Calibration method for corn and soybean strip-shaped composite planting model
By acquiring experimental field data and using elite genetic algorithms to calibrate the Aqua Crop model, the problem of unscientific field configuration in traditional maize-soybean intercropping was solved, realizing intelligent calibration of the maize-soybean strip intercropping model, improving yield and economic benefits, and supporting mechanized planting.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-25
- Publication Date
- 2026-04-21
AI Technical Summary
Traditional corn-soybean intercropping has unscientific field configurations, with a large corn-soybean row ratio, low planting density, poor light conditions for soybeans (which are low-lying crops), low total yield, low land equivalent ratio, poor economic benefits, and difficulty in achieving mechanization.
By acquiring experimental field data from the Internet, the Aqua Crop model was calibrated using an elite genetic algorithm, features were selected, and model calibration intervals were set to verify the simulation effect of the model under different conditions, thus realizing the intelligent calibration of the corn-soybean strip intercropping model.
It improved the calibration effect and practicality of the corn-soybean strip intercropping model, realized the optimal decision-making for multi-objective production management, increased total yield and economic benefits, and supported mechanized planting.
Smart Images
Figure CN121890472A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of agricultural planting technology, specifically a calibration method for a corn-soybean strip intercropping model. Background Technology
[0002] The soybean-corn strip intercropping model is an innovative planting method that combines the nitrogen-fixing and soil-nourishing effects of soybeans with the edge-row effect of corn, bringing numerous benefits to agricultural production. Firstly, this planting model helps improve soil conditions and fertility. Soybeans' nitrogen-fixing function provides ample nitrogen to the soil, while the edge-row effect of corn allows for better utilization of soil nutrients, thus increasing soil fertility. Secondly, this planting method utilizes land space, offering advantages such as ventilation, light penetration, water retention, and shading, achieving synergistic crop growth and a double harvest in one season. Finally, according to Xia Longteng, a professional technician from the Production Department of the Yongzhou Citrus Research Institute, the institute applied for approximately 1,000 mu (about 67 hectares) of soybean-corn strip intercropping area this year, with corn yielding over 800 jin (about 400 catties) per mu and soybean yielding 200 jin (about 100 catties) per mu. This fully demonstrates the high efficiency and economic benefits of the soybean-corn strip intercropping model.
[0003] Intercropping of corn and soybean has a long history, but the traditional field configuration of corn-soybean intercropping is extremely unscientific. The corn-soybean row ratio is too large, the planting density is too low, the soybean crop in the lower position has poor light conditions, the total yield is not high, the land equivalent ratio is low, the economic benefits are poor, and it is difficult to achieve mechanization.
[0004] Therefore, given the extremely limited per capita arable land resources in China, innovating and developing optimal production through strip intercropping of corn and soybeans is of great significance for developing modern agriculture and ensuring national food and oil security.
[0005] To address the problems raised in the background art, those skilled in the art have proposed a calibration method for a corn-soybean strip intercropping model. Summary of the Invention
[0006] To address the aforementioned technical problems, this invention provides a calibration method for a corn-soybean strip intercropping model. This method solves the problems of unscientific field configuration in traditional corn-soybean intercropping, excessively high corn-soybean row ratio, low planting density, poor light conditions for low-lying soybeans, low total yield, low land equivalent ratio, poor economic benefits, difficulty in mechanization, and inability to achieve optimal corn-soybean strip intercropping.
[0007] A calibration method for a corn-soybean strip intercropping model includes the following steps:
[0008] S1. First, obtain the corn-soybean strip intercropping data of the experimental field from the Internet, then perform feature filtering on the planting data, and finally set the filtered data as the dataset;
[0009] S2. Next, based on the screening results, the crop parameters of corn-soybean in the Aqua Crop model are calibrated using the elite genetic algorithm. The corresponding decision variables, objective functions and other parameters in the algorithm are determined, and the calibration efficiency of the algorithm under different objective function conditions is compared and analyzed to achieve efficient automatic calibration of corn-soybean model parameters.
[0010] S3. Set the model calibration interval values, and then substitute the calibrated Aqua Crop model parameters into the model calibration interval to verify and evaluate the model's simulation effect on maize-soybean growth and development, water and fertilizer use, and meteorological factor changes under different conditions in the Xiliaohe Plain. When the simulation effect matches the model calibration interval, the model is suitable for the study area. When the simulation effect does not match the model calibration interval, detect the cause, correct the cause, and repeat the above steps until the model is suitable for the study area.
[0011] S4. Finally, complete the calibration of the corn and soybean strip intercropping model.
[0012] Preferably, in step S1, the feature selection is divided into junk / useless features, weak features, and relevant features.
[0013] Preferably, the feature screening steps are as follows: first coarse screening followed by fine screening, first screening out junk / useless features, and then performing detailed screening on weak features and relevant features; the detailed screening steps are as follows: missing rate screening, variance selection, constant value proportion screening, IV value screening, PSI screening (not necessary), collinearity screening, significance screening, and coefficient sign consistency screening.
[0014] Preferably, based on maize-soybean strip intercropping, high-resolution meteorological input data is generated by interpolating environmental temperature, humidity, soil temperature, soil moisture, light intensity, carbon dioxide concentration, and rainfall collected by smart monitoring small weather stations, as well as government meteorological data. Then, AquaCrop, GIS, and multi-objective optimization algorithms are combined to construct regional-scale simulation optimization models of the growth and environment of the maize-soybean strip intercropping system under different typical year conditions. This aims to explore the optimal production technology in the Xiliaohe Plain when considering multiple objectives such as key decisions in the production management of the maize-soybean strip intercropping system.
