CN114358442A - Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions - Google Patents
Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions Download PDFInfo
- Publication number
- CN114358442A CN114358442A CN202210078094.9A CN202210078094A CN114358442A CN 114358442 A CN114358442 A CN 114358442A CN 202210078094 A CN202210078094 A CN 202210078094A CN 114358442 A CN114358442 A CN 114358442A
- Authority
- CN
- China
- Prior art keywords
- annual
- litchi
- grade
- year
- meteorological
- 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.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a construction method of a Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions, which comprises the following steps: the method comprises the following steps: collecting annual grade data of regional litchi yield; step two: determining meteorological data; step three: selecting meteorological indexes; step four: the prediction model and the parameters are determined, direct field management measures and standards can be provided for producers and managers, short litchi trees can be covered by a thin film under certain conditions, the sunlight intensity is increased, the lowest temperature is regulated and controlled to be between 26.5 and 27.5 ℃ by measures such as irrigation, grass covering on the ground and reflective film laying between 6 and 7 months and 31 days of the current year, the high yield is facilitated, in a main litchi production area, compared with the annual single yield, the single yield is increased by more than 50 percent through the regulation and control of microclimate conditions, and the economic benefit is very great; measures such as awning, irrigation, grass covering on the ground and the like are conventional cultivation techniques in the litchi main production area, and are easy to popularize and apply.
Description
Technical Field
The invention relates to the technical field of quantitative prediction of yield of horticultural crops, in particular to a construction method of a annual grade region prediction model of the yield of Hepu litchi based on meteorological conditions.
Background
Litchi is one of tropical and subtropical fruit trees with the most strict requirements on the climate conditions in the world. In the vegetative growth period, sufficient sunlight, high temperature and rainy days are needed; the flower bud differentiation period needs low-temperature drying; the fruit development period requires sunny weather. The litchi is a perennial fruit tree, the annual yield fluctuation is mainly influenced by the meteorological conditions in the production period, and when the annual yield is 100%, the annual yield is below 30%, namely the annual maximum fluctuation amplitude of the litchi yield is about 70%. The change of the yield between different ages is called as the phenomenon of big and small years of fruit trees in the industry, namely the annual yield is high and the annual yield is low. The previous research results on the causes of fruit trees in the year and year can be summarized into four aspects, namely meteorological conditions, soil-based site conditions, management methods and characteristics of fruit trees, and the four aspects jointly control the yield of each production cycle.
Due to the limitation of data and research methods, most of previous researches are descriptive or semi-quantitative or short-term researches, and a systematic technology capable of quantitatively predicting yield is not formed. Generally, modern production management technology does not cause large fluctuation of yield, and the influence can be slight; the fertilizer application and irrigation can timely supplement the relatively deficient state of soil nutrients and water after the year; the phenomenon of regular annual fluctuation is not found due to the obvious characteristics of fruit trees; the meteorological conditions of each growth cycle are obviously different, and researches show that the meteorological conditions are the main uncertain factors influencing the growth and the growth of fruit trees in years. The difficulty of the annual grade of the litchi variety yield is not solved all the time, and the fundamental reason is that no key quantitative influence factor is found.
Disclosure of Invention
The invention aims to provide a construction method of a annual grade region prediction model of Hepu litchi yield based on meteorological conditions, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a construction method of a Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions comprises the following steps:
the method comprises the following steps: collecting annual grade data of regional litchi yield;
step two: determining meteorological data;
step three: selecting meteorological indexes;
step four: prediction model and parameter determination.
As a further scheme of the invention: in the first step, the year-year grade data (including year quantity and year-year grade) of the litchi yield of the region in recent years are determined through field investigation and public information and are divided into five grades of big year, flat year, small year and small year, and 5, 4, 3, 2 and 1 are respectively assigned as dependent variables Y; and determining the initial harvest month so as to determine the initial month of the meteorological conditions of the next production cycle, wherein the initial month is advanced to the current month of the flower bud differentiation period aiming at the variety which enters the next flower bud differentiation period before harvest.
As a still further scheme of the invention: and in the second step, the region day-by-day meteorological data of the annual grade data corresponding to the growth cycle is used, and the region day-by-day meteorological data comprises average temperature, highest temperature, lowest temperature, average relative humidity, minimum relative humidity, sunshine hours and precipitation.
