soil humidity between 21% and 26% in the seeding seedling stage, the kernel function of the meteorological index and the BCSS are respectively H 、/>
Figure BDA0001932118770000172
Respectively is the number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index, BCFS, of which the daily soil humidity is more than 26 percent in the seeding seedling stage L 、/>
Figure BDA0001932118770000173
Respectively is the number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index, BCFS, of which the daily average wind speed is less than or equal to 4m/s in the seeding seedling stage H 、
Figure BDA0001932118770000174
B is respectively the number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index, wherein the daily average wind speed is greater than 4m/s in the seeding seedling stage bc Is the deviation.
The calculation formula of the weather index-biomass prediction model of the sugar beet stem and leaf in the luxuriant period is as follows:
Figure BDA0001932118770000175
wherein y is jf JFTD for the meteorological biomass in the luxuriant period of stems and leaves L 、
Figure BDA0001932118770000176
Respectively isDays when the lowest daily temperature is less than 7 ℃ in the stem and leaf luxuriant period, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFTD M 、/>
Figure BDA0001932118770000177
Respectively the number of days with the lowest day temperature between 7 ℃ and 10 ℃ in the stem and leaf luxuriant period, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFTG M 、/>
Figure BDA0001932118770000178
Respectively the number of days when the highest temperature of the day is 10-12 ℃ in the stem and leaf luxuriant period, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFTG H 、/>
Figure BDA0001932118770000179
Respectively the number of days, the maximum day temperature of which is more than 12 ℃ in the stem and leaf luxuriant period, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFSS L 、/>
Figure BDA00019321187700001710
The weight of the day of less than 25% of the daily soil humidity, the kernel function of the meteorological index and the kernel function of the meteorological index in the stem and leaf luxuriant period, JFSS M 、/>
Figure BDA00019321187700001711
Respectively the days of the day soil humidity between 25% and 27% in the luxuriant period of the stem and leaf, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFSS H 、/>
Figure BDA00019321187700001712
Respectively the days of the stem and leaf in the luxuriant period when the daily soil humidity is more than 27%, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFFS L 、/>
Figure BDA00019321187700001713
Respectively the number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and JFFS of which the daily average wind speed is less than or equal to 4m/s in the stem and leaf luxuriant period H 、/>
Figure BDA00019321187700001714
B is respectively the number of days when the average daily wind speed is greater than 4m/s in the stem and leaf luxuriant period, the kernel function of the meteorological index and the kernel function weight of the meteorological index if Is the deviation.
The calculation formula of the weather index-biomass prediction model for the expansion and growth period of beet tubers is as follows:
Figure BDA0001932118770000181
wherein y is pz PZTD for enlarging tuber and increasing long-term meteorological biomass L 、
Figure BDA0001932118770000182
The weight of PZTD is respectively the number of days, the lowest day temperature of which is less than 5 ℃ in the tuber expansion and expansion period, the kernel function of the meteorological index and the kernel function weight of the meteorological index M 、/>
Figure BDA0001932118770000183
The number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and PZTG are respectively that the lowest day temperature in the tuber expansion and expansion period is between 5 ℃ and 12 DEG C M 、
Figure BDA0001932118770000184
The weight of PZTG is respectively the number of days, the maximum day temperature of which is 12-14 ℃ in the tuber expansion and expansion period, the kernel function of the meteorological index and the kernel function weight of the meteorological index H 、/>
Figure BDA0001932118770000185
Respectively the number of days, the maximum day temperature of which is more than 14 ℃ in the tuber expansion and growth period, the kernel function of the meteorological index and the kernel function weight of the meteorological index,PZSS L 、/>
Figure BDA0001932118770000186
the weight of the day of tuber expansion and growth period, the day of less than 22 percent of soil humidity, the kernel function of the meteorological index and the kernel function weight of the meteorological index, and the PZSS M 、/>
Figure BDA0001932118770000187
The number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index are respectively that the daily soil humidity in the tuber expansion and growth period is between 22% and 25%, and the weight of the PZSS H 、/>
Figure BDA0001932118770000188
Figure BDA0001932118770000189
PZFS is respectively weighted by day of tuber expansion and growth period, day soil humidity greater than 25%, kernel function of meteorological index and kernel function of meteorological index L 、
Figure BDA00019321187700001810
The number of days, the kernel function of the meteorological index and the kernel function weight of the meteorological index are respectively that the average daily wind speed in the tuber expansion and expansion period is less than or equal to 4m/s, and PZFS H 、/>
Figure BDA00019321187700001811
B is respectively the number of days of tuber expansion and growth period with the average daily wind speed greater than 4m/s, the kernel function of the meteorological index and the kernel function weight of the meteorological index pz Is the deviation.
The calculation formula of the weather index-biomass prediction model of the beet sugar accumulation period is as follows:
Figure BDA00019321187700001812
wherein y is tj For the meteorological biomass during the sugar accumulation period,TJTD L 、
Figure BDA0001932118770000191
TJTD, which is the number of days in which the lowest daily temperature is less than-5 ℃ in the sugar accumulation period, the kernel function of the meteorological index and the kernel function weight of the meteorological index M 、/>
Figure BDA0001932118770000192
The weight of the day of which the lowest temperature is between-5 ℃ and 12 ℃ in the sugar accumulation period, the kernel function of the meteorological index and TJTG are respectively M 、/>
Figure BDA0001932118770000193
The weight of the day of 12-14 ℃ of the day maximum temperature in the sugar accumulation period, the kernel function of the meteorological index and the kernel function of the meteorological index, TJTG H 、/>
Figure BDA0001932118770000194
