A precision cultivation decision-making method, system, device and medium for food crops

Abstract

The present application belongs to the technical field of agricultural intelligent decision support and crop cultivation optimization, and specifically provides a precision cultivation decision method, system, device and medium for grain crops, which comprises the following steps: obtaining cultivation-related data of all stations in a target area; performing downscaling processing on meteorological data by a bilinear interpolation method, and merging the meteorological data with soil data and management measure data into a grid data set; determining a plurality of key variety parameters with the greatest influence on yield and growth period importance by using a random forest model and a crop growth model; constructing a mapping relationship between the key variety parameters and the meteorological data and soil data in the grid data set by using the random forest model, and obtaining the key variety parameters of each grid in the target area; and obtaining the sowing date and planting density corresponding to the target yield of each grid by using the random forest model and the crop growth model. The present application realizes a precision breakthrough in the scale of decision-making, and the simulation accuracy is improved by 20-30%.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of agricultural intelligent decision support and crop cultivation optimization, and particularly relates to a precision cultivation decision method, system, device and medium for grain crops. BACKGROUND

[0002] With the continuous improvement of agricultural informatization and fine management needs, more and more researches begin to explore model-driven cultivation management optimization methods. Crop models have a strong mechanism basis, can simulate the dynamic growth process of crops under different soil, climate and management measures, and quantify yield, resource utilization rate and environmental effect. However, the simulation efficiency of crop models is low, and it is difficult to search and optimize large-scale, full-variable combinations on a national scale.

[0003] At the same time, artificial intelligence models, especially random forests, are widely used in the prediction of crop yield, nitrogen efficiency and other indicators due to their strong robustness and high fitting ability. However, the model lacks physiological basis, and the generalization ability and interpretability of the results are limited. Some existing researches attempt to use crop model simulation data as a training set to build an AI model for rapid estimation, but most of them still remain at the regional scale or for a single target, lacking integrated recommendation capabilities across scales and targets. In addition, the number of agricultural monitoring sites is not enough and the distribution is uneven, and the spatial scale of related data is large. Therefore, the current cultivation technology recommendation is mostly based on regional experience or expert consensus, and it is difficult to achieve the purpose of high-precision, site-specific decision-making and control. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a precision cultivation decision method, system, device and medium for grain crops, which can provide high-precision decisions for different crops at a low spatial scale in a global range.

[0005] The present application provides a precision cultivation decision method for grain crops, comprising the following steps:

[0006] Obtain cultivation-related data of all sites in the target area, the cultivation-related data including meteorological data, soil data and management measure data;

[0007] Downscale the meteorological data by bilinear interpolation method, and merge the soil data and the management measure data into a 1km x 1km resolution grid data set;

[0008] Using the grid data set and a preset variety parameter set as input data, determine a number of key variety parameters with the greatest influence on yield and growth period importance by using a random forest model and a crop growth model;

[0009] mapping relationship between the key variety parameters and meteorological data and soil data in the grid data set is constructed by using a random forest model, and the key variety parameters of each grid in the target region are obtained;

[0010] With the key variety parameters, meteorological data and soil data of each grid in the target region as input data, sowing dates and planting densities corresponding to the target yield of each grid are obtained by using a random forest model and a crop growth model.

[0011] Further, the step of determining a plurality of key variety parameters with the greatest influence on yield and growth period by using a random forest model and a crop growth model with the grid data set and the preset variety parameter set as input data comprises the following steps:

[0012] A variety parameter set is constructed, and each variety parameter is set with a random distribution in a preset range;

[0013] An equal number of variety parameter sets and data sets are selected and input into a crop growth model to obtain simulated yield and simulated growth period;

[0014] The importance of variety parameters on simulated yield and simulated growth period is analyzed by using a random forest model, and a plurality of key variety parameters with the greatest influence are selected.

