CN116681169A - Method for evaluating influence of extreme climate on crop yield - Google Patents

Method for evaluating influence of extreme climate on crop yield Download PDF

Info

Publication number
CN116681169A
CN116681169A CN202310649197.0A CN202310649197A CN116681169A CN 116681169 A CN116681169 A CN 116681169A CN 202310649197 A CN202310649197 A CN 202310649197A CN 116681169 A CN116681169 A CN 116681169A
Authority
CN
China
Prior art keywords
crop
extreme
model
yield
index
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
Application number
CN202310649197.0A
Other languages
Chinese (zh)
Inventor
柏会子
肖登攀
唐建昭
郭风华
刘剑锋
丁小燕
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.)
Institute Of Geography Hebei Academy Of Sciences
Hebei Normal University
Original Assignee
Institute Of Geography Hebei Academy Of Sciences
Hebei Normal University
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 Institute Of Geography Hebei Academy Of Sciences, Hebei Normal University filed Critical Institute Of Geography Hebei Academy Of Sciences
Priority to CN202310649197.0A priority Critical patent/CN116681169A/en
Publication of CN116681169A publication Critical patent/CN116681169A/en
Pending legal-status Critical Current

Links

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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G06F18/2111—Selection of the most significant subset of features by using evolutionary computational techniques, e.g. genetic algorithms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Evolutionary Biology (AREA)
  • Biophysics (AREA)
  • Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physiology (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • Agronomy & Crop Science (AREA)
  • Genetics & Genomics (AREA)
  • Geometry (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Animal Husbandry (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Biomedical Technology (AREA)
  • Marine Sciences & Fisheries (AREA)

Abstract

The invention relates to an evaluation method of influence of extreme climate on crop yield, which comprises the steps of selecting representative research sites in a detected area, collecting historical meteorological data, soil data and crop management measure data of each research site, and correcting a crop mechanism model APSIM; simulating crop growth period, crop yield and crop biomass of each research site under a long-time sequence by using a crop mechanism model APSIM; selecting an extreme climate index capable of expressing that the crop is influenced by an extreme climate event, and calculating the extreme climate indexes of different growth stages of the crop based on meteorological observation data; optimizing an extreme climate index combination with the best effect on simulating the crop yield through a genetic algorithm; inputting the combination of the crop biomass simulation value and the extreme climate index into a random forest model, and establishing a hybrid model based on feature selection, machine learning and a crop model; the mixed model is used for simulating crop yield of a region to be tested under extreme climate conditions, and the yield simulation level of the mixed model is evaluated.

Description

Method for evaluating influence of extreme climate on crop yield
Technical Field
The invention relates to a prediction method of crop yield, in particular to an evaluation method of influence of extreme climate on crop yield.
Background
Climate conditions are the most important component in the natural resources of the manufacturing agricultural industry. The impact of climate change on agricultural production has attracted extensive attention and high attention from scientists in all countries. As global climate warms, agricultural weather disasters (including high temperature heat injury, low temperature freeze injury, drought, and flooding) that frequently occur in extreme climate events have a serious impact on crop production. Thus, accurate simulation and assessment of the impact of extreme climate events on crop yield is a premise and basis for understanding and predicting the impact of future climate change on agricultural production.
Over the past decades, the development and development of crop models based on process mechanisms has become more sophisticated and is increasingly being used to evaluate and quantify the impact of climate change on crop production (including climate, yield, water consumption, etc.). However, existing crop mechanism models mainly simulate the growth process and yield formation of crops under normal climate conditions and climate change, and lack of consideration of the response process of crop production to extreme climate events often leads to underestimation of the negative impact of climate change on crop yield by model simulation results.
Disclosure of Invention
The invention aims to provide an evaluation method for the influence of extreme climate on crop yield, so that the comprehensive influence of different extreme climate factors (including high temperature, low temperature, strong rainfall and drought) on crop yield can be effectively evaluated.
The purpose of the invention is realized in the following way:
a method of assessing the effect of extreme weather on crop yield comprising the steps of:
s1, determining a plurality of research sites in a detected area, collecting historical meteorological data, soil data and crop data of each research site, inputting the data into a crop mechanism model APSIM, determining parameter values of the crop mechanism model APSIM by adopting a trial-and-error method, and correcting and verifying the determined model parameters according to crop weathers and yield data observed by each research site;
s2, simulating the crop growth period, the crop yield and the crop biomass of each research site under a long time sequence by using a crop mechanism model APSIM with corrected parameters so as to obtain simulation values of the crop growth period, the crop yield and the crop biomass;
s3, selecting an extreme climate index according to extreme climate events which are easy to be received by crops in different growth stages, and calculating and determining the extreme climate index of the crops in different growth stages by using meteorological observation data on the basis of outputting a crop key growth period simulation value by using an APSIM (advanced programmable logic array) of a crop mechanism model;
s4, selecting an extreme climate index combination with the best effect on simulating the crop yield from three extreme climate indexes including an extreme high temperature index, an extreme low temperature index and an extreme rainfall index by using a genetic algorithm;
s5, inputting the crop biomass simulation value obtained in the step S2 and the extreme climate index combination optimized in the step S4 into a Random Forest (RF) machine learning model, and establishing a hybrid model based on feature selection, machine learning and crop model; simulating crop yield of the detected area under extreme climate conditions by using the mixed model, and evaluating the yield simulation level of the mixed model according to crop yield data observed by each research site; finally, the results are output through the mixed model, and the relative contribution of the key extreme climate indexes of the tested area to the crop yield simulation is estimated.
Further, the extreme high temperature index includes high Wen Rishu (HD), high temperature strength (HSI), and high temperature persistence index (HCD); the extremely low temperature index includes Frost Date (FD), frost intensity (CSI), and cold persistence index (FCD); the extreme rainfall indices include the number of days of strong precipitation (R25), continuous wetting index (CWD), and continuous drying index (CDD).
Calculating the values of the three extreme climate indexes in different crop growth stages according to the three extreme climate indexes; the calculation period of the extreme high temperature index is: two stages, jointing to flowering (JF) and flowering to maturity (FM); the calculation period of the extreme low temperature index is: sowing to the jointing (SJ) and jointing to the flowering (JF); the calculation period of the extreme rainfall index is: sowing to the Stage of Jointing (SJ), jointing to flowering (JF) and flowering to maturity (FM); according to the combination of three types of extreme climate indexes and different growth stages of crops, 21 extreme climate indexes are obtained.
Further, a Random Forest (RF) machine learning model is trained with the crop biomass simulation value and the preferred extreme climate index combination as prediction variables and the observed yield as target values to determine key parameter values in the Random Forest (RF) machine learning model, and a hybrid model based on feature selection, machine learning and crop model is constructed.
Further, the crop yield simulation level of the mixed model in step S5 is a model using Root Mean Square Error (RMSE) and correlation coefficient (R 2 ) Evaluating;
the calculation formula of the S5-1 Root Mean Square Error (RMSE) is as follows:
wherein X is obs,i Is the observed yield of crops, X model,i Is crop simulated yield, i is the number of study sites (1, 2.,. The.,. N.;
s5-2 correlation coefficient (R 2 ) Is of the meter(s)The calculation formula is as follows:
wherein,,is the average value of the observed yield
Machine learning algorithms have been widely used in crop yield predictive modeling by virtue of their advantages in dealing with non-linear problems. The machine learning algorithm takes data as an object, and discovers knowledge in the data and abstracts a model by extracting data characteristics to make predictions on the data. Before a machine learning task is developed, feature selection is usually performed on the acquired data, allowance features are removed, and the difficulty of the learning task is reduced. The invention uses genetic algorithm to make feature selection for candidate extreme climate indexes.
Genetic Algorithm (GA) is a method of searching for optimal solutions based on natural selection and biological evolution processes of genetic mechanisms. The algorithm starts with a candidate solution set consisting of a group of coded individuals, and evolves from generation to produce better and better approximation solutions according to the principles of survival and win-win elimination of the fittest. At each generation, individuals are selected according to their fitness in the problem domain, and combined crossover and mutation are performed by means of genetic operators, yielding a population representing a new solution set. This process is repeated until some convergence criterion is met. Feature extraction was performed using the Caret package in R language software, with population number (popSize) set to 50, crossover probability (pcrosover) set to 0.8, mutation probability (pmutation) set to 0.1.
The crop mechanism model (APSIM) is an agricultural production system simulation model capable of simulating main components of an agricultural system, can be used for simulating the growth process of crops and the dynamic state of soil water and nitrogen in the agricultural system, and is particularly suitable for evaluating the influence of climate fluctuation and environmental change on the production potential of the agricultural system and the yield benefit of cultivation measures. The APSIM model allows the user to conveniently configure his own crop model by selecting a range of crops, soil and other sub-modules. The logical relationship between modules may be specified very simply by the "plug-and-pull" function of the module. The apsi model is considered a flexible software environment for a model system because of its flexibility and operability.
A Random Forest (RF) model is a machine learning algorithm that combines multiple mutually uncorrelated decision trees through an ensemble learning method. The RF model extracts a plurality of samples from the original data by utilizing a Bootstrap resampling method, constructs a base predictor (such as CART) for each Bootstrap sample, combines the prediction results of all the base predictors, and obtains a final result by a voting mode. RF modeling was performed using the randomforest package in R language software. In the RF model, there are two main parameters to set: the number of trees (ntree) and the number of variables chosen by the tree nodes (mtry). The model is tuned by selecting a set of candidate tuning parameter values.
The method is based on the characteristic selection method to select the key extreme climate factors influencing the crop growth, and combines the machine learning algorithm and the crop mechanism model simulation, so that the influence of the extreme climate conditions on the crop yield can be fully considered, and the simulation capability of the crop yield under the climate change background is improved.
According to the invention, meteorological data, soil data and crop management measure data of research sites are utilized to drive an APSIM crop mechanism model, and crop yield under long-time sequences of different research sites is simulated; calculating extreme climate indexes by using meteorological observation data, and optimizing out the extreme climate index combination with the best simulation effect on crop yield by using a genetic algorithm characteristic selection method; the crop biomass simulation value and the optimal extreme climate index are combined and input into a random forest model, a mixed model based on feature selection, machine learning and the crop model is established, crop yield under extreme climate conditions is simulated and considered by using the mixed model, and contribution of key extreme climate indexes is evaluated, so that the method has important significance in understanding and predicting influence of future climate change on agricultural production and providing countermeasure adapting to climate change.
Drawings
FIG. 1 is a flow chart of the evaluation method of the present invention.
FIG. 2 is a simulated representation of a crop model and a hybrid model; wherein, (a) is a crop model simulated winter wheat yield verification graph of the invention, and (b) is a mixed model simulated winter wheat yield verification graph.
FIG. 3 is a time series plot of APSIM model simulation values for winter wheat growth period, yield and biomass.
Fig. 4 is a time series plot of 21 extreme climate indexes.
FIG. 5 is a graph of the relative contribution of key extreme climate index to crop yield simulation.
Detailed Description
The invention is further described in detail below with reference to the drawings and examples.
Examples:
as shown in fig. 1, the effect of the extreme climate of the region on winter wheat yield was evaluated using the north-China region as the region to be measured, as follows:
s1, determining the following 32 research sites in North China (see table 1), and collecting historical meteorological data, soil data and crop data of each research site. Historical weather data is detailed weather data of 1981-2009, including the highest temperature of the day, the lowest temperature, radiation, rainfall and the like. The soil data comprise soil organic matter content, field water holding capacity and the like. Crop data includes winter wheat climates, yield, variety, and fertilizer irrigation management measures, among others.
Table 1: research site information
According to the requirement of the crop mechanism model APSIM, solar weather data, soil data and field management measure data (sowing mode, irrigation, fertilization, harvest and the like) of the corresponding year of the research site are input into the crop mechanism model APSIM, a trial-and-error method is adopted to determine the parameter values of crop varieties in the crop mechanism model (main parameters of winter wheat varieties comprise tt_end_of_juvenle, startgf_to_mat, vern_sens, photon_ sens, potential _grain_film_rate, grains_per_grain_stem, max_grain_size), and the determined model parameters are corrected and verified according to winter wheat weather and yield data observed by each research site.
According to the comparative analysis of the simulated yield and the measured yield by each research site in North China, a correlation coefficient R is obtained 2 At 0.70, as shown in fig. 2 (a), it is illustrated that the determined model parameter values have better applicability and representativeness at each research site in north China.
S2, utilizing a crop mechanism model APSIM with corrected parameters, inputting meteorological data, soil data and field management measure data strictly according to observation data, simulating winter wheat growth period, winter wheat yield and winter wheat biomass of each research site under a long time sequence, and outputting simulation values of winter wheat growth period, winter wheat yield and winter wheat biomass in 1981-2009 in North China (see figure 3).
S3, designing three extreme high temperature indexes including a high Wen Rishu (HD), a high temperature strength (HSI) and a high temperature duration index (HCD) according to extreme climate events to which winter wheat is subjected in different growth stages; three extreme low temperature indices, including Frost Date (FD), frost strength (CSI), and cold persistence index (FCD); and three extreme rainfall indices, including the number of days of strong precipitation (R25), continuous wetting index (CWD), and continuous drying index (CDD). Wherein, the calculation period of the extreme high temperature index is as follows: two stages, jointing to flowering (JF) and flowering to maturity (FM); the calculation period of the extreme low temperature index is: sowing to the jointing (SJ) and jointing to the flowering (JF); the calculation period of the extreme rainfall index is: sowing to the jointing (SJ), jointing to flowering (JF) and flowering to maturity (FM). According to the combination of three types of extreme climate indexes and different growth stages of winter wheat, 21 extreme climate indexes are obtained. The definition of the extreme climate index of winter wheat at different growth stages is shown in Table 2. Based on a crop mechanism model APSIM, outputting a winter wheat key growth period simulation value, calculating extreme climate indexes of winter wheat in different growth stages by using meteorological observation data, and calculating the extreme climate indexes in North China as shown in figure 4.
Table 2: extreme climate index of winter wheat at different growth stages
Sequence number Name of the name Extreme climate index Definition of the definition Growth stage
1 HD_JF Number of days at high temperature Day number with day maximum temperature not less than 30 DEG C Jointing to bloom
2 HD_FM Number of days at high temperature Day number with day maximum temperature not less than 30 DEG C Flowering to maturity
3 HSI_JF High temperature strength Average maximum air temperature of day number of day of which the maximum air temperature is more than or equal to 30 DEG C Jointing to bloom
4 HSI_FM High temperature strength Average maximum air temperature of day number of day of which the maximum air temperature is more than or equal to 30 DEG C Flowering to maturity
5 HCD_JF High temperature persistence index Day number of continuous 3 days and more, the highest day temperature is more than or equal to 30 DEG C Jointing to bloom
6 HCD_FM High temperature persistence index Day number of continuous 3 days and more, the highest day temperature is more than or equal to 30 DEG C Flowering to maturity
7 FD_SJ Number of frost days Day minimum air temperature<Day number at 0 DEG C Sowing to the jointing
8 FD_JF Number of frost days Day minimum air temperature<Day number at 0 DEG C Jointing to bloom
9 CSI_SJ Frost strength Day minimum air temperature<Reverse number of average minimum air temperature of day number at 0 DEG C Sowing to the jointing
10 CSI_JF Frost strength Day minimum air temperature<Reverse number of average minimum air temperature of day number at 0 DEG C Jointing to bloom
11 FCD_SJ Cold duration index The lowest air temperature for 3 or more consecutive days<Day number at 0 DEG C Sowing to the jointing
12 FCD_JF Cold duration index The lowest air temperature for 3 or more consecutive days<Day number at 0 DEG C Jointing to bloom
13 R25_SJ Day number of strong precipitation Daily precipitation is greater than or equal to 25mm Sowing to the jointing
14 R25_JF Strong precipitationDay number Daily precipitation is greater than or equal to 25mm Jointing to bloom
15 R25_FM Day number of strong precipitation Daily precipitation is greater than or equal to 25mm Flowering to maturity
16 CWD_SJ Continuous wetting index Daily number with continuous 3-day precipitation of more than or equal to 0.1mm Sowing to the jointing
17 CWD_JF Continuous wetting index Daily number with continuous 3-day precipitation of more than or equal to 0.1mm Jointing to bloom
18 CWD_FM Continuous wetting index Daily number with continuous 3-day precipitation of more than or equal to 0.1mm Flowering to maturity
19 CDD_SJ Continuous drying index Daily precipitation<Maximum number of consecutive days of 5mm Sowing to the jointing
20 CDD_JF Continuous drying index Daily precipitation<Maximum number of consecutive days of 5mm Jointing to bloom
21 CDD_FM Continuous drying index Daily precipitation<Maximum number of consecutive days of 5mm Flowering to maturity
S4, optimizing an extreme climate index combination with the best effect on winter wheat yield simulation from the 21 extreme climate indexes by using a Genetic Algorithm (GA). Setting the population number (popSize) of GA as 50, the crossover probability (pcrosover) as 0.8, the mutation probability (pmutation) as 0.1, and calculating and searching the optimal extreme climate index combination by taking the minimum Root Mean Square Error (RMSE) as an fitness function. The optimal combination is HD_FM, HSI_FM, HCD_FM, FD_SJ, CSI_SJ, CSI_JF, FCD_SJ, R25_SJ, CWD_FM and CDD_JF for 10 indices.
S5, training a random forest model (RF) by taking the winter wheat biomass simulation value obtained in the step S2 and the 10 extreme climate indexes selected in the step S4 as prediction variables and taking the observed yield as a target value, and determining key parameter values in the RF model. In the RF model, there are two main parameters to set: 1. number of trees (ntree); 2. the number of variables (mtry) the tree node decimates. The value of the number of trees (ntree) is set to be 100-1500, and the step length is 100; the value of the number of variables (mtry) of the tree node lottery is set to be 1-15, and the step length is 1.
The RF model is tuned by selecting a set of candidate tuning parameter values consisting of different ntree and mtry. When ntree=400 and mtry=7, the Root Mean Square Error (RMSE) of the constructed hybrid model based on feature selection, machine learning and crop model simulates winter wheat yield to be the smallest and best.
The yield of winter wheat in the North China under extreme climate conditions is simulated by using the mixed model, and the yield simulation level of the mixed model is evaluated according to crop yield data observed by each research site. In particular using Root Mean Square Error (RMSE) and correlation coefficient (R 2 ) To evaluate the simulation level of the hybrid model on winter wheat yield.
1. The Root Mean Square Error (RMSE) is calculated as:
wherein X is obs,i Is the observed yield of winter wheat, X model,i Is the winter wheat simulated yield, i is the study site number (1, 2.,. The.,. N.);
2. correlation coefficient (R) 2 ) The calculation formula of (2) is as follows:
wherein,,is the average of the observed yields.
As shown in FIG. 2 (b), the simulation effect of the hybrid model on winter wheat yield is far higher than that of the APSIM crop model by evaluation index calculation, wherein the correlation coefficient R 2 The root mean square error RMSE was increased from 0.70 for APSIM crop model to 0.93 for mixed model and decreased from 934.6 kg/ha for crop mechanism model APSIM to 425.5 kg/ha for mixed model.
As shown in fig. 5, the relative contribution of the key extreme climate indexes to the winter wheat yield simulation was evaluated by the mixed model output results, and in general, the relative contribution of the extreme temperature indexes to the winter wheat yield simulation was greater than the extreme rainfall indexes, wherein the 5 extreme climate indexes with the largest relative contribution are csi_sj, fd_sj, hsi_fm, fcd_sj and hd_fm in order.

Claims (4)

1. A method for assessing the effect of extreme weather on crop yield comprising the steps of:
s1, determining a plurality of research sites in a detected area, collecting historical meteorological data, soil data and crop data of each research site, inputting the data into a crop mechanism model APSIM, determining parameter values of the crop mechanism model APSIM by adopting a trial-and-error method, and correcting and verifying the determined model parameters according to crop weathers and yield data observed by each research site;
s2, simulating the crop growth period, the crop yield and the crop biomass of each research site under a long time sequence by using a crop mechanism model APSIM with corrected parameters so as to obtain simulation values of the crop growth period, the crop yield and the crop biomass;
s3, selecting an extreme climate index according to extreme climate events which are easy to be received by crops in different growth stages, and calculating the extreme climate index of the crops in different growth stages by using meteorological observation data on the basis of outputting a crop key growth period simulation value by using an APSIM (advanced programmable logic array) of a crop mechanism model;
s4, selecting an extreme climate index combination with the best effect on simulating the crop yield from three extreme climate indexes including an extreme high temperature index, an extreme low temperature index and an extreme rainfall index by using a genetic algorithm;
s5, inputting the crop biomass simulation value obtained in the step S2 and the extreme climate index combination optimized in the step S4 into a Random Forest (RF) machine learning model, and establishing a hybrid model based on feature selection, machine learning and crop model; simulating crop yield of the detected area under extreme climate conditions by using the mixed model, and evaluating the yield simulation level of the mixed model according to crop yield data observed by each research site; finally, the results are output through the mixed model, and the relative contribution of the key extreme climate indexes of the tested area to the crop yield simulation is estimated.
2. The method of assessing the effect of extreme weather on crop yield of claim 1 wherein said extreme high temperature index comprises high Wen Rishu (HD), high temperature strength (HSI) and high temperature persistence index (HCD); the extremely low temperature index includes Frost Date (FD), frost intensity (CSI), and cold persistence index (FCD); the extreme rainfall indices include strong precipitation days (R25), continuous wetting index (CWD), and continuous drying index (CDD);
calculating the values of the three extreme climate indexes in different crop growth stages according to the three extreme climate indexes; the calculation period of the extreme high temperature index is: two stages, jointing to flowering (JF) and flowering to maturity (FM); the calculation period of the extreme low temperature index is: sowing to the jointing (SJ) and jointing to the flowering (JF); the calculation period of the extreme rainfall index is: sowing to the Stage of Jointing (SJ), jointing to flowering (JF) and flowering to maturity (FM); according to the combination of three types of extreme climate indexes and different growth stages of crops, 21 extreme climate indexes are obtained.
3. The method of claim 1, wherein the combination of crop biomass simulation values and preferred extreme climate indices are used as predictive variables, and the Random Forest (RF) machine learning model is trained with observed yield as target values to determine key parameter values in the Random Forest (RF) machine learning model, and a hybrid model based on feature selection, machine learning and crop model is constructed.
4. The method for evaluating the effect of extreme weather on crop yield according to claim 1, wherein the crop yield simulation level of the mixed model in step S5 is a method using Root Mean Square Error (RMSE) and correlation coefficient (R 2 ) Evaluating;
the calculation formula of the S5-1 Root Mean Square Error (RMSE) is as follows:
wherein X is obs,i Is the observed yield of crops, X model,i Is crop simulated yield, i is the number of study sites (1, 2.,. The.,. N.;
s5-2 correlation coefficient (R 2 ) The calculation formula of (2) is as follows:
where X is the average of the observed yields.
CN202310649197.0A 2023-06-02 2023-06-02 Method for evaluating influence of extreme climate on crop yield Pending CN116681169A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310649197.0A CN116681169A (en) 2023-06-02 2023-06-02 Method for evaluating influence of extreme climate on crop yield

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310649197.0A CN116681169A (en) 2023-06-02 2023-06-02 Method for evaluating influence of extreme climate on crop yield

Publications (1)

Publication Number Publication Date
CN116681169A true CN116681169A (en) 2023-09-01

Family

ID=87784836

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310649197.0A Pending CN116681169A (en) 2023-06-02 2023-06-02 Method for evaluating influence of extreme climate on crop yield

Country Status (1)

Country Link
CN (1) CN116681169A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117436710A (en) * 2023-12-20 2024-01-23 中国气象局气象干部培训学院 Drought assessment method based on crop model
CN117542443A (en) * 2023-09-27 2024-02-09 中国农业大学 Method and device for balancing yield and relieving nitrogen pollution and electronic equipment
CN118296971A (en) * 2024-06-05 2024-07-05 南京农业大学 Crop weathered phenotype prediction method, system, device and storage medium

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117542443A (en) * 2023-09-27 2024-02-09 中国农业大学 Method and device for balancing yield and relieving nitrogen pollution and electronic equipment
CN117542443B (en) * 2023-09-27 2024-05-24 中国农业大学 Method and device for balancing yield and relieving nitrogen pollution and electronic equipment
CN117436710A (en) * 2023-12-20 2024-01-23 中国气象局气象干部培训学院 Drought assessment method based on crop model
CN117436710B (en) * 2023-12-20 2024-03-26 中国气象局气象干部培训学院 Drought assessment method based on crop model
CN118296971A (en) * 2024-06-05 2024-07-05 南京农业大学 Crop weathered phenotype prediction method, system, device and storage medium
CN118296971B (en) * 2024-06-05 2024-10-22 南京农业大学 Crop weathered phenotype prediction method, system, device and storage medium

Similar Documents

Publication Publication Date Title
Kucharik Evaluation of a process-based agro-ecosystem model (Agro-IBIS) across the US Corn Belt: Simulations of the interannual variability in maize yield
Bannayan et al. Application of the CERES‐wheat model for within‐season prediction of winter wheat yield in the United Kingdom
Dobor et al. Crop planting date matters: Estimation methods and effect on future yields
Cantelaube et al. Seasonal weather forecasts for crop yield modelling in Europe
Kucharik et al. Integrated BIosphere Simulator (IBIS) yield and nitrate loss predictions for Wisconsin maize receiving varied amounts of nitrogen fertilizer
CN116681169A (en) Method for evaluating influence of extreme climate on crop yield
CN110705182B (en) Crop breeding adaptive time prediction method coupling crop model and machine learning
CN116485040B (en) Seed vitality prediction method, system, electronic equipment and storage medium
CN115619583A (en) Construction method of composite agricultural meteorological disaster monitoring index system
Tan et al. Comparison of the generalized likelihood uncertainty estimation and Markov chain Monte Carlo methods for uncertainty analysis of the ORYZA_V3 model
Mugiyo et al. Investigation of the optimum planting dates for maize varieties using a hybrid approach: A case of Hwedza, Zimbabwe
Baigorria et al. Assessing predictability of cotton yields in the southeastern United States based on regional atmospheric circulation and surface temperatures
Baruah et al. Use of data mining technique for prediction of tea yield in the face of climate change of Assam, India
Guo et al. Calibrating AquaCrop model using genetic algorithm with multi‐objective functions applying different weight factors
CN101430735B (en) Protective farming mode selection method
Li et al. Within‐season yield prediction with different nitrogen inputs under rain‐fed condition using CERES‐Wheat model in the northwest of China
CN113139717B (en) Crop seedling condition grading remote sensing monitoring method and device
US9107355B2 (en) Real-time process for targeting trait phenotyping of plant breeding experiments
CN116629453B (en) Remote sensing yield estimation method suitable for whole crop growth period
Aggarwal Applications of systems simulation for understanding and increasing yield potential of wheat and rice
CN116629117A (en) Crop disease occurrence area prediction method based on gridding monitoring
Wani et al. A study on cross validation for model selection and estimation.
Hoang et al. A robust parameter approach for estimating CERES-Rice model parameters for the Vietnam Mekong Delta
Sima et al. Evaluating RZWQM2-CERES-Maize and water production functions for predicting irrigated maize yield and biomass in eastern Colorado
Uehara et al. Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years—A Trial of Feature Engineering Incorporating Hidden Regional Characteristics—

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