TJSS is respectively the number of days in which the highest daily temperature is more than 14 ℃ in the sugar accumulation period, the kernel function of the meteorological index and the kernel function weight of the meteorological index L 、/>
Figure BDA0001932118770000195
TJSS is respectively the number of days in which the daily soil humidity is less than 20% in the sugar accumulation period, the kernel function of the meteorological index and the kernel function weight of the meteorological index M 、/>
Figure BDA0001932118770000196
TJSS is respectively the number of days of 20% -22% of daily soil humidity in sugar accumulation period, the kernel function of the meteorological index and the kernel function weight of the meteorological index H 、/>
Figure BDA0001932118770000197
Respectively weighing days of which the daily soil humidity is more than 22 percent, the kernel function of the meteorological index and the kernel function of the meteorological index in the sugar accumulation period, TJFS L 、/>
Figure BDA0001932118770000198
Respectively the days of the average daily wind speed in the sugar accumulation period is less than or equal to 4m/s, the kernel function of the meteorological index and the kernel function weight of the meteorological index, TJFS H 、/>
Figure BDA0001932118770000199
B is respectively the number of days in which the daily average wind speed is greater than 4m/s in the sugar accumulation period, the kernel function of the meteorological index and the kernel function weight of the meteorological index tj Is the deviation.
Preferably, said determining beet weather yield data over the past n years based on the beet economic yield data over the past n years comprises:
generating economic yield sequence data according to time sequence of the data of the beet economic yield for the past n years;
taking i years as a sliding step length, and carrying out statistical regression analysis on the economic yield of beet every i years by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
determining simulated values of j economic productions of beet each year based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual economic yield according to the simulated values of the j annual economic yields of the beet, and taking the average value as the annual trend economic yield of the beet;
the annual economic yield and the trend economic yield of the beet are subtracted to obtain the annual meteorological yield of the beet.
Preferably, determining the predicted model of beet weather biomass-weather yield based on the data of the weather biomass for the past n years and the data of the weather yield for the beet for the past n years for each growth period comprises:
determining a kernel function of the meteorological biomass and the meteorological yield of each growing period based on the data of the meteorological biomass of each growing period and the data of the meteorological yield of the beet for the past n years, the weight of each kernel function, and determining a deviation value of the meteorological yield according to the kernel function;
Determining a beet weather biomass-weather yield prediction model based on a kernel function of weather biomass and weather yield of the beet in each growth period, the weight of each kernel function and the deviation value, wherein the calculation formula is as follows:
Figure BDA0001932118770000201
wherein y is the current weather yield of beet,
Figure BDA0001932118770000202
is a kernel function of meteorological biomass in the ith growth period of beet in the current year, omega i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +.>
Figure BDA0001932118770000203
And determining the deviation value of the meteorological yield of the beet in the current year.
In the preferred embodiment, the growing stage of beet is divided into 4 growth stages of seeding and seedling emergence stage, stem and leaf luxuriant stage, tuber swelling and growth stage and sugar accumulation stage. Correspondingly, the calculation formula of the prediction model of the meteorological biomass and the meteorological yield of the beet in each growth period is as follows:
Figure BDA0001932118770000204
wherein z is beet meteorological yield, y bc 、
Figure BDA0001932118770000205
Respectively weighing biomass of beet seeding and seedling emergence stage, kernel function and kernel function of beet seeding and seedling emergence stage, y jf 、/>
Figure BDA0001932118770000206
Respectively, the biomass and nuclear letter of the beet stem and leaf in the luxuriant periodNumber and kernel weight, y pz 、/>
Figure BDA0001932118770000207
w pz The weight of the kernel function and the kernel function of the expanding and growing period biomass of the beet tuber and y tj 、/>
Figure BDA0001932118770000208
The weights of the biomass in the sugar beet sugar accumulation period, the biomass kernel function in the sugar beet sugar accumulation period and the kernel function are respectively given, and b is the deviation.
FIG. 2 is a schematic diagram of a system for determining beet weather yield in accordance with a preferred embodiment of the present invention. As shown in FIG. 2, the system 200 for determining beet weather yield according to the present preferred embodiment includes:
a beet growing period dividing unit 201 for dividing the growing period of beet into a plurality of growing periods according to the growing characteristics of beet;
a growth period time determining unit 202 for determining the start-stop time of each growth period in the current year based on the historical data of the start-stop time of each growth period of the beet.
A data acquisition unit 203 for acquiring data of the past n years of weather indicators affecting the growth of sugar beets and data of known times of the year, data of the past n years of biomass per growing period, and data of the past n years of economic yield.
A first data unit 204 for determining weather biomass data for each growing season of beets over the last n years based on the biomass data for each growing season over the last n years.
A first model unit 205 for determining a weather indicator-weather biomass prediction model for each growing season of the sugar beet based on the weather indicator data for the last n years and the weather biomass data for the last n years of the sugar beet.
A second data unit 206 for determining data of the past n years of beet weather yield based on data of the past n years of beet economic yield.
A second model unit 207 for determining a weather biomass-weather yield prediction model of the sugar beet based on the data of the weather biomass of the sugar beet for the past n years and the data of the weather yield of the sugar beet for the past n years for each growing period.