[0015] Compared with the prior art, the present invention has the following beneficial effects:
[0016] This invention couples a corn-soybean model with a genetic algorithm to achieve rapid and automatic calibration of model parameters, realizing the intelligence of the calibration of the corn-soybean strip intercropping model. By verifying the simulation effect of the Aqua Crop model on corn-soybean growth and water and fertilizer utilization under different conditions, the practicality of the model is improved, thereby improving the calibration effect. At the same time, by setting the model calibration interval values, the simulation effect is further verified, further improving the calibration effect of the model, so as to achieve the optimal production technology for multiple objectives such as key decision-making in corn-soybean strip intercropping production management. Attached Figure Description
[0017] Figure 1 This is a flowchart of the calibration method for the corn-soybean strip intercropping model of the present invention;
[0018] Figure 2 This is a flowchart illustrating the detailed screening steps of the present invention. Detailed Implementation
[0019] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.
[0020] like Figure 1 and Figure 2 As shown:
[0021] Example: This invention provides a calibration method for a corn-soybean strip intercropping model, comprising the following steps:
[0022] S1. First, obtain the corn-soybean strip intercropping data of the experimental field from the Internet, and then perform feature screening on the planting data. The feature screening is divided into junk / useless features, weak features and relevant features. Finally, set the screened data as a dataset.
[0023] S2. Next, based on the screening results, the crop parameters of corn-soybean in the Aqua Crop model are calibrated using the elite genetic algorithm. The corresponding decision variables, objective functions and other parameters in the algorithm are determined, and the calibration efficiency of the algorithm under different objective function conditions is compared and analyzed to achieve efficient automatic calibration of corn-soybean model parameters.
[0024] S3. Set the model calibration interval values, and then substitute the calibrated Aqua Crop model parameters into the model calibration interval to verify and evaluate the model's simulation effect on maize-soybean growth and development, water and fertilizer use, and meteorological factor changes under different conditions in the Xiliaohe Plain. When the simulation effect matches the model calibration interval, the model is suitable for the study area. When the simulation effect does not match the model calibration interval, detect the cause, correct the cause, and repeat the above steps until the model is suitable for the study area.
[0025] S4. Finally, complete the calibration of the corn and soybean strip intercropping model.
[0026] As can be seen from the above, this invention achieves rapid and automatic calibration of model parameters by coupling the corn-soybean model with a genetic algorithm, realizing the intelligence of the calibration of the corn-soybean strip intercropping model. Furthermore, by verifying the simulation effect of the Aqua Crop model on corn-soybean growth and water and fertilizer utilization under different conditions, the practicality of the model is improved, thereby enhancing the calibration effect of the model.
[0027] Specifically, the feature selection steps are as follows: first, coarse screening followed by fine screening. First, discard junk / useless features, and then perform detailed screening on weak and relevant features. The detailed screening steps are as follows: missing rate screening, variance selection, constant value proportion screening, IV value screening, PSI screening (not necessary), collinearity screening, significance screening, and coefficient sign consistency screening.
[0028] As can be seen from the above, by setting the model calibration interval values, the simulation effect is further verified, and the calibration effect of the model is further improved, so as to achieve the optimal production technology when multiple objectives such as key decision-making in corn-soybean strip intercropping production management are met.
[0029] Application examples
[0030] To explore the applicability of this corn-soybean strip intercropping model, 20 experimental fields were selected. One group (experimental group) was planted using the calibrated model, while the other group (control group) used the current corn-soybean intercropping method. The results are shown in the table below:
[0031] Overall effectiveness (%) experimental group 87.6 control group 66.8
[0032] As can be seen from the above, the experimental group performed significantly better than the control group, indicating that the planting model of this calibration method is effective for strip intercropping of corn and soybeans and is suitable for large-scale promotion and application.
[0033] The embodiments of the present invention are given for the purposes of illustration and description. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.
Claims
1. A calibration method for a corn-soybean strip intercropping model, characterized in that: Includes the following steps: S1. First, obtain the corn-soybean strip intercropping data of the experimental field from the Internet, then perform feature filtering on the planting data, and finally set the filtered data as the dataset; S2. Next, based on the screening results, the crop parameters of corn-soybean in the Aqua Crop model are calibrated using the elite genetic algorithm. The corresponding decision variables, objective functions and other parameters in the algorithm are determined, and the calibration efficiency of the algorithm under different objective function conditions is compared and analyzed. S3. Set the model calibration interval values, and then substitute the calibrated Aqua Crop model parameters into the model calibration interval to verify and evaluate the model's simulation effect on maize-soybean growth and development, water and fertilizer use, and meteorological factor changes under different conditions in the Xiliaohe Plain. When the simulation effect matches the model calibration interval, the model is suitable for the study area. When the simulation effect does not match the model calibration interval, detect the cause, correct the cause, and repeat the above steps until the model is suitable for the study area. S4. Finally, complete the calibration of the corn and soybean strip intercropping model.
2. The calibration method for a corn-soybean strip intercropping model as described in claim 1, characterized in that: In step S1, the feature selection is divided into junk / useless features, weak features, and relevant features.
3. The calibration method for a corn-soybean strip intercropping model as described in claim 2, characterized in that: The feature selection process is as follows: first, a coarse screening followed by a fine screening. First, discard junk / useless features, and then perform a detailed screening on weak and relevant features. The detailed screening steps are as follows: missing rate screening, variance selection, constant value proportion screening, IV value screening, PSI screening (not necessary), collinearity screening, significance screening, and coefficient sign consistency screening.