Method and system for determining production mode for maximizing crop yield

Abstract

The invention discloses a method and a system for determining a production mode for maximizing crop yield. The method comprises the following steps: acquiring objective factor data which continuously influence the crop yield for many years; according to the objective factor data influencing the crop yield continuously for many years, predicting the objective factor data influencing the crop yield in the next year to obtain a predicted value of the objective factor data influencing the crop yield in the next year; determining a subjective factor prediction value influencing the crop yield in the next year according to the prediction value of the objective factor data influencing the crop yield in the next year and the crop growth prediction model by taking crop yield maximization as a target; wherein the crop growth prediction model is a multiple linear regression model between the crop yield and objective and subjective factors influencing the crop yield. And the total power of agricultural machinery and the farmland irrigation area are effectively optimized while the crop yield is ensured to be maximized.

Description

Technical Field

[0001] The present invention relates to the field of agricultural production technology, and in particular to a method and system for determining a production mode for maximizing crop yield. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In the process of grain crop production, agricultural machinery is needed to carry out operations such as planting and plant protection. The agricultural machinery power required for crop production can reflect certain planting density, plant protection effects, etc., and thus affect crop yields.

[0004] In order to ensure the normal growth of grain crops, crops need to be irrigated in a timely manner. The irrigated area of ​​arable land directly reflects the degree of agriculture's dependence on water resources, and the size of the irrigated area of ​​arable land can also affect the growth and yield of crops.

[0005] Currently, there are methods for determining agricultural machinery power and arable land irrigation area based on crop yield. However, when determining mechanical power based on crop yield, the current method mainly relies on a separate analysis of mechanical power based on factors such as planting density, or a separate analysis of arable land irrigation area based on crop yield. However, crop yield is affected by both mechanical power and arable land irrigation area. When mechanical power and arable land irrigation area are analyzed separately, it cannot be guaranteed that the determined mechanical power and arable land irrigation area will maximize crop yield. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a method and system for determining a production mode that maximizes crop yield, which effectively optimizes the total power of agricultural machinery and the irrigation area of ​​arable land while ensuring the maximization of crop yield.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] First, a method for determining a production mode that maximizes crop yield is proposed, including:

[0009] Obtain data on objective factors affecting crop yields for many consecutive years;

[0010] Based on the objective factor data affecting crop yields for many consecutive years, the objective factor data affecting crop yields for the next year are predicted to obtain the predicted value of the objective factor data affecting crop yields for the next year;

[0011] With the goal of maximizing crop yield, the predicted values ​​of subjective factors affecting crop yield in the next year are determined based on the predicted values ​​of objective factors affecting crop yield in the next year and the crop growth prediction model;

[0012] Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

[0013] Furthermore, subjective factors affecting crop yield include the irrigated area of ​​cultivated land and the total power of agricultural machinery.

[0014] Furthermore, with the goal of maximizing crop yield, the predicted values ​​of subjective factors affecting crop yield in the next year are determined based on the predicted values ​​of objective factor data affecting crop yield in the next year, the crop growth prediction model, and the subjective factor prediction constraints;

[0015] Among them, the subjective factor prediction constraints include crop yield increase constraints, agricultural machinery total power variation constraints and cultivated land irrigation area constraints.

[0016] Furthermore, the agricultural machinery total power variation constraint includes that the agricultural machinery total power is greater than or equal to 0 and the error between the agricultural machinery total power of the next year and the agricultural machinery total power of the current year is less than or equal to an error threshold.

[0017] Furthermore, the trained objective factor prediction model is used to predict the objective factor data that will affect crop yields in the next year; wherein, the objective factor prediction model takes the objective factor data that have affected crop yields for many consecutive years as input and the predicted value of the objective factor data that will affect crop yields in the next year as output, and is constructed using an autoregressive moving average model.

[0018] Furthermore, data on various factors affecting crop yields over many years and their corresponding crop yield data are obtained;

[0019] Based on the data of each factor and crop yield data, determine the correlation between each factor and crop yield;

[0020] The factors with correlation greater than the set value are selected as the main factors affecting crop yield, which include objective factors and subjective factors.