A beet weather indicator unit 208 for determining data of weather indicators for each growth period of the beet in the current year according to the set weather indicator prediction model based on data of weather indicators affecting the growth of the beet for the past n years and data of known time of the current year, wherein the weather indicators include a day minimum temperature, a day maximum temperature, soil humidity and wind speed.
A beet weather biomass unit 209 for determining weather biomass for each growing period of the beet in the current year based on the data of the weather indicators for each growing period of the beet in the current year according to the weather indicator-weather biomass prediction model for each growing period of the beet.
A beet weather yield unit 210 for determining the weather yield of the beet in the current year based on the weather biomass of each growing period of the beet in the current year according to the beet weather biomass-weather yield prediction model.
Preferably, the beet weather indicator unit 208 includes:
the unknown weather indicator unit 281 is configured to determine weather indicator data of an unknown time of the year according to a set weather indicator prediction model based on data of past n years of weather indicators affecting growth of the beet, wherein calculation formulas of the day minimum temperature, day maximum temperature, soil humidity and wind speed prediction model are the same as those in the method for determining the weather yield of the beet, and are not described herein.
The index determining unit 282 is configured to divide weather-indicating data of known time of the current year and weather-indicating data of unknown time of the current year determined by the weather-indicating prediction model according to start-stop time of each growing period of the beet, so as to obtain weather-indicating data of each growing period of the beet.
Preferably, the first data unit 204 includes:
a first sequence unit 241 for generating biomass sequence data from data of the last n years of biomass of each growing period of beet in chronological order;
a first equation set unit 242, configured to perform statistical regression analysis on biomass of beet in each year of each growing period by using a linear sliding average method with i years as a sliding step length, to obtain j sets of unitary linear regression equations, where i is greater than or equal to 1 and less than or equal to n, j is greater than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
A first analog value unit 243 for determining analog values of j biomass per year for each growth period of beet based on j sets of unitary linear regression equations;
a first trend value unit 244 for determining an average value of the simulated values of the annual biomass according to the simulated values of the j biomass of the beet per year of birth, and taking it as the annual trend biomass of the beet per year of birth;
the first result unit 245 is for subtracting the annual biomass and trend biomass of the beet for each growth period, i.e. the annual meteorological biomass of the beet for each growth period.
Preferably, the first model unit 205 includes:
a first parameter unit 251 for determining a kernel function of each weather indicator and the weather biomass, a weight of each kernel function, and determining a deviation value of the weather biomass from the kernel function, based on the weather indicator data of the last n years and the weather biomass data of the last n years of each growth period of the beet;
a first formula unit 252 for determining a weather indicator-weather biomass prediction model for each growth period of beet based on a kernel function of each weather indicator and weather biomass, a weight of each kernel function, and a deviation value, wherein the calculation formula is:
Figure BDA0001932118770000221
Wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure BDA0001932118770000222
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure BDA0001932118770000223
And determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year.
Preferably, the second data unit 206 includes:
a second sequence unit 261 for generating economic yield sequence data from the data of the last n years of economic yield of beets in chronological order;
a second equation set unit 262, configured to perform statistical regression analysis on economic output of beet every i years by using a linear sliding average method with i years as a sliding step length, to obtain j sets of unitary linear regression equations, where i is greater than or equal to 1 and less than or equal to n, j is greater than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
a second simulation value unit 263 for determining simulation values of j economic productivities of beet each year based on j sets of unitary linear regression equations;
a second trend value unit 264 for determining an average value of the analog values of the economic yields per year from the analog values of j economic yields per year of beet, and taking it as the trend economic yield per year of beet;
The second outcome unit 265 subtracts the annual economic and trended economic yields of beets from the annual meteorological yield of beets.
Preferably, the second model unit 207 includes:
a second parameter unit 271 for determining a kernel function of the weather biomass and the weather yield of each growing period, a weight of each kernel function, and determining a deviation value of the weather yield from the kernel function, based on the data of the weather biomass and the weather yield of the beet for the past n years and the data of the weather yield of the beet for the past n years for each growing period;
a second formula unit 272 for determining a beet weather biomass-weather yield prediction model based on the kernel functions of weather biomass and weather yield for each growth period of the beet, the weight of each kernel function, and the deviation value, the calculation formula of which is:
Figure BDA0001932118770000231
wherein y is the current weather yield of beet,
Figure BDA0001932118770000232
is a kernel function of meteorological biomass in the ith growth period of beet in the current year, omega i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +.>
Figure BDA0001932118770000233
And determining the deviation value of the meteorological yield of the beet in the current year.
The invention has been described with reference to a few embodiments. However, as is well known to those skilled in the art, other embodiments than the above disclosed invention are equally possible within the scope of the invention, as defined by the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/an/the [ means, component, etc. ]" are to be interpreted openly as referring to at least one instance of said means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