[0015] Further, the step of constructing the mapping relationship between the key variety parameters and meteorological data and soil data in the grid data set by using a random forest model, and obtaining the key variety parameters of each grid in the target region comprises the following steps:

[0016] The randomForest function in the random forest model is used to construct the mapping relationship between the key variety parameters and meteorological data and soil data in the grid data set by using a random forest model;

[0017] The key variety parameters are predicted by using the predict function in the random forest model, and the key variety parameters of each grid in the target region are obtained.

[0018] Further, the step of obtaining sowing dates and planting densities corresponding to the target yield of each grid by using a random forest model and a crop growth model with the key variety parameters, meteorological data and soil data of each grid in the target region as input data comprises the following steps:

[0019] The key variety parameters, meteorological data and soil data of each grid in the target region are input into a crop growth model to obtain a simulated data set containing growth period, sowing date, planting density, daily yield and total yield;

[0020] constructing a management measure set, wherein the planting density and the sowing date are set with random distribution within a preset range, and the rest of the management measures are set with the local optimal values by default;

[0021] a random forest model is used to construct a mapping relationship between the simulation data set and the scenario parameter set;

[0022] the sowing date and the planting density corresponding to the target yield of each grid are obtained by using the mapping relationship between the simulation data set and the scenario parameter set.

[0023] Further, the crop growth model is an APSIM model.

[0024] Further, the key variety parameters of corn include accumulated temperature required from crop emergence to the end of the juvenile stage, accumulated temperature required from booting to flowering, accumulated temperature required from flowering to physiological maturity, and radiation use efficiency;

[0025] The key variety parameters of wheat include spring sensitivity coefficient, photoperiod sensitivity coefficient, accumulated temperature required from sowing to emergence, and accumulated temperature required from emergence to the end of the juvenile stage.

[0026] The key variety parameters of rice include juvenile daily development rate, photoperiod sensitive period daily development rate, ear development period daily development rate, and filling maturity period daily development rate.

[0027] Further, the meteorological data include daily maximum temperature, daily minimum temperature, daily precipitation and daily radiation data;

[0028] The soil data include soil bulk density, pH value, clay content, silt content, sand content, organic carbon content and cation exchange rate;

[0029] The management measure data include longitude and latitude, year, sowing date, harvesting date, planting density, fertilizer amount, fertilizer time, irrigation amount, irrigation time and yield.

[0030] The application also provides a precision cultivation decision system for grain crops, comprising:

[0031] An acquisition module is configured to acquire cultivation-related data of all stations in a target area, wherein the cultivation-related data include meteorological data, soil data and management measure data;

[0032] A preprocessing module is configured to perform downscaling processing on the meteorological data by using a bilinear interpolation method, and combine the meteorological data, the soil data and the management measure data into a grid data set with a resolution of 1km x 1km;

[0033] A parameter determination module is configured to use the grid data set and a preset variety parameter set as input data, and determine a plurality of key variety parameters with the greatest influence on yield and growth period by using a random forest model and a crop growth model.

[0034] a parameter prediction module, configured to construct a mapping relationship between the key variety parameters and meteorological data and soil data in the grid dataset by using a random forest model, and obtain the key variety parameters of each grid in the target area;

[0035] a decision generation module, configured to take the key variety parameters, meteorological data and soil data of each grid in the target area as input data, and obtain the sowing date and planting density corresponding to the target yield of each grid by using the random forest model and the crop growth model.

[0036] The application further provides a precision cultivation decision-making device for grain crops, characterized by comprising a processor and a memory, the memory is used for storing a computer program, and the processor is used for executing the computer program to realize the steps of the method.

[0037] The application further provides a computer readable and writable storage medium, characterized by storing a computer program, and the computer program is executed by a processor to realize the method.

[0038] The application has the following beneficial effects:

[0039] 1. The application realizes a precision breakthrough in decision scale, relies on high-resolution driving factors (i.e. variety parameters, soil data and meteorological data), and realizes a 20-30% precision improvement compared with a traditional regional uniform parameter mode.

[0040] 2. The application realizes a leap in simulation efficiency, and has more than 100 times efficiency improvement compared with the single-point simulation efficiency of the traditional crop growth model, and reduces the simulation time to the order of hours.

[0041] 3. The application realizes reasonable optimization of management strategies, and the average yield potential of three main crops is improved by 30-80%. DETAILED DESCRIPTION

[0042] Figure 1 is a flowchart of the method in the application;

[0043] Figure 2 is a prediction result graph of a corn crop in a crop growth model in the application (a represents a yield result, b represents a growth period result, the horizontal coordinate represents a measured value, and the vertical coordinate represents a simulated value);

[0044] Figure 3 is a prediction result graph of a wheat crop in a crop growth model in the application (a represents a yield result, b represents a growth period result, the horizontal coordinate represents a measured value, and the vertical coordinate represents a simulated value);

[0045] Figure 4Fig. 1 is a prediction result graph of a rice crop in the present application (a represents yield results, b represents growth period results, the horizontal coordinate represents the measured value, and the vertical coordinate represents the simulated value) in the crop growth model;

[0046] Figure 5 Fig. 4 is an effect graph of the yield of a corn crop in the present application by a random forest model to reverse the crop growth model (a represents the training set effect, b represents the test set effect, the horizontal coordinate represents the simulated yield of the crop growth model, and the vertical coordinate represents the yield reversed by the random forest model);

[0047] Figure 6 Fig. 5 is an effect graph of the yield of a wheat crop in the present application by a random forest model to reverse the crop growth model (a represents the training set effect, b represents the test set effect, the horizontal coordinate represents the simulated yield of the crop growth model, and the vertical coordinate represents the yield reversed by the random forest model);

[0048] Figure 7 Fig. 6 is an effect graph of the yield of a rice crop in the present application by a random forest model to reverse the crop growth model (a represents the training set effect, b represents the test set effect, the horizontal coordinate represents the simulated yield of the crop growth model, and the vertical coordinate represents the yield reversed by the random forest model);

[0049] Figure 8 Fig. 7 is a cultivation decision result corresponding to the target yield of a corn crop in the present application;

[0050] Figure 9 Fig. 8 is a cultivation decision result corresponding to the target yield of a wheat crop in the present application;

[0051] Figure 10 Fig. 9 is a cultivation decision result corresponding to the target yield of a rice crop in the present application. DETAILED DESCRIPTION

[0052] The present application will be further described below in conjunction with the drawings. The following examples are only used to more clearly illustrate the technical solutions of the present application, and cannot be used to limit the protection scope of the present application.

[0053] As shown in Fig. 1, a precision cultivation decision method for grain crops includes the following steps: Figures 1 to 10 S1, obtain cultivation-related data of all stations in the target region from 2004 to 2023, wherein the target region is China (Hong Kong, Macau and Taiwan data are temporarily missing), and the cultivation-related data includes meteorological data, soil data and management measure data. The meteorological data comes from the China Meteorological Administration Land Data Assimilation System (CLDAS-V2.0, 0.0625° resolution), which includes daily maximum temperature, daily minimum temperature, daily precipitation and daily radiation data.

[0054]

[0055] ​Soil data comes from the soil database of Sun Yat-Sen University (1km resolution, 0-100cm depth range layered data), which includes soil bulk density, pH value, clay, silt, sand content, organic carbon content and cation exchange capacity.

[0056] Management measure data comes from all monitoring sites in public literature, which includes latitude and longitude, year, sowing date, harvesting date, planting density, fertilizer amount, fertilizer time, irrigation amount, irrigation time and yield.

[0057] S2, Because the cultivation-related data in S1 has large resolution in spatial scale, it has limitations and is not conducive to high-precision prediction. Therefore, this step processes the weather data by bilinear interpolation method to obtain a 1km x 1km resolution weather data set, and merges it with the soil data and management measure data into a 1km x 1km resolution grid data set, realizing the unification of scale, which helps to significantly improve the regional adaptability and precision of model simulation in subsequent processes.

[0058] S3, Because the crop variety parameters are numerous and interact with each other, it is extremely challenging to identify the key parameters that have a global dominant effect on yield and growth period in a highly heterogeneous spatial environment, and to overcome the nonlinear coupling effect between parameters. Therefore, this step uses the grid data set and the preset variety parameter set as input data, and uses the random forest model and the crop growth model to determine the several key variety parameters that have the greatest influence on yield and growth period. Specifically, S3 includes the following steps;

[0059] S301, Construct a variety parameter set M{A i ,B i ,C i ,..N i}, each variety parameter is set to a random distribution within the preset range; A to N represent variety parameters, and i represents the sample number. According to experience, the value range of each variety parameter is preset, and the variety parameter set with a sample size of 10000 is obtained by random distribution.

[0060] S302, Select the grid data set of 10000 grids in S2, and use the 10000-sample variety parameter set as input data to simulate 10000 simulated yields and simulated growth periods by the crop growth model. That is, one grid corresponds to one set of variety parameters, that is, one set of simulation results. In this example, the crop growth model is the APSIM model.

[0061] S303, based on the result of S302, the importance function in the random forest model is used to analyze the importance of the variety parameters on the simulated yield and the simulated growth period, and then the four key variety parameters with the largest influence on each crop are selected according to the influence size. Specifically, the key variety parameters of corn are tt_emerg_to_endjuv (accumulated temperature required from crop emergence to juvenile stage end), tt_flag_to_flower (accumulated temperature required from booting to flowering stage), tt_flower_to_maturity (accumulated temperature required from flowering to physiological maturity stage), and RUE (radiation use efficiency).

[0062] The key variety parameters of wheat are vern_sens (vernalization sensitivity coefficient), photop_sens (photoperiod sensitivity coefficient), tt_emergence (accumulated temperature required from sowing to emergence), and tt_end_of_juvenile (accumulated temperature required from emergence to juvenile stage end).

[0063] The key variety parameters of rice are DVRJ (juvenile stage daily development rate), DVRI (photoperiod sensitive stage daily development rate), DVRP (spike development stage daily development rate), and DVRR (grain filling and maturation stage daily development rate).

[0064] The APSIM model based on the key variety parameters is strictly calibrated using the observation data of the representative station yield covering the target area. As shown in Figures 2 to 4 , the results show that the model yield and growth period simulation effect is good, and the R 2 reaches 0.91-0.99, which fully verifies the effectiveness of the selected key parameters and the strong adaptability of the model in the target area. For non-important variety parameters, the optimal value is selected by default, and the APSIM model is adjusted using the measured data to determine the optimal value of the four variety parameters.

[0065] S4, the mapping relationship between the key variety parameters and the meteorological data and soil data in the grid data set is constructed using the random forest model, and the key variety parameters of each grid in the target area are obtained. The traditional method can only determine a set of parameters for one planting area, while this step also performs a downscaling operation on the key variety parameters to obtain the key variety parameters of each grid in the whole country, thereby providing a basis for subsequent high-precision prediction. Specifically, S4 includes the following steps:

[0066] S401, the randomForest function in the random forest model is used to construct the mapping relationship between the key variety parameters and the meteorological data and soil data in the grid data set.

[0067] S402, using the predict function in the random forest model to predict the key variety parameters, to obtain the key variety parameters of each grid in the target area.

[0068] S5, since S2-S4 has carried out grid processing on the relevant data, the data volume has been exponentially increased, and it is necessary to process the mapping relationship of massive grid data and multiple crop and variety parameters. Each grid has a unique combination of environmental factors (climate and soil), and there is a highly nonlinear and spatial non-stationary complex relationship between these factors and variety parameters. The predicted parameter combination not only needs to be statistically optimal, but also must meet the logical constraints of crop physiological processes (such as the order of accumulated temperature in the development stage and the rationality of the rate) to avoid physically unfeasible parameter values. Therefore, this step takes the key variety parameters, meteorological data and soil data of each grid in the target area as input data, and uses the random forest model and the crop growth model to obtain the sowing date and planting density corresponding to the target yield of each grid. Specifically, S5 includes the following steps:

[0069] S501, input the key variety parameters, meteorological data and soil data of each grid in the target area into the crop growth model to obtain a simulation data set containing the growth period, sowing date, planting density, daily yield and total yield; the simulation data set has the following characteristics: 1) spatial and temporal resolution: the time resolution is daily scale (statistically annual scale to facilitate AI modeling), and the spatial resolution is 1km x 1km; 2) regional division: the results are generated according to the crop planting area: corn division: Northeast Corn Belt (NEC), North China Corn Belt (NCP), Northwest Corn Belt (NWC), Southwest Corn Belt (SWC); wheat division: North China Wheat Belt (NC), North China Wheat Belt (NCP), Southwest Wheat Belt (SWC), Yangtze River Middle and Lower Reaches Wheat Belt (YRB); rice division: North China Rice Belt (NC), South China Rice Belt (SC), Southwest Rice Belt (SWC), Yangtze River Middle and Lower Reaches Rice Belt (YRB).

[0070] S502, to determine the optimal planting management scheme, a management measure set Y{a j ,b j ,c j ,d j ,......,n jThe planting density and sowing date are set using a random distribution within a preset range, while other management measures default to the local optimal values; a to n represent management measures, and j represents the sample size. Based on experience, the value ranges for each planting density and sowing date are preset, and other cultivation measures default to the cultivation conditions of local high-yield fields. Each partition obtains a scenario parameter set with a sample size of 5000 through random distribution. This sample design ensures the representativeness of the scenario combination and can comprehensively cover the possible value ranges of each parameter. Specifically, the value ranges for planting density and sowing date are shown in Table 1.

[0071] Table 1. Range of values ​​for planting density and sowing date of major crops

[0072]

[0073] S503. A random forest model is used to construct a mapping relationship between the simulated dataset and the scenario parameter set, achieving a fast and accurate mapping from multi-dimensional environmental-management factors to output indicators. For example... Figures 5 to 7 As shown, this step divides the training and test sets in a 7:3 ratio to ensure spatial representativeness. A random forest is used with 500 decision trees. The maximum depth of a single tree is determined to be 15 using grid search. The node splitting criterion is variance reduction. Performance optimization: Ten-fold cross-validation is used to adjust hyperparameters. The final test set R... 2 The accuracy reached 0.84-0.91. While maintaining over 90% of the prediction accuracy of the mechanistic model, this model improves computational efficiency by approximately 200 times (the APSIM model requires approximately 7 seconds to simulate a single point over 20 years, while the model proxy processing time is approximately 0.035 seconds), providing a reliable intelligent tool for regional-scale agricultural production decision-making.

[0074] This step deeply integrates the physical interpretability advantage of the mechanistic model (APSIM) with the efficient computing power of machine learning, solving the dual bottlenecks of "low computational efficiency" of traditional crop models in large-scale applications and "insufficient mechanistic interpretability" of pure data-driven models.

[0075] S504, obtain the sowing date and planting density corresponding to each grid target yield by using the mapping relationship of the simulation data set and the scenario parameter set. Obviously, this step effectively captures the nonlinear relationship between multi-dimensional environmental factors and variety parameters, and realizes efficient processing of high-dimensional feature space and huge sample size. In the prediction process, through feature importance analysis, the physical rationality and regional specificity of the parameter combination are indirectly guaranteed, and a 1kmx1km three-crop key variety parameter database covering the target area is successfully established. The core value of the database lies in that it completely solves the key bottleneck problem that the traditional uniform parameters in a large area cannot accurately reflect the local environmental differences ('unfit to the environment'), and provides essential basic data support for subsequent high-precision and large-scale crop growth process simulation and yield prediction.

[0076] The application can also support global optimization and spatialization decision output. The management strategy optimization engine: taking yield maximization as the goal, performing global optimization in the full variable space (sowing date x planting density); using full-factor combination experimental design (non-heuristic algorithm), relying on the high-performance computing platform of China Agricultural University to realize million-level scenario parallel computing, 100% guaranteeing to obtain the global optimal solution, and the solution set is not affected by random seeds, having absolute stability.

[0077] As shown in Figures 8 to 10 , the 1km grid level decision layer generation: using the ArcGIS spatial analysis engine, accurately matching the optimization solution set to the 1km grid; outputting multi-band GeoTIFF grid: band 1: optimal sowing day (day of year); band 2: recommended density (plants / m 2 ); band 3: expected yield potential (kg / ha); constructing a WebGIS intelligent decision platform to support instant extraction of parameter combinations according to administrative divisions / geographical coordinates, directly guiding field practice.

[0078] Based on the same inventive concept, the application also provides a precision cultivation decision system for grain crops, comprising:

[0079] An acquisition module is configured to acquire cultivation-related data of all stations in a target area, wherein the cultivation-related data includes meteorological data, soil data and management measure data;

[0080] A preprocessing module is configured to perform downscaling processing on the meteorological data by using a bilinear interpolation method, and combine the soil data and the management measure data into a grid data set with a resolution of 1kmx1km;

[0081] A parameter determination module is configured to use a random forest model and a crop growth model to determine a plurality of key variety parameters with the greatest influence on yield and growth period, by taking the grid data set and a preset variety parameter set as input data;

[0082] A parameter prediction module is configured to construct a mapping relationship between a key variety parameter and meteorological data and soil data in a grid dataset by using a random forest model, and obtain the key variety parameter of each grid in a target region;

[0083] A decision generation module is configured to take the key variety parameter, meteorological data and soil data of each grid in the target region as input data, and obtain a sowing date and a planting density corresponding to a target yield of each grid by using a random forest model and a crop growth model.

[0084] Based on the same inventive concept, the application further provides a precision cultivation decision device for grain crops, characterized by comprising a processor and a memory, the memory is configured to store a computer program, and the processor is configured to execute the computer program to realize the steps of the above method.

[0085] Based on the same inventive concept, the application further provides a computer readable and writable storage medium, characterized by storing a computer program, and the computer program is executed by a processor to realize the above method.

[0086] The above is only a preferred embodiment of the application, and it should be pointed out that for those skilled in the art, without departing from the technical principles of the application, a number of improvements and modifications can be made, and these improvements and modifications should also be considered as the protection scope of the application.

Claims

1. A precision cultivation decision method for food crops, characterized by, comprise meteorological data, soil data and management measure data; The meteorological data is down-scaled by a bilinear interpolation method, and is combined with the soil data and the management measure data into a grid data set with a resolution of 1 km x 1 km; The grid data set and a preset variety parameter set are taken as input data, and a random forest model and a crop growth model are used to determine a plurality of key variety parameters that have the greatest influence on yield and growth period importance; A mapping relationship between the key variety parameters and meteorological data and soil data in the grid data set is constructed by using the random forest model, and the key variety parameters of each grid in the target region are obtained. The grid data set and a preset variety parameter set are taken as input data, and a random forest model and a crop growth model are used to determine a plurality of key variety parameters that have the greatest influence on yield and growth period importance, comprising the following steps: A variety parameter set is constructed, and each variety parameter is randomly distributed in a preset range to set its value; 2. The method for precision cultivation decision of grain crops according to claim 1, characterized in that, An equal number of variety parameter sets and data sets are selected to be input into a crop growth model to obtain simulated yield and simulated growth period; A random forest model is used to analyze the importance of variety parameters on simulated yield and simulated growth period, and a plurality of key variety parameters with the greatest influence are selected. The mapping relationship between the key variety parameters and meteorological data and soil data in the grid data set is constructed by using a randomForest function in the random forest model; The key variety parameters are predicted by using a predict function in the random forest model, and the key variety parameters of each grid in the target region are obtained.

3. The method for precision cultivation decision of grain crops according to claim 1, characterized in that, The key variety parameters, meteorological data and soil data of each grid in the target region are taken as input data, and a random forest model and a crop growth model are used to obtain sowing dates and planting densities corresponding to the target yield of each grid, comprising the following steps: The key variety parameters, meteorological data and soil data of each grid in the target region are input into a crop growth model to obtain a simulated data set containing growth period days, sowing dates, planting densities, daily yield and total yield; A management measure set is constructed, wherein planting density and sowing date are randomly distributed in a preset range to set their values, and the remaining management measures are set to default local optimal values; 4. The method for precision cultivation decision of grain crops according to claim 1, characterized in that, A mapping relationship between the simulated data set and the scenario parameter set is constructed by using a random forest model; Sowing dates and planting densities corresponding to the target yield of each grid are obtained by using the mapping relationship between the simulated data set and the scenario parameter set. The crop growth model is an APSIM model.

6. The method according to claim 1, wherein ​ 5. The method for precision cultivation decision of grain crops according to claim 1, characterized in that, ​ ​ The key variety parameters of corn include accumulated temperature required from crop emergence to the end of the juvenile stage, accumulated temperature required from booting to flowering, accumulated temperature required from flowering to physiological maturity, and radiation use efficiency; The key variety parameters of wheat include spring sensitivity coefficient, photoperiod sensitivity coefficient, accumulated temperature required from sowing to emergence, and accumulated temperature required from emergence to the end of the juvenile stage; The key variety parameters of rice include daily development rate in the juvenile stage, daily development rate in the photoperiod sensitive stage, daily development rate in the panicle development stage, and daily development rate in the grain filling and maturation stage.

7. The method for precision cultivation decision of grain crops according to claim 1, characterized in that, The meteorological data includes daily maximum temperature, daily minimum temperature, daily precipitation, and daily radiation data; The soil data includes soil bulk density, pH value, clay content, silt content, sand content, organic carbon content, and cation exchange capacity; The management measure data includes latitude and longitude, year, sowing date, harvesting date, planting density, fertilizer amount, fertilizer time, irrigation amount, irrigation time, and yield.

8. A precision cultivation decision system for food crops, characterized by, The method comprises the following steps: An acquisition module is configured to acquire cultivation-related data of all stations in a target region, wherein the cultivation-related data includes meteorological data, soil data, and management measure data; A preprocessing module is configured to perform downscaling processing on the meteorological data by using a bilinear interpolation method, and combine the meteorological data, the soil data, and the management measure data into a grid data set with a resolution of 1 km x 1 km; A parameter determination module is configured to determine, by using a random forest model and a crop growth model, a plurality of key variety parameters that have the greatest influence on yield and growth period, by taking the grid data set and a preset variety parameter set as input data; A parameter prediction module is configured to construct a mapping relationship between the key variety parameters and the meteorological data and the soil data in the grid data set by using a random forest model, and obtain the key variety parameters of each grid in the target region; A decision generation module is configured to obtain sowing dates and planting densities corresponding to target yields of each grid in the target region by using a random forest model and a crop growth model, by taking the key variety parameters, the meteorological data, and the soil data of each grid in the target region as input data.

9. A precision cultivation decision device for food crops, characterized by, The computer readable storage medium stores a computer program, and the processor executes the computer program to implement the steps of the method of claim 1.

10. A computer readable and writable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the processor executes the computer program to implement the steps of the method of claim 1.

Images