[0021] Secondly, a production method determination system for maximizing crop yield is proposed, including:

[0022] A data acquisition unit is used to obtain objective factor data affecting crop yields for many consecutive years;

[0023] An objective factor prediction unit is used to predict the objective factor data affecting crop yield in the next year based on the objective factor data affecting crop yield in consecutive years, and obtain the predicted value of the objective factor data affecting crop yield in the next year;

[0024] A subjective factor determination unit is used to determine the predicted value of the subjective factor affecting the crop yield in the next year based on the predicted value of the objective factor data affecting the crop yield in the next year and the crop growth prediction model, with the goal of maximizing the crop yield;

[0025] Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

[0026] In a third aspect, a computer device is provided, comprising:

[0027] a processor adapted to execute a computer program;

[0028] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the method for determining a production mode for maximizing crop yield proposed in the first aspect is implemented.

[0029] In a fourth aspect, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executed by a method for determining a production mode for maximizing crop yield proposed in the first aspect.

[0030] In a fifth aspect, a computer program product is proposed, which includes a computer program. When the computer program is executed by a processor, it implements the method for determining a production mode for maximizing crop yield proposed in the first aspect.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention proposes a method and system for determining a production method that maximizes crop yield. The method predicts the objective factor data affecting crop yield for the next year based on multiple consecutive years of objective factor data. Based on the predicted values ​​of the objective factor data affecting crop yield for the next year, the method determines the predicted values ​​of the subjective factors affecting crop yield for the next year based on a crop growth prediction model, with the goal of maximizing crop yield. The crop growth prediction model is a multiple linear regression model between crop yield and the objective and subjective factors affecting crop yield. By comprehensively analyzing the objective and subjective factors and considering the coupling relationships between them, the determined subjective factor prediction values ​​are made more accurate. When used to guide crop production, these subjective factor prediction values ​​can maximize crop yield.

[0033] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0035] Figure 1 A flow chart of a method for determining a production mode for maximizing crop yield disclosed in an embodiment;

[0036] Figure 2 The diagram for predicting the total area of ​​total crop failure disclosed in the embodiment;

[0037] Figure 3 The annual average temperature prediction map disclosed in the embodiment;

[0038] Figure 4 The annual average relative humidity prediction diagram disclosed in the embodiment;

[0039] Figure 5 This is a crop yield increase constraint diagram disclosed in the embodiment. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0043] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0044] Example 1

[0045] The growth of grain crops is closely related to climate change, environmental resources, etc. Factors such as uneven distribution of water resources, temperature fluctuations, and changes in precipitation can all affect grain production.

[0046] Water is essential for the growth and development of crops. It directly participates in their growth, development, and physiological metabolism, and participates in the growth process as a medium for material transport, synthesis, and transformation. Agricultural water consumption is primarily consumed for irrigation. Therefore, expanding irrigated arable land within certain limits, developing water-saving agriculture, selecting the most appropriate irrigation methods for crop cultivation, and improving water use efficiency in farmland are effective measures to alleviate water scarcity and maximize grain production under limited water resources. The following study examines the yields of the major crops wheat, rice, and corn under different irrigation methods, as well as their water utilization.

[0047] (1) The impact of different irrigation methods on wheat yield and water resource utilization.

[0048] In recent years, integrating cropping methods with water-saving irrigation has become a new research direction. Significant inter-annual differences in soil moisture between wheat cultivation using furrow and ridge planting and flat sowing have been observed. Ridge cultivation, as a rainwater harvesting method, not only increases soil water storage but also improves water use efficiency, thereby boosting crop yields. Water use efficiency of winter wheat can be improved while saving 30% of irrigation water. Under irrigation, furrow sowing consumes slightly more water, but yield increases significantly, with significantly higher water use efficiency than both ridge and flat sowing.

[0049] (2) The impact of different irrigation methods on rice yield and water resource utilization.

[0050] Direct seeding of rice is a new, highly efficient, and water-saving cultivation technique that can be categorized as dry direct seeding, wet direct seeding, and flooded direct seeding. Dry direct seeding involves mechanical row or hole seeding, often performed after dry land preparation and leveling. Wet direct seeding involves manual broadcasting, often performed when the field soil is saturated with water but free of standing water. Wet direct seeding typically uses germinated rice seeds, similar to the seed germination treatment used for traditional transplanting and water-raising seedlings, but dry rice seeds can also be used for direct seeding. Flooded direct seeding requires a shallow water layer in the field and is typically broadcast by large-scale aerial broadcasting. Dry rice seeds or seeds that have been soaked and germinated are used. Direct seeding saves significant water resources by eliminating the water-intensive process of soaking the field for transplanting. "Rainwater storage irrigation" offers the best water-saving and yield-increasing results; intermittent irrigation offers variable yield increases but better water-saving benefits; and "rainfall irrigation" offers moderate yield increases but good water-saving benefits.