As a still further scheme of the invention: and in the third step, meteorological indexes which are in obvious or extremely obvious correlation with the annual grade of the litchi yield are screened.
As a still further scheme of the invention: and in the fourth step, a multivariate regression model is established by using the screened indexes and the annual grade of litchi yield, and finally, a prediction model and parameters are determined by taking the model autoregressive qualification rate of more than 80% as a model qualification rate standard.
Compared with the prior art, the invention has the beneficial effects that:
1. on the basis of survey and observation of litchi yield per unit of recent regional litchi, dividing litchi yield grades into five grades of big year, flat year, small year and small year, assigning 5, 4, 3, 2 and 1, matching and analyzing the annual grade assignment and weather factors month by month and day by day, optimizing weather indexes influencing the litchi yield year and small year annual grade, performing multiple regression modeling, and determining a prediction model and parameters after model autoregressive inspection, thereby providing a big data algorithm, a model and parameters for litchi yield year and small year grade prediction;
2. the invention has the creativity that: establishing a litchi yield annual grade regional prediction model based on meteorological conditions of each growth period, fully excavating the production potential of meteorological data, and interpreting the data which is the scientific basis of production data;
3. novelty of the invention: through big data analysis, the indexes and the time periods which influence the annual grade meteorological conditions of litchi yield and the time step length in days are accurately determined, and specific regulation and control indexes and standards are provided for field management decision making and measure implementation;
4. the practicability of the invention is as follows: specific time periods and optimal ranges of meteorological influence indexes are determined, so that producers can easily master and regulate the indexes, and the practicability of a prediction model can be obviously improved;
5. the invention is technically used as follows: direct field management measures and standards can be provided for producers and managers, for example, measures such as sunshade, irrigation, ground grass covering and the like are used in the harvest of the current year for 1 month, the air temperature can be relatively reduced, the air temperature of 1 month is less than 13 ℃ and is favorable for the formation of the year, reflective films can be paved on the ground in the harvest of the current year for 5 months, 1 day to 6 months, 25 days, the air temperature is increased, short litchi trees can be covered by films under certain conditions, the sunlight intensity is increased, the minimum temperature is regulated and controlled to be between 26.5 ℃ and 27.5 ℃ between the harvest of the current year for 6 months, 6 days to 7 months, 31 days through measures such as irrigation, ground grass covering, reflective film laying and the like, and the high yield is favorable;
6. the invention has the following economic benefits: litchi is one of the fruits with the largest yield fluctuation, and in the main litchi yield area, compared with the annual yield per unit, the yield per unit is increased by more than 50% through the regulation and control of microclimate conditions, so that the economic benefit is very great;
7. the invention has social benefits: measures such as awning, irrigation, grass covering on the ground and the like are conventional cultivation techniques in the litchi main production area, and are easy to popularize and apply.
Drawings
FIG. 1 shows Hepu county litchi X1Graph of the relationship with Y.
FIG. 2 shows Hepu county litchi X2Graph of the relationship with Y.
FIG. 3 shows Hepu county litchi X3Graph of the relationship with Y.