Claims (6)

1. A method of determining beet weather yield, the method comprising:
dividing the growth stage of beet into a plurality of growth stages according to the growth characteristics of beet;
collecting weather indicators affecting beet growth over the past n years and known time of day data, biomass over the past n years for each growing period, economic yield over the past n years data, and historical data of beet start and stop times for each growing period;
determining the starting and stopping time of each growing period in the current year according to the historical data of the starting and stopping time of each growing period of beet;
determining weather biomass data for each growth period of the sugar beet for the past n years based on the biomass data for each growth period for the past n years;
Determining a weather indicator-weather biomass prediction model for each growing season of the sugar beet based on the weather indicator data for the last n years of each growing season of the sugar beet and the weather biomass data for the last n years of each growing season of the sugar beet, comprising:
determining a kernel function of each weather index and the weather biomass based on the weather index data of the beet in the past n years and the weather biomass data in the past n years, the weight of each kernel function, and determining a deviation value of the weather biomass according to the kernel function;
determining a weather index-weather biomass prediction model of the beet in each growth period based on a kernel function of each weather index and weather biomass, a weight of each kernel function and a deviation value, wherein the calculation formula is as follows:
Figure FDA0004124530070000011
wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure FDA0004124530070000012
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure FDA0004124530070000013
Determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year;
determining data for the past n years of beet weather yield based on the data for the past n years of beet economic yield;
Determining a weather biomass-weather yield prediction model for the sugar beet based on the weather biomass data for the last n years for each growing period and the weather yield data for the last n years for the sugar beet, comprising:
determining a kernel function of the meteorological biomass and the meteorological yield of each growing period based on the data of the meteorological biomass of each growing period and the data of the meteorological yield of the beet for the past n years, the weight of each kernel function, and determining a deviation value of the meteorological yield according to the kernel function;
determining a beet weather biomass-weather yield prediction model based on a kernel function of weather biomass and weather yield of the beet in each growth period, the weight of each kernel function and the deviation value, wherein the calculation formula is as follows:
Figure FDA0004124530070000021
wherein y is the current weather yield of beet,
Figure FDA0004124530070000022
is a kernel function of meteorological biomass in the ith growth period of beet in the current year, omega i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +.>
Figure FDA0004124530070000023
Determining a deviation value of the meteorological yield of the beet in the current year;
based on the data of the past n years of the weather indicators affecting the growth of the beet and the data of the known time of the current year, determining the data of the weather indicators of each growing period of the beet in the current year according to the set weather indicator prediction model comprises:
Determining weather index data of unknown time in the current year based on weather index data affecting beet growth in the past n years according to a set weather index prediction model, wherein the weather indexes comprise a lowest day temperature, a highest day temperature, soil humidity and wind speed, and the weather index data comprises the following components:
the calculation formula of the daily minimum temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmin ＝μ min +σ min ×χ
Figure FDA0004124530070000024
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure FDA0004124530070000025
Figure FDA0004124530070000026
wherein T is nmin Is the lowest temperature of the day of the unknown time of the current year, T hmax Is the maximum value, mu, of the highest temperature of the day of the last n years in a certain day of the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the daily highest temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure FDA0004124530070000031
Figure FDA0004124530070000032
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmax ＝μ max +σ max ×χ
Figure FDA0004124530070000033
wherein T is nmax Is the highest temperature, T, of the day in the unknown time of the year hmin Is the minimum value, mu, of the lowest temperature of the day of the last n years of a certain day in the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the soil humidity prediction model is as follows:
R HUmon ＝R Hmon +(1-R Hmon )×exp(R Hmon -1)
R HLmon ＝R Hmon ×(1-exp(-R Hmon ))
when (when)
Figure FDA0004124530070000034
When (1):
R H ＝R HLmon +[rnd 1 ×(R HUmon -R HLmon )×(R Hmon -R HLmon )] 0.5
when (when)
Figure FDA0004124530070000041
When (1):