[0051] (3) The impact of different irrigation methods on corn yield and water resource utilization.

[0052] In arid and semi-arid regions, drip irrigation can provide timely water supply for crops, increasing yields by 8% to 15% compared to Yellow River border irrigation and 10% to 15% compared to groundwater border irrigation. Drip irrigation also reduces water waste and improves crop water use efficiency, increasing it by 54.3% and 49.4% compared to Yellow River border irrigation and groundwater border irrigation, respectively. Shallow buried drip irrigation increases yields and water use efficiency compared to sub-mulch drip irrigation and traditional border irrigation. It not only saves water and increases productivity, but also avoids environmental pollution from residual film.

[0053] Greenhouse gas emissions are increasing atmospheric concentrations and accelerating global warming. Agricultural activities are a significant source of greenhouse gas emissions, and agricultural management practices such as cropping patterns, tillage systems, irrigation, and fertilization significantly impact these emissions. Compared to the conventional cropping system (CON), optimized cropping systems (OPT and NT) reduced nitrogen fertilizer and irrigation water inputs by 44% and 33% respectively, while maintaining yield stability and sustainability. By modifying the cropping system and combining optimized water and nitrogen management with WSI, WSII, WR, and ORG treatments, yield decreased by 22-61% compared to the CON treatment, but nitrogen fertilizer and irrigation water inputs decreased by 56-79% and 46-64%, respectively, while improving nitrogen fertilizer and irrigation water use efficiency by 56-190% and 11-57%, respectively. Indirect greenhouse gas emissions from agricultural inputs were the primary source of these emissions across all studied treatments, contributing 78-85% of net greenhouse gas emissions. Nitrogen fertilizer application and irrigation electricity consumption were the two main sources of indirect greenhouse gas emissions, accounting for 31-53% and 29-58% of indirect emissions, respectively, and 24-45% and 23-45% of total emissions, respectively. The greenhouse effect of N₂O emissions accounted for 15-22% of net greenhouse gas emissions across all treatments. Besides N₂O emissions, nitrogen fertilizer application, and irrigation electricity consumption, the other emission sources accounted for a combined 7-15% of net greenhouse gas emissions. These results indicate that soil N₂O emissions, ammonia fertilizer application, and irrigation electricity consumption are the three main sources of greenhouse gas emissions in agricultural production.

[0054] During the process of growing grain crops, agricultural machinery is needed to carry out operations, and crops need to be irrigated in a timely manner. The irrigated area of ​​arable land directly reflects the degree of agriculture's dependence on water resources. Its expansion may aggravate shortages or pollution, but efficient irrigation technology can alleviate the pressure; the total power of agricultural machinery indirectly affects water resources and ecology through energy consumption and land use.

[0055] Among them, the irrigated cultivated land area refers to the ratio of the cultivated land area that can be effectively supplemented with water through artificial irrigation facilities to the sown area; it reflects the ability to ensure the utilization of water resources in agricultural production and is an important indicator for measuring agricultural disaster resistance and modernization level.

[0056] The expansion of irrigated areas directly increases agricultural water demand. If irrigation water relies on groundwater or rivers, it can lead to ecological problems such as falling groundwater levels and river dry-ups. For example, excessive irrigation can cause severe groundwater funneling; unscientific irrigation practices (such as flooding) can lead to soil salinity accumulation, reducing the quality of arable land, especially in arid and rainless regions; and irrigation can introduce fertilizer and pesticide residues into water bodies, causing non-point source pollution. For example, drainage from rice field irrigation can lead to eutrophication of surrounding water bodies.

[0057] Total agricultural machinery power refers to the sum of the rated powers of all types of power machinery used in agricultural production. It reflects the level of mechanization and the intensity of investment in technological equipment in agricultural production. It is a key indicator for measuring production efficiency and labor substitution capacity, and can also influence planting density and plant protection effectiveness. Increases in total machinery power typically rely on energy sources such as diesel and electricity, directly contributing to greenhouse gas emissions. For example, diesel consumption by large agricultural machinery is a significant contributor to the agricultural carbon footprint. Frequent operation of heavy machinery can damage soil structure, reducing air permeability and water retention, and potentially disrupting field ecosystems, such as earthworm habitats. Mechanization is often combined with large-scale monoculture, which can increase the concentrated use of fertilizers and pesticides, exacerbating environmental pollution.