FIG. 4 shows Hepu county litchi X4Graph of the relationship with Y.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 4, in an embodiment of the present invention, a method for constructing a annual grade regional prediction model of the output of he-pu litchi under meteorological conditions includes the following steps:
the method comprises the following steps: collecting annual grade data of regional litchi yield;
the method comprises the steps of determining annual grade data (including the number of years and annual grade of each year) of litchi yield of a recent region through field investigation and public information, dividing the annual grade data into five grades of big year, flat year, small year and small year, and respectively assigning 5, 4, 3, 2 and 1 as dependent variables Y; determining a harvest starting month so as to determine a meteorological condition starting month of the next production cycle, wherein the starting month is advanced to the current month of the flower bud differentiation period aiming at the variety which enters the next flower bud differentiation period before harvest;
step two: determining meteorological data;
using the region daily meteorological data of the annual grade data corresponding to the growth cycle, wherein the region daily meteorological data comprises average temperature, highest temperature, lowest temperature, average relative humidity, minimum relative humidity, sunshine hours and precipitation;
step three: selecting meteorological indexes;
screening meteorological indexes which are in obvious or extremely obvious correlation with the annual grade of the litchi yield;
step four: determining a prediction model and parameters;
establishing a multiple regression model by using the screened multiple indexes and the annual grade of litchi yield, and finally determining a prediction model and parameters by taking the autoregressive qualification rate of the model of more than 80% as the standard of the qualification rate of the model;
the invention determines the meteorological indexes which affect the annual grade of the litchi yield, namely, the average of the minimum daily temperature of 1 month in the current year, the accumulation of the daily sunshine hours of 1 day-6 months and 25 days of 5 months and 1 day in the current year and the average of three meteorological indexes of the minimum daily temperature of 6 days and 6 days to 7 days and 31 days in the current year;
the average of the lowest temperature per day of 1 month in the year of harvesting, the accumulation of the sunshine hours per day of 5 months and 1 day to 6 months and 25 days in the year of harvesting and the average of the lowest temperature per day of 6 days to 7 months and 31 days in the year of harvesting, which influence the annual grade of the litchi yield; ternary regression prediction model and parameters established based on three meteorological indexes, namely y-17.631-0.428 xX1+0.021×X2+0.689×X3(r＝0.963**N is 9), wherein y is the chronological grade of the yield, and X1、X2、X3And three weather indicators respectively representing the average of the minimum daily temperatures of 1 month in the current year, the accumulation of the daily sunshine hours of 5 months and 1 day to 6 months and 25 days in the current year and the average of the minimum daily temperatures of 6 days to 7 months and 31 days in the current year, wherein a, b, c and d are model parameters. The autoregressive qualification rate is calculated according to the grade of the annual prediction error +/-1, and the qualification rate is 100.0 percent;
examples
1. Data and research methods
The annual type grade data of the Hepu county Xiangshan Jizui litchi yield: through field investigation, public information and data analysis, the annual grade data of the yield of the Xiangshan chicken mouth litchi in Hepu county in recent years are sorted, the annual grade of the yield of the Xiangshan chicken mouth litchi in Jipu county in nine years is determined and is divided into 5 grades, and 5, 4, 3, 2 and 1 are respectively assigned to the big year, the next year, the small year and the small year (Y), and the results are shown in Table 1;
TABLE 1 annual type grade of Xiangshan chicken mouth litchi yield
| For years | For a few years | Year after year | For youngster | Small year |
| 2007、2018 | 2016 | 2012、2014 | 1991 | 2000、2001、2019 |
Meteorological data: the meteorological data used in the case mainly comprises daily average temperature, highest temperature, lowest temperature, average relative humidity, minimum relative humidity, sunshine hours and precipitation, and the data is from 756 basic and benchmark annual data sets of the climate data of the ground meteorological observation station in China weather science data sharing service network (http:// cdc.nmic.cn); year-by-year and day-by-day meteorological data in Hepu county are derived from meteorological data of a meteorological station in North sea. The harvesting time of the Xiangshan Yangtze litchi in Hepu county is 6-7 months, so that the growth cycle of the Xiangshan Yangtze litchi in Hepu county is determined to be 8-7 months, and data of 7 meteorological indexes (average temperature, maximum temperature, minimum temperature, average relative humidity, monthly mean value of minimum relative humidity, sunshine hours and monthly accumulated value of precipitation) of 8-7 months in each growth cycle of the Xiangshan Yangtze litchi in Hepu county are extracted. Here, the weather data of the previous year is taken in 8-12 months, and the weather data of the current year is taken in 1-7 months.