Figure FDA0004124530070000042
wherein R is H Is the daily average relative humidity, rnd, of a day in the unknown time of the year 1 Is a random number, R Hmon Is the average value of the average relative humidity of the month of the day in the unknown time of the year in the past n years, R HUmon Is the maximum value of the average relative humidity of the month of the day in the unknown time of the current year in the day of the past n years, R HLmon Is the minimum value of the average relative humidity of the month of the day of the last n years in the month of the day of the unknown time of the current year;
the calculation formula of the wind speed prediction model is as follows:
Figure FDA0004124530070000043
Figure FDA0004124530070000044
where u is the wind speed, μ at a day of the current year at an unknown time u Is the month of the unknown time of the year in the last n yearsMean value of the sun wind speed sigma u Is the standard deviation of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, ζ is the skewness coefficient of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, χ is the generated daily standard normal deviation according to two random numbers rnd 1 And rnd 2 Obtaining;
dividing weather index data of known time in the current year and weather index data of unknown time in the current year determined by a weather index prediction model according to the start and stop time of each growing period of the beet to obtain weather index data of each growing period of the beet;
Determining the weather biomass of each growing period of the beet in the current year according to the weather index-weather biomass prediction model of each growing period of the beet based on the data of the weather index of each growing period of the beet in the current year;
and determining the weather yield of the beet in the current year according to the weather biomass-weather yield prediction model of the beet based on the weather biomass of each growing period of the beet in the current year.
2. The method of claim 1, wherein the determining the data for the past n years of the meteorological biomass for each growth period of the sugar beet based on the data for the past n years of the biomass for each growth period of the sugar beet comprises:
generating biomass sequence data from the data of the beet biomass in the past n years of each growing period in time sequence;
taking i years as a sliding step length, and carrying out statistical regression analysis on biomass of beet in each year of each growing period by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
determining simulated values of j biomass per year for each growth period of the beet based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual biomass according to the simulated values of the j biomass of the beet in each growth period and taking the average value as the annual trend biomass of the beet in each growth period;
The annual biomass and trend biomass of beet in each growing period are subtracted to obtain the annual meteorological biomass of beet in each growing period.
3. The method of claim 1, wherein the determining data for the past n years of beet weather yield based on data for the past n years of beet economic yield comprises:
generating economic yield sequence data according to time sequence of the data of the beet economic yield for the past n years;
taking i years as a sliding step length, and carrying out statistical regression analysis on the economic yield of beet every i years by using a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
determining simulated values of j economic productions of beet each year based on j sets of unitary linear regression equations;
determining an average value of the simulated values of the annual economic yield according to the simulated values of the j annual economic yields of the beet, and taking the average value as the annual trend economic yield of the beet;
the annual economic yield and the trend economic yield of the beet are subtracted to obtain the annual meteorological yield of the beet.
4. A system for determining beet weather production, the system comprising:
the beet growing period dividing unit is used for dividing the growing period of the beet into a plurality of growing periods according to the growing characteristics of the beet;
A data acquisition unit for acquiring data of past n years of weather indicators affecting the growth of sugar beets and data of known time of the year, data of past n years of biomass per growing period, data of past n years of economic yield, and historical data of start and stop time of sugar beets per growing period;
a growth period time determining unit for determining the start-stop time of each growth period in the current year according to the historical data of the start-stop time of each growth period of the beet;
a first data unit for determining weather biomass data for each growing season of the sugar beet over the past n years based on the biomass data for each growing season of the sugar beet over the past n years;
a first model unit for determining a weather indicator-weather biomass prediction model for each growing season of beets based on the weather indicator data for the past n years and the weather biomass data for the past n years of beets, the first model unit comprising:
a first parameter unit for determining a kernel function of each weather indicator and the weather biomass, a weight of each kernel function, and determining a deviation value of the weather biomass from the kernel function based on the weather indicator data of the last n years and the weather biomass data of the last n years of each growth period of the beet;
A first formula unit for determining a weather index-weather biomass prediction model of each growing period of beet based on a kernel function of each weather index and weather biomass, a weight of each kernel function, and a deviation value, wherein a calculation formula is as follows:
Figure FDA0004124530070000061
wherein y is i Is the meteorological biomass of the ith growing period of the beet in the current year,
Figure FDA0004124530070000062
is a kernel function of the jth meteorological index of the ith growing period of the beet in the current year, omega ij Is the weight of the kernel function of the jth meteorological index of the ith growing period of the beet in the current year, b i Is based on kernel function->
Figure FDA0004124530070000063
Determining the deviation value of the meteorological biomass in the ith growth period of the beet in the current year;
a second data unit for determining data of the past n years of beet weather yield based on data of the past n years of beet economic yield;
a second model unit for determining a weather biomass-weather yield prediction model of sugar beets based on the weather biomass data of the sugar beets for the past n years and the weather yield data of the sugar beets for the past n years for each growing period, the second model unit comprising:
a second parameter unit for determining a kernel function of the meteorological biomass and the meteorological yield of each growing period, a weight of each kernel function, and determining a deviation value of the meteorological yield according to the kernel function based on the meteorological biomass data of each growing period and the meteorological yield data of the beet for the past n years;
A second formula unit for determining a beet weather biomass-weather yield prediction model based on a kernel function of weather biomass and weather yield for each growth period of the beet, a weight of each kernel function, and a deviation value, the calculation formula of which is:
Figure FDA0004124530070000071
wherein y is the current weather yield of beet,
Figure FDA0004124530070000072
is a kernel function of meteorological biomass in the ith growth period of beet in the current year, omega i Is the weight of the kernel function of the ith growth period of beet in the current year, b is based on the kernel function +.>
Figure FDA0004124530070000073
Determining a deviation value of the meteorological yield of the beet in the current year;
a beet weather indicator unit for determining data of weather indicators for each growth period of a beet in the current year according to a set weather indicator prediction model based on data of weather indicators affecting the growth of the beet for the past n years and data of known time of the current year, the beet weather indicator unit comprising:
an unknown weather index unit for determining weather index data of unknown time of the year according to a set weather index prediction model based on data of past n years of weather indexes affecting beet growth, the weather indexes including a day minimum temperature, a day maximum temperature, soil humidity and wind speed, wherein:
the calculation formula of the daily minimum temperature prediction model is as follows:
When the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmin ＝μ min +σ min ×χ
Figure FDA0004124530070000074
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure FDA0004124530070000075
Figure FDA0004124530070000076
wherein T is nmin Is the lowest temperature of the day of the unknown time of the current year, T hmax Is the maximum value, mu, of the highest temperature of the day of the last n years in a certain day of the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard deviationDifference, based on two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the daily highest temperature prediction model is as follows:
when the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is greater than or equal to the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
Figure FDA0004124530070000081
Figure FDA0004124530070000082
When the daily maximum temperature standard deviation determined from the daily maximum temperature of a certain day in the past n years is smaller than the daily minimum temperature standard deviation determined from the daily minimum temperature of a certain day in the past n years:
T nmax ＝μ max +σ max ×χ
Figure FDA0004124530070000083
wherein T is nmax Is the highest temperature, T, of the day in the unknown time of the year hmin Is the minimum value, mu, of the lowest temperature of the day of the last n years of a certain day in the unknown time of the current year min Is the average value, mu, of the lowest temperature of the month of the day of the last n years of the month of the day of the unknown time of the current year max Is the average value of the highest temperature of the month of the day in the past n years, sigma min Is the standard deviation, sigma, of the lowest temperature of the month in the last n years of the month of the day of the current unknown time max Is the standard deviation of the highest temperature of the month of the day in the last n years, x is the generated daily standard normal deviation, according to two random numbers rnd 1 And rnd 2 Obtaining;