[0058] To achieve stable and high-yield growth of grain crops, realize ecological protection and sustainable development, achieve harmonious coexistence of agricultural production and the natural environment, and ensure maximum crop yield, this embodiment discloses a method for determining a production mode that maximizes crop yield, including:

[0059] Obtain data on objective factors affecting crop yields for many consecutive years;

[0060] Based on the objective factor data affecting crop yields for many consecutive years, the objective factor data affecting crop yields for the next year are predicted to obtain the predicted value of the objective factor data affecting crop yields for the next year;

[0061] With the goal of maximizing crop yield, the predicted values ​​of subjective factors affecting crop yield in the next year are determined based on the predicted values ​​of objective factors affecting crop yield in the next year and the crop growth prediction model;

[0062] Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

[0063] This embodiment first obtains data on various factors affecting crop yields over many years and their corresponding crop yield data;

[0064] Based on the data of each factor and crop yield data, determine the correlation between each factor and crop yield;

[0065] The factors with correlation greater than the set value are selected as the main factors affecting crop yield, which include objective factors and subjective factors.

[0066] Specifically, objective factors affecting crop yields include annual average temperature, crop failure area, and annual average relative humidity.

[0067] Subjective factors affecting crop yields include irrigated land area and total power of agricultural machinery.

[0068] The data obtained in this embodiment are all data of a certain set area, and the values ​​of the irrigated land area and the area with no harvest are the percentages of the area to the total sown area in the country.

[0069] This embodiment collects research related to agricultural development and food crop growth to determine the factors affecting crop yield, which are mainly climate factors, water and soil resources, and natural environment; from climate factors, water and soil resources, and natural environment factors, multiple factors affecting crop yield are selected, and these multiple factors include eight indicators: annual average temperature, annual sunshine length, annual average precipitation, annual average relative humidity, total power of agricultural machinery, irrigated arable land area, fertilizer application amount, and area of ​​complete crop failure.

[0070] The rise and fall of temperature affect the growth and development speed of grain crops and the length of their growth period, thereby affecting the yield of grain production crops; the length of daylight affects the intensity of crop photosynthesis, and the appropriate length of daylight ensures the normal development and growth of grain crops; precipitation provides the water needed for crop growth and affects the soil moisture conditions. Too much or too little precipitation can lead to floods and droughts, which are not conducive to crop growth; high relative humidity may lead to the occurrence and spread of pests and diseases, and low humidity may cause crops to suffer from water stress; the use of agricultural machinery improves grain production efficiency, expands the planting area, precise sowing and efficient harvesting increase crop yields, stabilizes production scale, reduces soil abandonment that may be caused by labor shortages, and the improvement of mechanization level enhances the adaptability of grain production to adverse climatic conditions; irrigation ensures the supply of water for the growth of grain crops, especially in arid and semi-arid areas, improves land utilization and crop production efficiency, adjusts and improves the functions of water conservancy and irrigation facilities, adapts to environmental changes caused by the intensification of global climate change, and ensures food security. Soil organic matter is one of the important indicators to measure the level of soil fertility. Through reasonable fertilization, soil fertility can be effectively improved and sufficient nutrients can be provided for the growth of grain crops. The total area of ​​crop failure refers to the sown area where crop yields are reduced by more than 80% due to natural disasters. It is an important indicator to measure the impact of natural disasters on crop growth and is of great significance to risk management and disaster prevention.

[0071] In this embodiment, the crop yield is characterized by the yield per unit area of ​​the crop.

[0072] After acquiring data on various factors affecting crop yields over the years and their corresponding crop yield data, this embodiment pre-processes the acquired data and uses the Pearson correlation coefficient algorithm to analyze the pre-processed data to determine the correlation between each factor and crop yield. Specifically:

[0073] The linear relationship between two variables is quantified by calculating their covariance and standard deviation. Its value ranges from -1 to 1, with r > 0 indicating a positive correlation, r indicating a negative correlation, and r = 0 indicating zero correlation. |r| indicates the degree of correlation between the two variables. The closer |r| is to 1, the higher the correlation and the closer the relationship. The formula is as follows:

[0074]

[0075] Among them, r represents the Pearson correlation coefficient, X i represents the i-th data point of variable X, Y i represents the i-th data point of variable Y, represents the mean of variable X, Represents the mean of variable Y, X is a factor data, and Y is crop yield data.

[0076] Regression analysis was conducted on the eight factors and crop yield data to examine the correlation between each factor and crop yield. The corresponding correlation coefficients (R) and significance points (P) were obtained, as shown in Table 1. Analysis of the correlation coefficients (R) and significance points (P) revealed that the strongest correlation between irrigated land area and grain crop yield was observed, followed by annual average temperature, crop failure area, annual average relative humidity, total agricultural machinery power, annual sunshine, and annual precipitation. There was no correlation between fertilizer use and crop yield. Factors with correlation coefficients (R) greater than 0.6 were identified as the primary factors influencing crop yield. These factors included irrigated land area, annual average temperature, crop failure area, annual average relative humidity, and total agricultural machinery power.

[0077] Analysis shows that water resources have the greatest impact on the growth of grain crops. Irrigation is the primary source of water for grain crops, and proper water management is crucial for ensuring healthy crop growth and high yields. Appropriate irrigation strategies should be implemented based on crop type, growth stage, and environmental conditions to ensure adequate and appropriate water supply. Suitable temperatures are also crucial for ensuring grain crop yields. Furthermore, in the event of natural disasters, effective disaster prevention measures should be implemented to minimize significant yield losses. Promoting agricultural mechanization and modernization will have a positive impact on the growth of grain crops.

[0078] Table 1 Influence coefficients of various factors on crop yield

[0079]

[0080]

[0081] Of the five main factors identified as influencing crop yield, annual average temperature and annual average relative humidity are related to the natural environment and have little human control. The area of ​​crop failure is closely related to natural disasters, the severity of which is not controlled by human factors, and human intervention is minimal in particularly severe natural disasters. Therefore, the area of ​​crop failure, annual average temperature, and annual relative humidity are considered objective factors. However, the area of ​​irrigated land and the total power of agricultural machinery are human-controllable and are considered subjective factors.

[0082] There is a multiple linear regression relationship between the main factors affecting crop yield and crop yield. This embodiment uses a multiple linear regression model to analyze crop yield and the main factors affecting crop yield and construct a crop growth prediction model.

[0083] First, we determine whether the model has collinearity and autocorrelation. The data results are shown in Table 2. As shown in Table 2, the VIF values ​​in the model are all less than 5, indicating that there is no collinearity between the factors. The DW value is 2.202, which is close to the number 2, indicating that there is no autocorrelation in the model. The model is good. Finally, the crop growth prediction model is determined as follows:

[0084] W j =α1A j +α2B j +α3C j +α4D j +α5E j +β

[0085] Where α1 is the annual average temperature coefficient, which is 64.286; α2 is the annual average relative humidity coefficient, which is 42.280; α3 is the total power coefficient of agricultural machinery, which is 763.785; α4 is the coefficient of cultivated land irrigation area, which is 12259.029; α5 is the coefficient of crop failure area, which is -1766.286; β is the linear regression constant, which is -5452.260. j is the year, A j is the annual mean temperature, B j is the annual average relative humidity, C j is the total power of agricultural machinery, D j is the irrigated land area, E j The area with no harvest.

[0086] Table 2 Linear regression analysis results

[0087]

[0088] Since the values ​​of objective factors are not affected by subjective factors, this embodiment uses a trained objective factor prediction model to predict the objective factor data that will affect crop yields in the next year. The objective factor prediction model takes the objective factor data that have affected crop yields for many consecutive years as input and outputs the predicted value of the objective factor data that will affect crop yields in the next year, and is constructed using an autoregressive moving average model (ARIMA).

[0089] like Figure 2 、 Figure 3 、 Figure 4 As shown, the embodiment of the present application constructs a prediction model for each objective factor respectively, and uses the historical data of each objective factor to predict the objective factor data for the next year.

[0090] The irrigated area of ​​cultivated land and the total power of agricultural machinery are affected by human factors. Strengthening the intelligentization of agricultural technology can effectively improve the growth of grain crops. Mechanized planting and the rational use of agricultural machinery can achieve precise monitoring and management of grain crop growth. Expanding the irrigated area of ​​cultivated land can reduce unstable crop growth caused by uneven rainfall or drought, reduce the risks brought by weather changes, and ensure that crops receive sufficient water during critical growth periods, thereby increasing yields. Irrigation water mainly comes from surface water and groundwater. Large-scale irrigation and improper irrigation methods can lead to a drop in groundwater levels, water shortages, and damage to ecosystems. Furthermore, the economic costs of establishing and maintaining irrigation systems are high. The expansion of irrigation area needs to consider the sustainability of water resources. Sustainable grain production can be achieved through scientific planning and management.

[0091] In order to maximize crop yield while achieving sustainable development of the ecological environment, this embodiment takes maximizing crop yield as the goal and determines the predicted value of the subjective factors affecting crop yield in the next year based on the predicted value of the objective factor data affecting crop yield in the next year, the crop growth prediction model, and the subjective factor prediction constraints.

[0092] Among them, the subjective factor prediction constraints include crop yield increase constraints, agricultural machinery total power variation constraints and cultivated land irrigation area constraints.

[0093] The crop yield increase constraint is: △W≥0, △W=W j -W j-1 , where W j is the crop yield in year j, W j-1 is the crop yield in year j-1, and △W is the increase in crop yield.

[0094] The constraint of irrigated land area is: 0≤D j ≤1.

[0095] like Figure 5As shown, within the shaded area, the values ​​of total agricultural machinery power and irrigated land area will both increase grain crop yields. Due to the speed of mechanization, the limited use of mechanization, and the scarcity of water resources, these values ​​cannot be increased indefinitely. Therefore, this embodiment imposes a limit on the increase in total agricultural machinery power. By selecting appropriate parameters and rationally planning the next year's production plan, grain crop yields can be increased.

[0096] The agricultural machinery total power variation constraint includes that the agricultural machinery total power variation constraint includes that the agricultural machinery total power is greater than or equal to 0 and the error between the agricultural machinery total power of the next year and the total power of the agricultural machinery of the current year is less than or equal to the error threshold, that is:

[0097] C j ≥0;

[0098] |C j -C j-1 1≤N;

[0099] Where C j is the total power of agricultural machinery in year j, C j-1 is the total power of agricultural machinery in year j-1, and N is the error threshold, preferably 0.05.

[0100] In this embodiment, the predicted values ​​of objective factors affecting crop yields for the next year are substituted into the crop growth prediction model. With the goal of maximizing crop yield, the model uses an intelligent learning algorithm to solve the problem, using crop yield increase constraints, agricultural machinery total power fluctuation constraints, and arable land irrigation area constraints as constraints. This algorithm obtains the predicted values ​​of subjective factors affecting crop yields for the next year, including the predicted values ​​of agricultural machinery total power and arable land irrigation area. These predicted values ​​of agricultural machinery total power and arable land irrigation area are used to guide crop production in the next year, maximizing crop yields while minimizing impacts on the ecological environment.

[0101] The following paragraphs analyze the model results by adding three variables to the above model: disaster-affected area, disaster-affected area, and water resources.

[0102] The losses caused by natural disasters on crop growth only consider the area of ​​crop failure, ignoring the area affected by the disaster and the area affected by the disaster. The water required for crop growth takes into account irrigation water and precipitation, ignoring the relationship between irrigation water and regional water resources. This example incorporates the area affected by the disaster, the area affected by the disaster, and water resources into data indicators. Representative regions are selected for optimization model application, and the specific analysis is as follows:

[0103] Rice, one of the major food crops, was selected for research. Rice is an aquatic plant and requires an adequate water supply during its growth phase. Even upland rice requires moist soil during critical periods. Rice thrives in warm temperatures, with an ideal growth range of 20-35°C, with a minimum temperature of 10°C. Rice also requires 6 to 8 hours of sunlight daily to promote photosynthesis and growth. Based on a 60-year spatiotemporal map of suitable rice distribution, the Northeast region was selected as a representative region. The Northeast region is located in a continental climate zone, with short, humid summers and long, cold winters, which restrict the rice planting cycle and growing environment. While it has abundant water resources, its distribution is highly uneven due to large elevation differences and narrow watersheds. The soil is nutrient-rich, but the nutrient distribution is uneven, which can lead to starvation and make sterilization difficult. Furthermore, prolonged freeze-thaw cycles can easily lead to soil salinization. Most areas in the Northeast region have low suitability for rice cultivation. This region was selected for model application, providing specific recommendations for optimizing agricultural production. This example illustrates a method for determining a production method to maximize crop yield.

[0104] Data on rice yield and related factors affecting rice yield in Northeast China over the past 15 years were collected, and the correlation between each factor and rice yield was analyzed. The results of the correlation analysis showed that the total power of agricultural machinery had a significant impact on rice yield, followed by the irrigated area of ​​arable land, disaster-stricken area, disaster-affected area, and annual average temperature. Annual precipitation and fertilizer application had no correlation with rice yield.

[0105] Table 3 Correlation analysis results between rice yield and various factors

[0106] R <![CDATA[R 2 ]]> F P Annual average temperature (℃) 0.586 0.343 6.783 0.022 Annual precipitation (mm) 0.195 0.038 0.514 0.486 Annual sunshine (h) 0.251 0.063 0.876 0.366 Annual average relative humidity (%) 0.209 0.044 0.594 0.454 Water resources (billion cubic meters) 0.505 0.255 4.459 0.055 Total power of agricultural machinery (10,000 kilowatts / 1,000 hectares) 0.899 0.808 54.599 0.000 Irrigated cultivated land area (%) 0.752 0.565 16.876 0.001 Affected area (percentage) 0.633 0.401 8.688 0.011 Disaster-affected area (percentage) 0.674 0.454 10.826 0.006 Fertilizer application (10,000 tons / 1,000 hectares) 0.187 0.035 0.469 0.505

[0107] The results indicate that improving rice yields in Northeast China primarily involves optimizing annual average temperature, irrigated area, total power for agricultural mechanization, and natural disaster prevention and control. Natural disaster prevention and control encompasses disaster-affected and disaster-prone areas, as well as water resources. Northeast China boasts low temperatures and long days, while traditional rice is a high-temperature, short-day crop. Optimizing rice yield under these temperature conditions requires careful consideration of variety breeding and selection. The breeding of new rice varieties in Northeast China emphasizes the cultivation and selection of their photothermal ecotypes. Varieties such as the Jijing and Tonghua series from Jilin Province and the Liaojing and Yanjing series from Liaoning Province exhibit excellent traits for high quality, high yield, and disease resistance, as well as cold tolerance, making them highly adaptable to low-temperature, long-day conditions. Selecting appropriate varieties for large-scale planting is an effective measure to address the low temperatures and long days of the Northeast region. Rice prefers moisture, but common irrigation methods, such as surface irrigation, consume a lot of water and hinder water recycling. Establishing an intelligent irrigation system can ensure that rice receives the appropriate amount of water at different growth stages. By integrating advanced sensing technology, data analysis, and automated control, it can avoid over- or under-irrigation of rice, further improving rice production efficiency and quality. Applying intelligent irrigation systems to accurately measure and supply the amount of water needed for rice growth will not only reduce water consumption and alleviate water scarcity in Northeast China, but also promote sustainable agricultural development. Natural disasters include drought, flooding, wind damage, hail, frost, heat damage, and cold damage. Droughts require the establishment of irrigation systems and the implementation of water-saving irrigation techniques. Floods require improved drainage systems, regularly clearing debris and silt from channels to ensure unobstructed water flow. Water gates and water pipes should be installed in channels to improve drainage efficiency and flexible control. Durable and corrosion-resistant materials should be used for drainage pipes. Modern intelligent technologies should be promoted to improve drainage system management efficiency and water resource utilization. Wind damage requires the construction of windbreaks, the reinforcement of agricultural facilities, and the use of ground covers to reduce wind erosion. Hailstorms require the installation of hail nets and shelters, and artificial hail suppression. Frost can be prevented by covering crops with plastic film. Heat damage requires timely irrigation to reduce temperatures, or the use of shade nets and other shading measures to reduce the direct impact of high temperatures on crops. Cold damage can be prevented by appropriate fertilization to enhance crop cold resistance. In the face of natural disasters, we can not only use the above human control measures, but also select and breed varieties to cultivate heat-resistant and cold-resistant varieties.

[0108] Enhancing agricultural mechanization includes the mechanization of agricultural infrastructure construction, the mechanization of product transportation and processing, the mechanization of production operations, and the use of mechanized equipment such as tractors, bulldozers, and drones.

[0109] The present application proposes a method for determining a production mode for maximizing crop yields. The method predicts the objective factor data affecting crop yields in the next year based on objective factor data affecting crop yields for many consecutive years. On the basis of obtaining the predicted value of the objective factor data affecting crop yields in the next year, the method determines the predicted value of the subjective factor affecting crop yields in the next year based on a crop growth prediction model with the goal of maximizing crop yields. The crop growth prediction model is a multiple linear regression model between crop yields and the objective and subjective factors affecting crop yields. By comprehensively analyzing the objective and subjective factors and considering the coupling relationship between the factors, the determined subjective factor prediction value is made more accurate. When the subjective factor prediction value is used to guide crop production, the crop yield can be increased to the greatest extent possible without affecting the sustainable development of the ecological environment.

[0110] Example 2

[0111] In this embodiment, a system for determining a production method for maximizing crop yield is disclosed, comprising:

[0112] A data acquisition unit is used to obtain objective factor data affecting crop yields for many consecutive years;

[0113] An objective factor prediction unit is used to predict the objective factor data affecting crop yield in the next year based on the objective factor data affecting crop yield in consecutive years, and obtain the predicted value of the objective factor data affecting crop yield in the next year;

[0114] A subjective factor determination unit is used to determine the predicted value of the subjective factor affecting the crop yield in the next year based on the predicted value of the objective factor data affecting the crop yield in the next year and the crop growth prediction model, with the goal of maximizing the crop yield;

[0115] Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

[0116] The present invention also discloses a computer device, comprising:

[0117] a processor adapted to execute a computer program;

[0118] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the method for determining a production mode for maximizing crop yield disclosed in Example 1 is implemented.

[0119] The present invention also discloses a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executed by a method for determining a production mode for maximizing crop yield disclosed in Example 1.

[0120] The present invention also discloses a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for determining a production mode for maximizing crop yield disclosed in Example 1.

[0121] The method disclosed in Example 1 can be directly implemented as a hardware processor, or can be implemented using a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, it will not be described in detail here.

[0122] Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A method for determining a production mode for maximizing crop yield, characterized in that: include: Obtain data on objective factors affecting crop yields for many consecutive years; Based on the objective factor data affecting crop yields for many consecutive years, the objective factor data affecting crop yields for the next year are predicted to obtain the predicted value of the objective factor data affecting crop yields for the next year; With the goal of maximizing crop yield, the predicted values ​​of subjective factors affecting crop yield in the next year are determined based on the predicted values ​​of objective factors affecting crop yield in the next year and the crop growth prediction model; Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

2. The method for determining a production mode for maximizing crop yield according to claim 1, wherein: Subjective factors affecting crop yields include irrigated land area and total power of agricultural machinery.

3. The method for determining a production mode for maximizing crop yield according to claim 2, wherein: With the goal of maximizing crop yield, the predicted values ​​of subjective factors affecting crop yield in the next year are determined based on the predicted values ​​of objective factors affecting crop yield in the next year, the crop growth prediction model, and the subjective factor prediction constraints. Among them, the subjective factor prediction constraints include crop yield increase constraints, agricultural machinery total power variation constraints and cultivated land irrigation area constraints.

4. The method for determining a production mode for maximizing crop yield according to claim 1, wherein: The agricultural machinery total power variation constraints include that the agricultural machinery total power is greater than or equal to 0 and the error between the agricultural machinery total power of the next year and the total power of the agricultural machinery of the current year is less than or equal to the error threshold.

5. The method for determining a production mode for maximizing crop yield according to claim 1, wherein: The trained objective factor prediction model is used to predict the objective factor data that will affect crop yields in the next year. The objective factor prediction model takes the objective factor data that have affected crop yields for many consecutive years as input and the predicted value of the objective factor data that will affect crop yields in the next year as output, and is constructed using an autoregressive moving average model.

6. The method for determining a production mode for maximizing crop yield according to claim 1, wherein: Obtain data on various factors affecting crop yields over the years and their corresponding crop yield data; Based on the data of each factor and crop yield data, determine the correlation between each factor and crop yield; The factors with correlation greater than the set value are selected as the main factors affecting crop yield, which include objective factors and subjective factors.

7. A system for determining a production method for maximizing crop yield, characterized in that: include: A data acquisition unit is used to obtain objective factor data affecting crop yields for many consecutive years; An objective factor prediction unit is used to predict the objective factor data affecting crop yield in the next year based on the objective factor data affecting crop yield in consecutive years, and obtain the predicted value of the objective factor data affecting crop yield in the next year; A subjective factor determination unit is used to determine the predicted value of the subjective factor affecting the crop yield in the next year based on the predicted value of the objective factor data affecting the crop yield in the next year and the crop growth prediction model, with the goal of maximizing the crop yield; Among them, the crop growth prediction model is a multiple linear regression model between crop yield and objective and subjective factors affecting crop yield.

8. An electronic device, characterized in that: The device comprises: a processor adapted to execute a computer program; A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the method for determining a production mode for maximizing crop yield according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the method for determining a production mode for maximizing crop yield according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method for determining a production mode for maximizing crop yield according to any one of claims 1 to 6.

Images