The model establishing method comprises the following steps: establishing a weather condition-based annual grade prediction model of the Hepu Xiangshan chicken mouth litchi yield by adopting a statistical analysis method, wherein the statistical method comprises unitary and multiple regression; performing data analysis and modeling by using Excel and self-programming software;
2. weather index influencing large and small year type grade of Hepu county Xiangshan Jizui litchi yield
Through various algorithms and big data calculation, three variables are finally determined as meteorological indexes which influence the annual grade of the output of Xiangshan chicken mouth litchi in Hepu county, the results are shown in a table 2, and the corresponding meteorological data and model autoregressive results are shown in a table 3;
table 2 original weather indicators affecting the senior grade of the Yangshan Jizui litchi yield
| Variables and units | Defining and relating to annual classes |
| X1(℃) | Harvesting the average of the daily minimum temperatures for 1 month of the year; negative correlation |
| X2(h) | Harvesting the accumulation of daily sunshine hours from 1 day in 5 months to 25 days in 6 months; positive correlation |
| X3(℃) | Harvesting the average of the daily minimum temperatures from 6 |
Table 3 original meteorological data and model autoregressive results affecting the chronological grade of the Yangshan chicken mouth litchi yield
| Year of year | X1(℃) | X2(h) | X3(℃) | Y | Y′ | Y′-Y |
| 1991 | 13.2 | 28 | 26.0 | 2 | 2.53 | 0.53 |
| 2000 | 13.5 | 23 | 26.2 | 1 | 1.47 | 0.47 |
| 2001 | 13.6 | 19 | 26.0 | 1 | 0.49 | -0.51 |
| 2007 | 10.7 | 32 | 26.7 | 5 | 5.02 | 0.02 |
| 2012 | 9.9 | 21 | 26.8 | 3 | 3.22 | 0.22 |
| 2014 | 12.1 | 20 | 26.9 | 3 | 2.14 | -0.86 |
| 2016 | 12.6 | 30 | 27.3 | 4 | 4.23 | 0.23 |
| 2018 | 12.9 | 33 | 27.1 | 5 | 4.47 | -0.53 |
| 2019 | 13.0 | 15 | 27.8 | 1 | 1.42 | 0.42 |
3. Correlation between original meteorological indexes of Hepu county
Table 4 shows the correlation between the original weather indicators affecting the yield of shang shan zui litchi in he pu county in the year and the year, and all the indicators do not reach the significant correlation;
TABLE 4 correlation between original weather indicators in Hepu county
| r | X1(℃) | X2(h) | X3(℃) |
| X1(℃) | 1 | ||
| X2(h) | -0.175 | 1 | |
| X3(℃) | -0.170 | -0.062 | 1 |
Note: r is0.01＝0.666，r0.01＝0.798，n＝9
4. Relation between single meteorological index in Hepu county and annual grade of Xiangshan chicken mouth litchi yield
And (3) respectively making scatter diagrams of the relation between the three original meteorological indexes of Hepu county and the annual grade of the yield of the Xiangshan Yangtui litchi in the table 3, and matching regression equations, wherein the results are respectively shown in the figure 1, the figure 2 and the figure 3. X1And X3Weather indexes which can be converted and correspond to days are not found; FIG. 4 is X2Weather indicator (X) converted into days4) Quilt including three original weather indicators
Selecting four meteorological indexes;
FIG. 1 illustrates: with a limit of 13 ℃ as X1The yield of the Xiangshan chicken mouth litchis is reduced, and the annual grade of the Xiangshan chicken mouth litchis is increased. The regression equation is that Y is-0.688 multiplied by X1 2+15.543×X1-83.239，r＝-0.730*(n＝9)；
TABLE 5 lowest temperature per day (. degree.C.) in Hepu county 1 month of the year
FIG. 2 illustrates: the cumulative number of sunshine hours per day from 5 months 1 days to 6 months 25 days in the year in Hepu county has an extremely obvious positive correlation with the annual grade of the Xiangshan chicken mouth litchi yield; when X is present2And when the time is more than 400h, the annual grade of the yield is mainly annual and partial annual. The regression equation is that Y is 0.1037 × e0.0089×ZWherein Z ═ X2，r＝0.874**(n＝9)；
TABLE 6 Hepu county harvests daily sunshine hours (h) of 5 months 1 day-6 months 25 days
FIG. 3 illustrates: the average of the lowest temperature of 6-7-31 days in the year obtained in Hepu county is in extremely obvious correlation with the annual grade of the Xiangshan chicken mouth litchi yield; with 27.5 ℃ as a boundary when X3The litchi yield is good in the annual type grade of the year at the temperature of between 26.5 and 27.5 ℃. The regression equation is Y ═ -3.563 XX3 2+191.990×X3－2582.2，r＝0.839**(n＝9)；
Table 7 lowest temperature per day (c) from 6 months 6 to 31 days 7 months in the year was harvested in he prefecture
FIG. 4 is generated from the data associated with Table 6 and Table 3, and FIGS. 4 and 6 illustrate that: in Hepu county, the year or the semiyear type can be guaranteed only when the day of day is more than 8h and more than 30d when the day of day is from 5 months 1 days to 6 months 25 days in the year. The regression equation is that Y is 0.012X2(1) 2－0.396×X2(1)+4.680，r＝0.831**(n＝9)；
5. Large and small year type grade prediction model for Hepu county litchi yield
(1) The comprehensive prediction model based on the original meteorological index combination comprises the following steps: using X in Table 31、X2And X3Performing ternary regression to obtain a prediction model: y (1) ═ 18.354-0.421 xX1+0.021×X2+0.715×X3(r＝0.963**And n is 9), the autoregressive yield is calculated according to the grade of the annual prediction error +/-1, the yield is 100.0%, and the results are shown in table 8.
(2) The method is based on a comprehensive prediction model after some indexes in the original meteorological index combination are replaced by days indexes: performing ternary regression with Y and two original weather indicators in Table 3 and one weather indicator in Table 6 using days as indicators to obtain regression equation Y (2) — 17.933-0.463 × X1+0.804×X3+0.201×X4(r＝0.951**And n is 9), the model autoregressive yield is calculated according to the annual grade prediction error +/-1 grade, the yield is 88.9%, and the results are shown in table 8.
(3) Comprehensive prediction model of all meteorological index combinations: x in tables 3 and 6 was used1、X2、X3、X4Quaternary regression with Y to obtain regression equation Y (3) ═ 18.333-0.411 XX1+0.027×X2+0.688×X3－0.057×X4(r＝0.966**N is 9), the model autoregressive qualification rate is calculated according to the annual grade prediction error +/-1 grades, the qualification rate is 100.0 percent, and the result is thatSee table 8.
TABLE 8 annual grade model autoregressive results for Hepu county litchi yield
Note: in the table, Y is the annual rating1～3' is the annual grade predicted by model autoregression, (Y)1～3' -Y) is the prediction error.
6. Hepu county Xiangshan Jizui litchi yield big and small year meteorological index range
The meteorological index range of the annual grade of the nine-year litchi yield known in Hepu county is shown in Table 9, and X of the year2And X4The method is not overlapped with other types of years, and shows that the two meteorological indexes are key influence factors.
TABLE 9 weather indicator Range of known nine-year-yield big-year and small-year-type grades for Xiangshan Yangxi litchi in Hepu county
| Index (I) | For years | For a few years | Year after year | For youngster | Small year |
| X1(℃) | 10.7-12.9 | 12.6 | 9.9-12.1 | 13.2 | 13.0-13.6 |
| X2(h) | 420.0-423.6 | 410.0 | 307.4-325.8 | 373.7 | 249.2-321.8 |
| X3(℃) | 26.7-27.1 | 27.3 | 26.8-26.9 | 26.0 | 26.0-27.8 |
| X2(1)(d) | 32-33 | 30 | 20-21 | 28 | 15-23 |
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (5)
1. A construction method of a Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions is characterized by comprising the following steps of: the construction method comprises the following steps:
the method comprises the following steps: collecting annual grade data of regional litchi yield;
step two: determining meteorological data;
step three: selecting meteorological indexes;
step four: prediction model and parameter determination.
2. The method of claim 1, wherein the meteorological-condition-based method for constructing the annual-grade regional prediction model of Hepu litchi yield is as follows: in the first step, the year-year grade data (including year quantity and year-year grade) of the litchi yield of the region in recent years are determined through field investigation and public information and are divided into five grades of big year, flat year, small year and small year, and 5, 4, 3, 2 and 1 are respectively assigned as dependent variables Y; and determining the initial harvest month so as to determine the initial month of the meteorological conditions of the next production cycle, wherein the initial month is advanced to the current month of the flower bud differentiation period aiming at the variety which enters the next flower bud differentiation period before harvest.
3. The method of claim 1, wherein the meteorological-condition-based method for constructing the annual-grade regional prediction model of Hepu litchi yield is as follows: and in the second step, the region day-by-day meteorological data of the annual grade data corresponding to the growth cycle is used, and the region day-by-day meteorological data comprises average temperature, highest temperature, lowest temperature, average relative humidity, minimum relative humidity, sunshine hours and precipitation.
4. The method of claim 1, wherein the meteorological-condition-based method for constructing the annual-grade regional prediction model of Hepu litchi yield is as follows: and in the third step, meteorological indexes which are in obvious or extremely obvious correlation with the annual grade of the litchi yield are screened.
5. The method of claim 1, wherein the meteorological-condition-based method for constructing the annual-grade regional prediction model of Hepu litchi yield is as follows: and in the fourth step, a multivariate regression model is established by using the screened indexes and the annual grade of litchi yield, and finally, a prediction model and parameters are determined by taking the model autoregressive qualification rate of more than 80% as a model qualification rate standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210078094.9A CN114358442A (en) | 2022-01-24 | 2022-01-24 | Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210078094.9A CN114358442A (en) | 2022-01-24 | 2022-01-24 | Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358442A true CN114358442A (en) | 2022-04-15 |
Family
ID=81090924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210078094.9A Pending CN114358442A (en) | 2022-01-24 | 2022-01-24 | Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358442A (en) |
-
2022
- 2022-01-24 CN CN202210078094.9A patent/CN114358442A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114330931A (en) | Construction method of Guiping litchi yield major and minor annual grade region prediction model based on meteorological conditions | |
| Amichev et al. | Hybrid poplar growth in bioenergy production systems: biomass prediction with a simple process-based model (3PG) | |
| CN111898922B (en) | Multi-scale crop yield assessment method and system | |
| CN112906298A (en) | Blueberry yield prediction method based on machine learning | |
| CN106022538A (en) | Photovoltaic power generating predicting method based on K-mean clustering improved generalized weather | |
| Bandara | Assessing irrigation performance by using remote sensing | |
| CN114897423B (en) | Farm irrigation probability index calculation method based on crop moisture indication line | |
| Baigorria et al. | Assessing predictability of cotton yields in the southeastern United States based on regional atmospheric circulation and surface temperatures | |
| Sisodia et al. | Forecasting of pre-harvest crop yield using discriminant function analysis of meteorological parameters | |
| CN110516943B (en) | Surface temperature-based dynamic monitoring and remote sensing method for irrigation area in spring irrigation period | |
| WO2022222522A1 (en) | Method and system for diagnosing nitrogen nutrition deficit of cotton under drip irrigation | |
| CN114219183A (en) | Construction method of northern runoff litchi yield major-minor year type grade region prediction model based on meteorological conditions | |
| Angon et al. | Cropland mapping expansion for production forecast: rainfall, relative humidity and temperature estimation | |
| Zhu et al. | Spatial optimization of cotton cultivation in Xinjiang: A climate change perspective | |
| CN112945881A (en) | Method for monitoring water content of potato leaves based on hyperspectral characteristic parameters | |
| CN108460691A (en) | A kind of heliogreenhouse is even cloudy few according to Meteorological Index insurance method | |
| CN109934400B (en) | Rain collecting, regulating and deficiency crop water demand prediction method based on improved neural network | |
| Viola et al. | Olive yield and future climate forcings | |
| CN114358442A (en) | Construction method of Hepu litchi yield major-minor annual grade region prediction model based on meteorological conditions | |
| CN115166866A (en) | Citrus disease and insect pest occurrence forecasting method and system based on lattice point meteorological data | |
| CN112904920B (en) | Method for predicting yield of photosynthetic dry matter of greenhouse crops | |
| CN113935542A (en) | Method for predicting cotton yield per unit based on climate suitability | |
| CN113850465A (en) | Hydrology arid monitoring system in no data area | |
| CN113408793A (en) | Method for constructing litchi major and minor region forecasting model based on meteorological conditions | |
| Shabir et al. | Implementation Of The Double Exponential Smoothing Method In Determining The Planting Time In Strawberry Plantations |
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 |