the calculation formula of the soil humidity prediction model is as follows:
R HUmon ＝R Hmon +(1-R Hmon )×exp(R Hmon -1)
R HLmon ＝R Hmon ×(1-exp(-R Hmon ))
when (when)
Figure FDA0004124530070000084
When (1):
R H ＝R HLmon +[rnd 1 ×(R HUmon -R HLmon )×(R Hmon -R HLmon )] 0.5
when (when)
Figure FDA0004124530070000091
When (1):
Figure FDA0004124530070000092
wherein R is H Is the daily average relative humidity, rnd, of a day in the unknown time of the year 1 Is a random number, R Hmon Is the average value of the average relative humidity of the month of the day in the unknown time of the year in the past n years, R HUmon Is the maximum value of the average relative humidity of the month of the day in the unknown time of the current year in the day of the past n years, R HLmon Is the minimum value of the average relative humidity of the month of the day of the last n years in the month of the day of the unknown time of the current year;
the calculation formula of the wind speed prediction model is as follows:
Figure FDA0004124530070000093
Figure FDA0004124530070000094
in the method, in the process of the invention,u is the wind speed, mu, on a day in the unknown time of the year u Is the average value sigma of the day wind speed of the month of the day in the unknown time of the year in the past n years u Is the standard deviation of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, ζ is the skewness coefficient of the solar wind speed of the month in the past n years at the month in the unknown time of the current year, χ is the generated daily standard normal deviation according to two random numbers rnd 1 And rnd 2 Obtaining;
the index determining unit is used for dividing weather index data of known time in the current year and weather index data of unknown time in the current year determined by the weather index prediction model according to the start and stop time of each growing period of the beet, so as to obtain weather index data of each growing period of the beet;
a beet weather biomass unit for determining weather biomass of each growing period of the beet in the current year according to a weather index-weather biomass prediction model of each growing period of the beet based on data of weather indexes of each growing period of the beet in the current year;
And the beet weather yield unit is used for determining the weather yield of the beet in the current year according to the weather biomass-weather yield prediction model of the beet based on the weather biomass of each growing period of the beet in the current year.
5. The system of claim 4, wherein the first data unit comprises:
a first sequence unit for generating biomass sequence data from the data of the last n years of biomass of each growing period of beet in chronological order;
the first equation set unit is used for carrying out statistical regression analysis on biomass of beet in each year of each growing period by taking the year i as a sliding step length and adopting a linear sliding average method to obtain j sets of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
a first analog value unit for determining analog values of j biomass per year for each growth period of the beet based on j sets of unitary linear regression equations;
a first trend value unit for determining an average value of the simulated values of the annual biomass according to the simulated values of the j annual biomass of the beet in each growing period and taking the average value as the annual trend biomass of the beet in each growing period;
a first outcome unit for subtracting the annual biomass and trending biomass of the beets per growing season, i.e. the annual meteorological biomass of the beets per growing season.
6. The system of claim 4, wherein the second data unit comprises:
a second sequence unit for generating economic yield sequence data from the data of the last n years of economic yield of beet in time sequence;
the second equation set unit is used for carrying out statistical regression analysis on the economic output of the beet every i years by taking i years as a sliding step length and adopting a linear sliding average method to obtain j groups of unitary linear regression equations, wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to i, and i, j and n are natural numbers;
a second simulation value unit for determining simulation values of j economic productivities of beet each year based on j sets of unitary linear regression equations;
a second trend value unit for determining an average value of the analog values of the economic yields per year from the analog values of j economic yields per year of beet, and taking it as the trend economic yield per year of beet;
and a second result unit, namely subtracting the annual economic yield and the trend economic yield of the beet to obtain the annual meteorological yield of the beet.
CN201811646260.0A 2018-12-29 2018-12-29 Method and system for determining beet meteorological yield Active CN109615149B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811646260.0A CN109615149B (en) 2018-12-29 2018-12-29 Method and system for determining beet meteorological yield

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811646260.0A CN109615149B (en) 2018-12-29 2018-12-29 Method and system for determining beet meteorological yield

Publications (2)

Publication Number Publication Date
CN109615149A CN109615149A (en) 2019-04-12
CN109615149B true CN109615149B (en) 2023-04-28

Family

ID=66015407

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811646260.0A Active CN109615149B (en) 2018-12-29 2018-12-29 Method and system for determining beet meteorological yield

Country Status (1)

Country Link
CN (1) CN109615149B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110245444B (en) * 2019-06-21 2020-09-04 中国气象科学研究院 Development period simulation method based on response and adaptation mechanism of crops to environment
CN110378521B (en) * 2019-06-28 2022-04-22 河南农业大学 Construction and application of yield prediction model of winter wheat in northeast China of Henan province

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341577A (en) * 2017-07-25 2017-11-10 中国农业科学院农业信息研究所 A kind of crop yield Forecasting Methodology and system
CN107423853A (en) * 2017-07-25 2017-12-01 中国农业科学院农业信息研究所 A kind of determination method and system of per unit area yield meteorology variation coefficient
CN107950324A (en) * 2017-12-15 2018-04-24 上海应用技术大学 Based on corn irrigation requirement calculates stage by stage irrigation management system and irrigation method
CN108921351A (en) * 2018-07-06 2018-11-30 北京兴农丰华科技有限公司 Crop production forecast method based on trend yield and Meteorological Output

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10529036B2 (en) * 2016-01-22 2020-01-07 The Climate Corporation Forecasting national crop yield during the growing season using weather indices
US20170228743A1 (en) * 2016-02-05 2017-08-10 Weather Analytics, LLC Crop forecasting with incremental feature selection and spectrum constrained scenario generation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341577A (en) * 2017-07-25 2017-11-10 中国农业科学院农业信息研究所 A kind of crop yield Forecasting Methodology and system
CN107423853A (en) * 2017-07-25 2017-12-01 中国农业科学院农业信息研究所 A kind of determination method and system of per unit area yield meteorology variation coefficient
CN107950324A (en) * 2017-12-15 2018-04-24 上海应用技术大学 Based on corn irrigation requirement calculates stage by stage irrigation management system and irrigation method
CN108921351A (en) * 2018-07-06 2018-11-30 北京兴农丰华科技有限公司 Crop production forecast method based on trend yield and Meteorological Output

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
周俊,梁芳芝,陈传轲,伍宏志.夏大豆产量与气象因素关系的分析.河南职业技术师范学院学报.1988,(第02期),全文. *

Also Published As

Publication number Publication date
CN109615149A (en) 2019-04-12

Similar Documents

Publication Publication Date Title
CN109615148B (en) Method and system for determining meteorological yield of corn
US11617313B2 (en) Controlling agricultural production areas
Matthews Modeling the impact of climate change on rice production in Asia
CN109711102B (en) Method for rapidly evaluating crop disaster loss
CN105184445A (en) Calculation method of average corn loss ratio of many years under corn drought meteorological disasters
CN109615149B (en) Method and system for determining beet meteorological yield
CN101950321A (en) Method for controlling growth of tomatoes by establishing sunlight greenhouse long-season cultivated tomato plant leaf number model
CN110245444B (en) Development period simulation method based on response and adaptation mechanism of crops to environment
CN111798028A (en) Crop yield prediction method and device, electronic equipment and storage medium
CN111898922A (en) Multi-scale crop yield assessment method and system
AU2023203307A1 (en) Controlling Agricultural Production Areas
CN109858678B (en) Method and system for determining meteorological yield of sunflowers
CN109615150B (en) Method and system for determining rice meteorological output
CN115688997A (en) Accumulated temperature-based tea leaf picking period prediction method and system
CN109840623B (en) Method and system for determining meteorological yield of sesame
CN110276482B (en) Method for forecasting starting and ending time of growth period of plant flowers and fruits
CN116401882A (en) Method for evaluating influence of surface ozone on winter wheat yield based on multi-factor stress
CN115049126A (en) Evapotranspiration prediction method based on temperature effect and historical threshold
Lisson et al. Development of a hemp (Cannabis sativa L.) simulation model 4. Model description and validation
CN113935542A (en) Method for predicting cotton yield per unit based on climate suitability
CN114219183A (en) Construction method of northern runoff litchi yield major-minor year type grade region prediction model based on meteorological conditions
CN113052407A (en) Meteorological unit yield prediction method and prediction system for soybeans
CN111241485B (en) Novel diagnosis method for crop yield response to climate change
CN116451823A (en) Apple yield prediction method based on meteorological master control factors
Ribeiro et al. A bioclimatic model for forecasting olive yield

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant