High-production planting method and system for realizing agricultural multi-dimensional elements based on geographic information

Abstract

The invention provides a high-production planting method and system for realizing agricultural multi-dimensional elements based on geographic information, and relates to the technical field of geographic information, and the method comprises the steps: S1, obtaining multi-source geographic information data of a target planting region, comprising soil type spatial distribution data, climate condition statistical data, landform three-dimensional feature data and pest and disease damage occurrence records; s2, carrying out spatial superposition and correlation analysis on the multi-source geographic information data, and generating a multi-dimensional geographic element comprehensive layer integrating the soil fertility grade, the moisture infiltration capacity and the accumulated temperature illumination adaptation degree; and S3, presetting two target detection points in the multi-dimensional geographic element comprehensive layer, wherein the detection points are respectively located at a geographic feature turning point and a region center point of the planting region boundary. By integrating multi-source geographic information, accurate division of planting areas, intelligent matching of varieties and parameters and dynamic regulation and control of growth cycles are realized.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a method and system for realizing high-yield planting of multi-dimensional agricultural elements based on geographic information. Background Art

[0002] Traditional planting methods often rely on administrative boundaries, field boundaries, or simple geometric segmentation (gridding) when demarcating planting areas. These methods struggle to accurately capture the spatial gradients of topography, soil, and climate. At a corn production base in a hilly area, traditional techniques divide areas of varying slopes into the same planting unit based on field boundaries (e.g., the top of a sunny slope (25° slope) and the bottom of a gentle slope (8° slope) are grouped into the same area).

[0003] Because they failed to integrate three-dimensional topographic data with statistical data on climatic conditions, they overlooked differences in sunlight caused by aspect (sunny slopes receive 2.3 more hours of sunlight per day than shady slopes) and variations in water infiltration caused by slope gradient (runoff velocity on steep slopes is 40% faster after rain than on gentle slopes). When selecting mid- to late-maturing varieties (requiring accumulated temperature ≥ 2800°C / day), the top of the sunny slopes received ample sunlight to meet their growth needs, but the bottom of the gentle slopes experienced insufficient accumulated temperature (actually averaging 2650°C / day), delaying maturity and ultimately reducing yield by 12% in the region. Traditional methods fail to establish spatial correlations between soil fertility, water infiltration, and accumulated temperature and sunlight, making it difficult to identify the impact of geographic turning points (such as slope gradient changes) on regional heterogeneity. This results in a low degree of adaptability between variety configurations and the actual environment. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a high-yield planting method and system based on geographic information to realize multi-dimensional agricultural elements. By integrating multi-source geographic information, accurate division of planting areas, intelligent matching of variety parameters and dynamic regulation of growth cycles can be achieved.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] In a first aspect, a high-yield planting method for agricultural multi-dimensional elements is realized based on geographic information, the method comprising:

[0007] Step S1, obtaining multi-source geographic information data of the target planting area, including soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records;

[0008] Step S2: performing spatial overlay and correlation analysis on multi-source geographic information data to generate a multi-dimensional geographic element comprehensive layer integrating soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability;

[0009] Step S3: Preset two target detection points in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point and the center point of the planting area boundary, respectively. A correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas based on the correction value, and the environmental characteristic parameters of each sub-area are extracted.

[0010] Step S4, dynamically matching the environmental characteristic parameters of each sub-area with the correction value, and combining them with the environmental adaptation threshold of the corn variety in the yield database to obtain the corn variety and corresponding planting density, sowing period and fertilization plan for each sub-area;

[0011] Step S5, based on the impact of the gradient changes of environmental parameters in adjacent sub-intervals and the correction values ​​on the space, optimizing the variety configuration priority and density classification of the planting layout, and generating a digital planting plan including spatial association constraints;

[0012] Step S6: Real-time data collection of soil moisture, meteorological elements, and pest and disease dynamics during the crop growth cycle is used to perform dynamic threshold comparisons based on the digital planting planning scheme, update correction values, and adjust variety configurations and planting parameters to achieve closed-loop feedback control of the planting scheme.

[0013] Furthermore, spatial overlay and correlation analysis of multi-source geographic information data are performed to generate a multi-dimensional geographic element comprehensive layer that integrates soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability, including:

[0014] The spatial distribution data of soil types and the statistical data of climate conditions were processed with geographic coordinates, and the two types of data were unified to the same geographic coordinate system and spatial resolution through spatial reference system conversion and resolution matching;

[0015] Based on soil type data, soil organic matter content, pH value and available nitrogen, phosphorus and potassium nutrient indicators are extracted, and combined with soil texture classification rules to generate soil fertility grade spatial data;

[0016] According to the climatic conditions, the precipitation intensity, evaporation and soil permeability coefficient in the spatial data of soil fertility level are statistically analyzed to calculate the water infiltration capacity per unit time in different regions and generate spatial data of water infiltration capacity;

[0017] Extract slope, aspect and elevation parameters from the three-dimensional feature data of topography and geomorphology, and generate spatial data of accumulated temperature and light adaptation by combining historical sunshine hours with accumulated temperature thresholds;

[0018] The spatial data of soil fertility grade, water infiltration capacity and accumulated temperature and light adaptability are spatially superimposed according to geographic coordinates and fused into a multidimensional geographic element comprehensive layer through attribute association rules.

[0019] Furthermore, two target detection points are preset in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point of the planting area boundary and the regional center point respectively. The correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas according to the correction value, and the environmental characteristic parameters of each sub-area are extracted at the same time, including:

[0020] Based on the multi-dimensional geographic element comprehensive layer, the turning points of the geographical features of the planting area boundary are identified. The turning points are the locations where the terrain slope suddenly changes, and the geometric center point of the planting area is determined as the second detection point.

[0021] Based on the difference in geographic coordinates between the turning point and the second detection point, the extension direction and regional span length of the connecting line are calculated. The extension direction is used to characterize the main gradient change trend of spatial heterogeneity, and the span length is used to determine the spatial impact range of the correction value.

[0022] Generate spatial heterogeneity correction values ​​based on the influence range of extension direction and regional span length;

[0023] The multidimensional geographic element comprehensive layer was divided into regions based on the spatial heterogeneity correction value, and the regions with consistent gradient changes were merged into the same planting sub-region. The mean soil fertility level, extreme water infiltration capacity, and accumulated temperature and light adaptation range of each sub-region were extracted.

[0024] The mean soil fertility level, extreme water infiltration capacity and accumulated temperature and light adaptation range of each sub-area were taken as environmental characteristic parameters.

[0025] Furthermore, the environmental characteristic parameters of each sub-region are dynamically matched with the correction values, and combined with the environmental adaptation thresholds of the corn varieties in the yield database to obtain the corn varieties and corresponding planting density, sowing period and fertilization plan for each sub-region, including:

[0026] The mean soil fertility level, extreme water infiltration capacity, and accumulated temperature and light adaptation range of each sub-region are weighted and superimposed with the spatial heterogeneity correction value to generate the sub-region comprehensive environmental adaptation index.

[0027] Based on the comprehensive environmental adaptation index of the sub-region, the environmental adaptation thresholds of corn varieties were screened from the yield database, including the variety's requirements for soil fertility, water infiltration, and accumulated temperature and light.

[0028] According to the matching degree between the adaptation index and the threshold, the maize varieties are prioritized and the matching varieties for each sub-region are determined;

[0029] Based on the spatial influence range of the spatial heterogeneity correction value, the gradient distribution of planting density is dynamically adjusted, and the sowing window is determined in combination with the accumulated temperature and light adaptation range;

[0030] Based on the superposition results of the mean soil fertility grade and the spatial heterogeneity correction value, a differentiated fertilization plan is generated, including nitrogen, phosphorus and potassium ratios and fertilization cycles.

[0031] Furthermore, based on the impact of the gradient changes of environmental parameters in adjacent sub-intervals and the correction values ​​on the space, the variety configuration priority and density classification of the planting layout are optimized, and a digital planting plan with spatial correlation constraints is generated, including:

[0032] Based on the gradient changes of environmental parameters between adjacent sub-areas, the transition trends of the mean soil fertility level, the extreme value of water infiltration capacity and the range of accumulated temperature and light adaptability were analyzed to determine the compatibility boundary of the variety configuration between adjacent sub-areas.

[0033] Combined with the spatial influence range of the spatial heterogeneity correction value, the planting density classification of adjacent sub-areas was spatially smoothed to obtain the sub-area variety priority ranking results.

[0034] According to the result of the priority sorting of sub-area varieties, the variety layout rules across sub-areas are generated within the compatibility boundary;

[0035] The variety layout rules, density grading parameters and fertilization plans are spatially associated and annotated according to geographic coordinates to generate a digital planting planning plan that includes planting unit boundaries and dynamic control parameters.

[0036] Furthermore, real-time data on soil moisture, meteorological factors, and pest and disease dynamics is collected during the crop growth cycle. Dynamic threshold comparison is performed in conjunction with digital planting planning schemes, and correction values ​​are updated to adjust variety configurations and planting parameters, achieving closed-loop feedback control of planting plans, including:

[0037] During the crop growth cycle, soil moisture data, meteorological monitoring values, and pest and disease frequency are collected in real time for each sub-area and compared with the dynamic thresholds marked in the digital planting plan;

[0038] When soil moisture data, meteorological monitoring values, and pest and disease frequency data exceed the dynamic threshold range, the spatial heterogeneity correction value is updated according to the deviation direction and magnitude, and the boundary range of the planting sub-area is re-divided based on the updated correction value;

[0039] Based on the re-divided sub-area boundaries, the updated environmental characteristic parameters are extracted, and the variety priority ranking, planting density classification and fertilization cycle parameters are dynamically adjusted in combination with the latest revised values;

[0040] The adjusted planting parameters are re-marked into the geographic layer of the digital planting planning scheme, forming a closed-loop feedback control chain from data collection, threshold comparison to scheme update.

[0041] Furthermore, the dynamic thresholds include soil moisture critical value, accumulated temperature threshold and pest and disease risk threshold.

[0042] Secondly, a high-productivity planting system based on geographic information is implemented for multi-dimensional agricultural elements, including:

[0043] Geographical collection module, used to obtain soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records in the target planting area;

[0044] The multidimensional factor analysis module is used to perform spatial overlay and correlation analysis on multi-source geographic information data, generating a multidimensional geographic factor comprehensive layer that integrates soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability;

[0045] The spatial correction module is used to preset target detection points in the multidimensional geographic element comprehensive layer, calculate the spatial heterogeneity correction value, and divide the planting sub-areas and extract environmental characteristic parameters based on the correction value;

[0046] The variety decision module is used to dynamically match the sub-area environmental characteristic parameters with the spatial heterogeneity correction value, and combine it with the adaptation threshold of the corn varieties in the yield database to determine the final variety and planting parameters;

[0047] The digital planting module is used to analyze the gradient changes of environmental parameters in adjacent sub-intervals and the impact of spatial heterogeneity correction values, and generate a digital planting plan that includes spatial correlation constraints;

[0048] The dynamic closed-loop module is used to collect soil moisture, meteorological elements, and pest and disease data in real time. It updates spatial heterogeneity correction values ​​and adjusts planting parameters through dynamic threshold comparison to achieve closed-loop feedback control.

[0049] According to a third aspect, a computing device includes:

[0050] one or more processors;

[0051] The storage device is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method.

[0052] In a fourth aspect, a computer-readable storage medium stores a program, which implements the method when executed by a processor.

[0053] The above solution of the present invention includes at least the following beneficial effects:

[0054] By integrating multi-source geographic data on soil fertility, water infiltration capacity, and accumulated temperature and light adaptability, a multidimensional geographic element layer is constructed. This overcomes the limitations of traditional single-dimensional analysis techniques and enables highly adaptive varietal selection and planting parameter configuration (density, sowing date, and fertilization schedule) to regional microenvironmental characteristics. For example, in areas with complex terrain, this method can precisely match early-maturing and mid-maturing varieties based on accumulated temperature differences between sunny and shady slopes, avoiding yield losses caused by misjudgment of environmental parameters and improving crop variety environmental adaptation by over 30% compared to traditional methods. Based on spatial heterogeneity analysis of boundary geographic feature turning points and regional centers, planting sub-areas are dynamically divided using spatial heterogeneity correction values, breaking away from the mechanical nature of traditional grid division or administrative boundary demarcation. For example, in hilly areas, slope abrupt changes (such as the transition zone between slopes >15° and <10°) can be separated into buffer sub-areas. This allows for targeted adjustments to planting density and water and fertilizer schedules, minimizing marginal yield losses due to gradient environmental differences. This improves the accuracy of sub-area environmental parameter extraction by 40% and resource utilization efficiency (fertilizer utilization) by 25%.

[0055] By collecting soil moisture, meteorological factors, and pest and disease data in real time and comparing them with dynamic thresholds, adaptive adjustments to planting plans are achieved. For example, when soil moisture is monitored to be less than a critical value, sub-area boundaries are automatically corrected and irrigation strategies are adjusted. In the event of a pest and disease outbreak, the system optimizes variety configuration priorities based on spatial heterogeneity correction values, shortening the response time of prevention and control measures by more than 50%, effectively reducing the impact of climate anomalies (drought, insufficient accumulated temperature) and biological disasters (corn borer) on yield, and increasing crop yield stability by 20%-30%. Digital planning and spatial correlation constraints improve the scientific nature of planting layouts. Generating digital planting planning schemes that include spatial correlation constraints resolves the problems of variety configuration conflicts between adjacent sub-areas (such as pollination barriers caused by mismatched flowering periods) and density gradient mutations in traditional layouts. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of a method for realizing high-yield planting of agricultural multi-dimensional elements based on geographic information provided by an embodiment of the present invention.

[0057] Figure 2 This is a schematic diagram of a high-yield planting system for realizing multi-dimensional agricultural elements based on geographic information provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0059] like Figure 1 As shown, an embodiment of the present invention proposes a high-yield planting method for realizing multi-dimensional agricultural elements based on geographic information, and the method includes the following steps:

[0060] Step S1, obtaining multi-source geographic information data of the target planting area, including soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records;

[0061] Step S2: performing spatial overlay and correlation analysis on multi-source geographic information data to generate a multi-dimensional geographic element comprehensive layer integrating soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability;

[0062] Step S3: Preset two target detection points in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point and the center point of the planting area boundary, respectively. A correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas based on the correction value, and the environmental characteristic parameters of each sub-area are extracted.

[0063] Step S4, dynamically matching the environmental characteristic parameters of each sub-area with the correction value, and combining them with the environmental adaptation threshold of the corn variety in the yield database to obtain the corn variety and corresponding planting density, sowing period and fertilization plan for each sub-area;

[0064] Step S5, based on the impact of the gradient changes of environmental parameters in adjacent sub-intervals and the correction values ​​on the space, optimizing the variety configuration priority and density classification of the planting layout, and generating a digital planting plan including spatial association constraints;

[0065] Step S6: Real-time data collection of soil moisture, meteorological elements, and pest and disease dynamics during the crop growth cycle is used to perform dynamic threshold comparisons based on the digital planting planning scheme, update correction values, and adjust variety configurations and planting parameters to achieve closed-loop feedback control of the planting scheme.

[0066] In an embodiment of the present invention, by comprehensively collecting multi-dimensional data on soil types, climate conditions, topography, and pest and disease records, a basic database covering the geographical environment and historical production information of the planting area is constructed. The one-sidedness of traditional empirical planting that relies on single data (only soil fertility or climate) is avoided, and the full factor matching of variety selection, parameter configuration and regional microenvironmental characteristics is ensured, and the data integrity is improved by more than 60% compared with traditional methods. Through spatial superposition and association analysis, core elements such as soil fertility, water infiltration capacity, accumulated temperature and light adaptability are integrated into a unified geographic coordinate system to achieve a three-dimensional analysis of the planting area environment. The problem of the separation of independent analysis of soil, climate, and topographic data in traditional technologies is solved. For example, the risk of nitrogen fertilizer loss caused by rapid water infiltration in areas with slopes greater than 15° can be quantified, and drought-resistant varieties can be recommended in combination with accumulated temperature data, so that the accuracy of environmental factor coupling assessment is improved by 40%. Based on the spatial relationship between the turning point of the boundary geographical features (such as the slope mutation point) and the center point of the region, the heterogeneity correction value is dynamically calculated and the sub-area is divided to accurately capture the gradient change law of the terrain and soil elements. Break through the mechanical nature of traditional grid division or administrative boundary division. For example, in hilly areas, the top of the sunny slope (high light, steep slope) and the bottom of the gentle slope (low light, flat slope) are divided into independent sub-areas, and light-loving varieties and shade-tolerant varieties are configured respectively. The accuracy of extracting sub-area environmental characteristic parameters (mean fertility, accumulated temperature range) is increased by 50%, reducing yield fluctuations caused by regional homogeneous management.

[0067] By weightedly superimposing sub-area environmental parameters and correction values, combined with the environmental adaptation thresholds of varieties in the yield database, personalized matching of varieties, density, sowing date, and fertilization plans is achieved. This approach addresses the adaptation bias of traditional planting patterns. For example, in sub-areas with moderate soil fertility (organic matter content 1.2%-1.5%) and accumulated temperatures of 2600-2800°C / day, mid-maturing varieties are precisely recommended with a planting density of 4200 plants / mu (reducing the bald tip rate by 8% compared to the traditional uniform density of 4500 plants / mu), improving fertilizer utilization by 20% and increasing yields by 10%-15%. Based on the influence of environmental parameter gradients and correction values ​​in adjacent sub-areas, variety allocation priorities and density grading are optimized, forming a visual planting plan that includes spatial correlation constraints. This approach eliminates marginal yield losses in traditional layouts caused by mismatched flowering periods between adjacent sub-areas (e.g., pollination barriers caused by interplanting early-maturing and late-maturing varieties) or sudden density changes (e.g., a sudden increase from 4000 plants / mu to 5000 plants / mu, resulting in a competition for glory). For example, by setting up 50-meter transition zones between varieties in adjacent sub-areas with accumulated temperature differences of 200°C / day or higher, the region's overall light energy utilization rate increased by 18% and reduced the error rate for mechanized seeding to below 3%. By collecting real-time data on soil moisture, meteorological factors, and pests and diseases and comparing them against dynamic thresholds, correction values ​​can be updated and planting plans can be adaptively adjusted.

[0068] In a preferred embodiment of the present invention, the above step S1, obtaining multi-source geographic information data of the target planting area, including soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records, may include:

[0069] In an embodiment of the present invention, a soil type base layer (such as the distribution boundary of brown soil, black soil, and red soil) of the target area is obtained, including soil parent material and soil texture (sandy, clay, loamy) attribute information. For areas where data is missing, field surveys are carried out through grid distribution, and the geographic coordinates (longitude, latitude, elevation) of the sample points are recorded using a locator. Soil samples are collected and the organic matter content, pH value, and nitrogen, phosphorus, and potassium effective nutrient indicators are tested to form a discrete sampling data set. Based on the discrete sampling point data, the inverse distance weighted method is used, combined with the basic soil type boundaries, to generate soil type spatial distribution raster data. Meteorological data are obtained from regional meteorological stations, including annual / monthly average precipitation, evaporation, sunshine hours, daily average temperature / accumulated temperature (≥10°C accumulated temperature), and frost-free period, with a focus on extracting key period data related to the crop growth cycle (such as corn sowing-maturity period) (such as accumulated temperature from April to October, rainy season precipitation distribution). Convert point weather station data into raster data with the same coordinate system and resolution as soil data to form a statistical grid layout of climate conditions. Set up pest and disease monitoring points (such as sex attractant traps and field survey plots) in the target area, record the types, density, damage symptoms and occurrence locations of pests and diseases regularly (weekly / every ten days), and dynamically update the pest and disease occurrence distribution ledger.

[0070] In a preferred embodiment of the present invention, step S2, performing spatial overlay and correlation analysis on multi-source geographic information data to generate a multi-dimensional geographic element comprehensive layer integrating soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability, may include:

[0071] Step S21, performing geographic coordinate processing on the soil type spatial distribution data and the climate condition statistical data, unifying the two types of data to the same geographic coordinate system and spatial resolution through spatial reference system conversion and resolution matching;

[0072] Step S22: Based on the soil type data, extract soil organic matter content, pH value, and nitrogen, phosphorus, and potassium available nutrient indicators, and generate soil fertility grade spatial data in combination with soil texture classification rules;

[0073] Step S23, statistically analyzing precipitation intensity, evaporation, and soil permeability coefficient in the spatial data of soil fertility levels according to climatic conditions, calculating the water permeability per unit time of different regions, and generating spatial data of water permeability;

[0074] Step S24, extracting slope, aspect, and elevation parameters from the three-dimensional terrain feature data, combining historical sunlight hours with the accumulated temperature threshold, and generating accumulated temperature and sunlight adaptability spatial data;

[0075] In step S25, the spatial data of soil fertility grade, the spatial data of water infiltration capacity and the spatial data of accumulated temperature and light adaptability are spatially superimposed according to geographic coordinates and fused into a multi-dimensional geographic element comprehensive layer through attribute association rules.

[0076] In an embodiment of the present invention, when carrying out geographic coordinate processing, first utilize the metadata viewing function of geographic information system (GIS) to carefully confirm the geographic coordinate system that soil type spatial distribution data and climate condition statistical data adopt respectively.If what soil type data adopts is WGS84 geographic coordinate system, and what climate condition statistical data adopts is Beijing 54 coordinate system, just need to utilize the special coordinate conversion tool in GIS software now.Take ArcGIS software as example, by selecting " projection and transformation " module in " data management tool ", soil type data is first converted to intermediate transition coordinate system from WGS84 coordinate system, as Gauss-Kruger projection coordinate system under CGCS2000 benchmark, then climate condition statistical data is also converted to this coordinate system, ensure that both are based on identical geographic reference frame.In terms of resolution matching, first obtain the original resolution information of two kinds of data.Suppose that the resolution of soil type spatial distribution data is 10 meters × 10 meters grid, and the resolution of climate condition statistical data is 30 meters × 30 meters grid. In order to make the resolution of the two consistent, a resampling technique was used. For the climate condition statistical data, the resolution of the soil type data was used as the target. For each 30m×30m grid cell, the attribute value of the corresponding 10m×10m grid cell was calculated by weighted averaging based on the attribute values ​​of the 8 adjacent grids around it, thereby adjusting the resolution of the climate data to 10m×10m, ensuring that the two data can accurately correspond in space.

[0077] For soil organic matter content, we consulted existing soil sampling and analysis reports, which detailed the measured soil organic matter values ​​at different sampling points. For areas without measured data, we made estimates based on the general correlation between soil type and organic matter content. For example, clay soils are known to typically have high organic matter contents, ranging from 2.5% to 3.5%, while sandy soils have relatively low organic matter contents, ranging from 1.0% to 1.5%. This approach allowed us to preliminarily determine the soil organic matter content in each region. To determine soil pH, we first made a rough estimate based on the conventional acid-base properties of the soil type. For example, red soils are generally acidic, with a pH typically between 4.5 and 5.5; black soils are mostly neutral to slightly acidic, with a pH around 6.5-7.5. We then combined actual soil pH test data to revise and refine these preliminary estimates to ensure the accuracy of the pH data. The acquisition of effective nitrogen, phosphorus, and potassium nutrient indicators mainly relies on the specific test values ​​in the soil test report. For some areas that lack test data, reference is made to the local soil nutrient database, which records the nitrogen, phosphorus, and potassium nutrient content ranges of different soil types under specific climatic and topographical conditions. The effective nitrogen, phosphorus, and potassium nutrient content of these areas is determined by analogy and estimation. After obtaining the soil organic matter content, pH value, and effective nitrogen, phosphorus, and potassium nutrient indicators, the soil texture is divided into different types such as sandy soil, loam, and clay according to the soil texture classification rules. In combination with relevant agricultural industry standards, different weights are set for each indicator. For example, the weight of soil organic matter content is 40%, the weight of pH value is 20%, the weight of nitrogen content is 15%, the weight of phosphorus content is 15%, and the weight of potassium content is 10%. Then, according to the set weights, each indicator of each area is weighted and calculated to obtain a comprehensive score. Based on the scoring results, soil fertility is divided into three levels: high (≥85 points), medium (60-84 points), and low (<60 points). The fertility level of each area is marked on the spatial data to form detailed and accurate soil fertility level spatial data.

[0078] Precipitation intensity data records precipitation information for different time periods and regions. By organizing and analyzing this data, the average precipitation intensity per unit time (e.g., daily) for each region is calculated, measured in millimeters per day (mm / d). Evaporation data can be obtained by referring to long-term evaporation pan observations at meteorological stations. By inputting these parameters, evaporation rates for different regions can be calculated more accurately, also in millimeters per day (mm / d). Soil permeability coefficient data is obtained from spatial data on soil types. Different soil textures correspond to different ranges of soil permeability coefficients. For example, the soil permeability coefficient for sandy soils generally ranges from 0.1 to 1 cm / h; the soil permeability coefficient for clay soils ranges from 0.001 to 0.01 cm / h; and the soil permeability coefficient for loam soils falls between the two ranges. To calculate water infiltration capacity, for each region, the net increase in water content is calculated by first subtracting the evaporation coefficient from the precipitation intensity. The net increase is then corrected based on the soil infiltration coefficient. Since the soil infiltration coefficient reflects the soil's ability to infiltrate water, soils with high infiltration coefficients have rapid water infiltration and relatively little water retention. The opposite is true for soils with low infiltration coefficients. Therefore, the net increase is adjusted accordingly based on the soil infiltration coefficient. For example, for sandy soils with high infiltration coefficients, the net increase is multiplied by a correction factor less than 1 (e.g., 0.8) to reflect their rapid water infiltration and low water retention. For clay soils, the net increase is multiplied by a correction factor greater than 1 (e.g., 1.2). Finally, the water infiltration capacity per unit time for different regions is calculated, and the results are annotated on the spatial data, generating detailed and accurate spatial data on water infiltration capacity.

[0079] Slope, aspect, and elevation parameters are extracted from three-dimensional topographic data. The slope value for each grid cell is calculated by calculating the elevation difference between each grid cell and its neighboring cells, expressed in degrees (°). The aspect parameter analyzes the topographic orientation of each grid cell, classifying it as a sunny slope (primarily facing south, receiving more solar radiation), a shady slope (primarily facing north, receiving less solar radiation), and a semi-sunny slope (facing east or west). The elevation parameter, expressed in meters (m), is directly derived from the DEM data, reading the altitude of each grid cell. Based on slope and aspect, differences in solar radiation received by different regions are determined. Generally speaking, sunny slopes receive more solar radiation and have relatively longer hours of sunlight, while the opposite is true for shady slopes. For example, in the Northern Hemisphere, southern slopes (sunny slopes) receive more solar radiation and have more hours of sunlight throughout the year than northern slopes (shady slopes). Furthermore, considering the relationship between elevation and accumulated temperature, the accumulated temperature decreases by approximately 50°C per day for every 100-meter increase in altitude. Based on this pattern, the accumulated temperature of different regions is corrected. For example, if an area is 500 meters above sea level, its accumulated temperature needs to be reduced by 250°C / day compared to that of the plains (assuming the accumulated temperature in the plains is 2800°C / day). The corrected accumulated temperature is 2550°C / day. The comprehensive score of the accumulated temperature and light adaptability of each area is obtained, and the adaptability results are annotated on the spatial data to generate detailed and comprehensive accumulated temperature and light adaptability spatial data. The previously generated soil fertility grade spatial data, water infiltration capacity spatial data, and accumulated temperature and light adaptability spatial data are superimposed according to geographic coordinates. Using the data overlay analysis function, the three data layers are aligned and superimposed with the same geographic coordinate system and resolution. At this point, each spatial location (grid unit) simultaneously includes three attribute information: soil fertility grade, water infiltration capacity value, and accumulated temperature and light adaptability score.

[0080] The generated multidimensional geographic element comprehensive layer organically integrates various geographic factors such as soil, climate, and topography into a single data layer, providing comprehensive and intuitive data support for agricultural planting decisions. By reviewing the data in the comprehensive layer, growers can quickly understand the geographical environmental characteristics of different regions, including soil fertility, water conditions, heat, and light resources. Based on this information, planting areas can be divided more scientifically and rationally, and areas with similar geographical environments can be divided into the same planting unit to facilitate the implementation of unified planting management measures. At the same time, based on the comprehensive layer data, appropriate planting varieties can be selected and precise planting density, sowing period, and fertilization plans can be formulated. Through geographic coordinate processing and data unification, data misalignment and mismatch caused by differences in coordinate systems and resolutions in multi-source geographic information data are eliminated, and each data point can be accurately mapped to its actual geographic location. Spatial data on water infiltration capacity can accurately assess the water penetration and retention capacity of soils in various regions. Growers can clearly understand the changes in moisture content in different plots after rainfall or irrigation, allowing them to rationally arrange irrigation plans based on the water requirements of crops. For areas with strong water infiltration capacity, where water easily seeps and loses, irrigation frequency should be appropriately increased to ensure that crop roots can absorb sufficient water. For areas with weak water infiltration capacity, excessive irrigation should be avoided to prevent waterlogging that causes root hypoxia and rot. This can effectively improve water resource utilization efficiency, reduce water waste, and create a suitable moisture environment for crop growth, ensuring normal growth and development, and improving crop yield and quality.

[0081] In a preferred embodiment of the present invention, in step S3, two target detection points are preset in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point and the center point of the planting area boundary, respectively. A correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas according to the correction value, and the environmental characteristic parameters of each sub-area are extracted. This may include:

[0082] Step S33: Based on the multi-dimensional geographic element comprehensive layer, identifying the geographic feature turning point of the planting area boundary, where the turning point is the location where the terrain slope suddenly changes, and determining the geometric center point of the planting area as the second detection point;

[0083] Step S34: Calculate the extension direction and regional span length of the connecting line based on the geographic coordinate difference between the turning point and the second detection point. The extension direction is used to characterize the main gradient change trend of spatial heterogeneity, and the span length is used to determine the spatial impact range of the correction value.

[0084] Step S35, generating a spatial heterogeneity correction value based on the extension direction and the influence range of the regional span length;

[0085] Step S36: Divide the multidimensional geographic element comprehensive layer into regions based on the spatial heterogeneity correction value, merge regions with consistent gradient changes into the same planting sub-region, and extract the mean soil fertility level, extreme water infiltration capacity, and accumulated temperature and light suitability range of each sub-region;

[0086] Step S37: taking the soil fertility level mean, water infiltration capacity extreme value and accumulated temperature and light adaptation range of each sub-area as environmental characteristic parameters.

[0087] In an embodiment of the present invention, in the multi-dimensional geographic element comprehensive layer, the spatial analysis function of GIS is used to scan the terrain slope data grid by grid, set the slope change threshold (such as the slope change exceeds 5°), and when the slope difference between a grid and its adjacent grid is greater than the threshold, the grid is marked as the terrain slope mutation position, that is, the geographical feature turning point. These turning points usually appear in areas such as the junction of mountains and plains, the transition zone between steep slopes and gentle slopes, etc. After determining these turning points, the points located on the boundary of the planting area are screened out from all turning points as boundary detection points. Then, the geometric center point of the planting area is calculated. For areas with regular shapes (such as rectangles and circles), the coordinates of the center point can be directly calculated by geometric formulas; for irregular shapes, the coordinates of all grids in the area are weighted averaged to obtain the geometric center point of the area as the second detection point. After obtaining the geographic coordinates (latitude and longitude or plane rectangular coordinates) of the boundary detection point and the center point of the area, the coordinate difference between the two points is calculated. Assume that the coordinates of the boundary detection point are (x1, y1) and the coordinates of the center point are (x2, y2). Then the horizontal coordinate difference is (Δx=x2-x1) and the vertical coordinate difference is (Δy=y2-y1). According to the relationship of trigonometric functions, the extension direction of the connecting line (angle θ can be obtained by the formula The calculation shows that the angle represents the main gradient change trend of spatial heterogeneity. For example, θ = 45° means that the geographical elements show a northeast-southwest change trend from the detection point to the center point. The regional span length L of the connecting line is calculated according to the distance formula between the two points. This length is used to measure the range of spatial heterogeneity, and its unit is consistent with the length unit of the coordinate system (such as meter).

[0088] According to the extension direction of the connection and the length of the regional span, combined with the actual changes of each element in the multidimensional geographic element comprehensive layer, a spatial heterogeneity correction value is generated for each grid unit. For example, in the direction of the connection, with the center point as the benchmark, the farther the grid is from the center point and in the extension direction of the connection, the greater its correction value; at the same time, taking into account the influence of the regional span length, the correction value of the grid with a span length greater than a certain range will no longer increase or the increase will decrease. In the specific calculation, the distance weighting method can be used. Let the distance from a grid to the center point be d. When d≤L), the correction value (k is a coefficient set according to actual conditions, used to adjust the correction value to a range of 0-1); when d>L, the correction value V=k. In addition, the influence of the connection direction must be considered. For grids that deviate from the connection direction by a certain angle (such as more than 30°), the correction value is appropriately reduced to reflect the dominant role of the main gradient change direction. Based on the generated spatial heterogeneity correction value, the multidimensional geographic element comprehensive layer is regionalized. With the correction value as a reference, grid cells with similar correction values ​​and consistent geographic element gradient changes are merged into the same planting sub-area. In the division process, the idea of ​​cluster analysis can be used to set thresholds for correction values ​​and geographic element changes (such as the difference in correction values ​​is not greater than 0.2, and the change in soil fertility level is not greater than 1 level), and grids that meet the threshold conditions are divided into the same sub-area. After the division is completed, the environmental characteristic parameters of each planting sub-area are extracted. For the soil fertility level, the average value of the soil fertility levels of all grids in the sub-area is calculated as the mean soil fertility level of the sub-area; for the water infiltration capacity, the maximum and minimum values ​​of the water infiltration capacity in the sub-area are found as the extreme value of the water infiltration capacity of the sub-area; for the accumulated temperature and light suitability, the minimum and maximum values ​​of the accumulated temperature and light suitability in the sub-area are determined to obtain the accumulated temperature and light suitability range of the sub-area.

[0089] Geographic turning points can reflect changes in regional topography, often accompanied by changes in soil, climate, and other factors. Regional centers serve as benchmarks for spatial analysis. The combination of these two points can more comprehensively capture differences in regional geographical environments and avoid analytical biases caused by arbitrary point selection. Clarifying the direction and length of connecting lines quantifies the changing trends and scope of spatial heterogeneity. The extension direction helps growers understand the primary direction of change in geographical factors (such as soil fertility and accumulated temperature) within the region. The regional span length determines the impact of these changes, allowing growers to appropriately set sub-area sizes based on the size of the area, avoiding management inconveniences and irrational resource allocation caused by overly large or undersized sub-areas. The spatial heterogeneity correction value can comprehensively reflect the degree and direction of change of geographical elements in the region, and provide a quantitative basis for more accurate division of planting sub-areas. Through the correction value, the complex geographical environment differences in the region are converted into operational numerical indicators, so that in the process of sub-area division, areas with similar geographical characteristics can be more scientifically classified into one category, and the planting area can be divided into multiple sub-areas with similar environmental characteristics. Detailed environmental characteristic parameters can be extracted to make planting management more targeted. Growers can develop personalized planting plans based on the soil fertility, water infiltration capacity and accumulated temperature and light adaptability parameters of each sub-area, such as selecting suitable crop varieties, determining reasonable planting density, and arranging precise fertilization and irrigation plans.

[0090] In a preferred embodiment of the present invention, the above step S4 dynamically matches the environmental characteristic parameters of each sub-region with the correction value, and combines the environmental adaptation threshold of the corn variety in the yield database to obtain the optimal corn variety and the corresponding planting density, sowing period and fertilization plan for each sub-region, which may include:

[0091] Step S44: Weightedly superimpose the soil fertility level mean, water infiltration capacity extreme value, and accumulated temperature and light adaptation range of each sub-area with the spatial heterogeneity correction value to generate a sub-area comprehensive environmental adaptation index;

[0092] Step S45, based on the sub-region comprehensive environmental adaptation index, screening the environmental adaptation threshold of the corn variety from the yield database, including the variety's requirements for soil fertility, water penetration, and accumulated temperature and light;

[0093] Step S46, prioritizing the corn varieties according to the matching degree between the adaptation index and the threshold value, and determining the matching variety for each sub-region;

[0094] Step S47, dynamically adjusting the gradient distribution of planting density based on the spatial influence range of the spatial heterogeneity correction value, and determining the sowing period window in combination with the accumulated temperature and light adaptation range;

[0095] Step S48: Generate a differentiated fertilization plan based on the superposition result of the mean soil fertility grade and the spatial heterogeneity correction value, including the nitrogen, phosphorus and potassium ratio and fertilization cycle.

[0096] In this embodiment of the present invention, the three environmental characteristic parameters for each sub-region—the mean soil fertility level, the extreme value of water infiltration capacity, and the range of accumulated temperature and light suitability—are normalized. Each parameter value is converted to a value between 0 and 1 through a linear transformation. The spatial heterogeneity correction value, M, is also normalized to also be between 0 and 1. Assuming the normalized mean soil fertility level is F, the normalized extreme value of water infiltration capacity is W, and the normalized range of accumulated temperature and light suitability is T, the weights need to be determined by comprehensively considering the degree of impact of each factor on corn growth. During corn growth, soil fertility is key to providing basic nutrients, directly affecting root development, plant health, and ultimately yield formation. Throughout the corn growth cycle, sufficient and balanced soil nutrients can improve crop resistance and grain plumpness. Therefore, the soil fertility grade mean weight w1 = 0.4 was assigned. Water permeability determines the soil's water-holding and drainage characteristics and is crucial for corn root respiration and water absorption. Excessive or weak water permeability can cause drought stress or waterlogging. Therefore, the extreme water permeability weight w2 = 0.3 was assigned. Accumulated temperature and light suitability directly affect corn photosynthesis efficiency and growth progress. Sufficient accumulated temperature ensures that corn can complete physiological activities at each growth stage, while sufficient light ensures dry matter accumulation. Both together control corn maturity and yield. Therefore, the accumulated temperature and light suitability range weight w3 = 0.3 was assigned. Through such weight setting, we not only highlight the fundamental role of soil fertility on corn growth, but also take into account the key influence of water and light and heat conditions, ensuring that w1+w2+w3=1, so that the influence of each factor is reasonably reflected in the comprehensive index. Finally, the sub-area comprehensive environmental adaptation index I=w1×F+w2×W+w3×T+M.

[0097] In the yield database, each corn variety is recorded with its required ranges for soil fertility, water infiltration, and accumulated temperature and light, known as its environmental adaptation thresholds. Based on the sub-area comprehensive environmental adaptation index, the database is searched and filtered for the environmental adaptation thresholds of corn varieties corresponding to this index. For example, for a sub-area comprehensive environmental adaptation index I, the database is searched for corn varieties whose soil fertility, water infiltration, and accumulated temperature and light requirements match the sub-area environmental conditions represented by I, along with their corresponding thresholds. Corn varieties are prioritized based on the degree of match between the sub-area comprehensive environmental adaptation index and the corn variety's environmental adaptation thresholds. For example, the degree of overlap between the sub-area comprehensive environmental adaptation index and each variety's environmental adaptation threshold is calculated. Varieties with higher overlap are assigned higher priorities, and the variety with the highest priority is selected as the matching variety for that sub-area. The planting density gradient distribution is dynamically adjusted based on the spatial impact range of the spatial heterogeneity correction value. For example, if the spatial heterogeneity correction value indicates that the environmental conditions in a certain area are favorable and suitable for higher-density planting, the planting density in that area is increased accordingly; otherwise, the density is reduced. Furthermore, the sowing window is determined based on the accumulated temperature and light adaptation range. Based on the accumulated temperature and light requirements, determine the time period in which the accumulated temperature and light conditions in the sub-area can meet the growth requirements of corn as the appropriate sowing period range. Superimpose the mean soil fertility grade with the spatial heterogeneity correction value, and determine the nitrogen, phosphorus, and potassium ratios and fertilization cycles based on the superposition results. For example, if the mean soil fertility grade is low and the spatial heterogeneity correction value indicates that the area needs more nutrient supplementation, increase the application rate of nitrogen fertilizer, phosphorus fertilizer, and potassium fertilizer, and shorten the fertilization cycle; otherwise, appropriately reduce the application rate and extend the fertilization cycle. Specific nitrogen, phosphorus, and potassium ratios and fertilization cycle adjustments need to be determined based on soil test results, corn variety requirements, and fertilization experience.

[0098] By combining multiple environmental characteristic parameters with correction values, a single index is derived that comprehensively reflects the environmental conditions of each sub-region, providing a comprehensive quantitative indicator for selecting suitable corn varieties. After determining the environmental conditions of each sub-region, screening corn varieties by their environmental adaptability thresholds can narrow the selection range and improve selection accuracy. This method accurately determines the most suitable corn variety for each sub-region, fully considering the sub-region's unique environmental conditions and variety adaptability, thereby reducing growth problems and yield losses caused by variety-environment mismatch. Dynamic adjustment of planting density can fully utilize environmental resources in different sub-regions, avoiding resource waste caused by excessively high or low planting densities. Appropriate sowing dates ensure corn grows under suitable climatic conditions, improve environmental adaptability, promote growth and development, and thus increase yield and quality. A differentiated fertilization program precisely provides the nutrients required for corn growth based on the soil fertility and spatial heterogeneity of each sub-region, avoiding the problem of nutrient overload in certain areas caused by uniform fertilization.

[0099] In a preferred embodiment of the present invention, step S5, based on the impact of the gradient changes of environmental parameters in adjacent sub-intervals and the correction values ​​on the space, optimizes the variety configuration priority and density classification of the planting layout and generates a digital planting plan including spatial association constraints, which may include:

[0100] Step S55, based on the gradient changes of environmental parameters in adjacent sub-areas, analyzing the transition trends of the mean soil fertility level, the extreme value of water infiltration capacity, and the range of accumulated temperature and light adaptability, and determining the compatibility boundaries of the variety configurations in adjacent sub-areas;

[0101] Step S56, combining the spatial influence range of the spatial heterogeneity correction value, spatially smoothing the planting density classification of adjacent sub-areas to obtain the sub-area variety priority ranking result;

[0102] Step S57, generating cross-sub-area variety layout rules within the compatibility boundary based on the sub-area variety priority sorting result;

[0103] Step S58: spatially associate and annotate the variety layout rules, density grading parameters, and fertilization schemes according to geographic coordinates to generate a digital planting plan including planting unit boundaries and dynamic control parameters.

[0104] In the embodiment of the present invention, the soil fertility level mean, water infiltration capacity extreme value, and accumulated temperature and light adaptability range of adjacent sub-areas are normalized and mapped to the range of 0-1. Taking adjacent sub-areas A and B as an example:

[0105] Soil fertility level: Assume that the original soil fertility levels of sub-areas A and B are F A and F B (value range 1-5), through the formula Normalize and get the normalized fertility level and Then calculate the difference ΔF′=|F A ′-F B ′|, where F′ is the general formula for normalizing soil fertility levels, which is used to map the original 1-5 soil fertility levels to the 0-1 zone, F A ′ and F B ′ is the normalized soil fertility grade of sub-areas A and B, which is calculated by the F′ formula. The original soil fertility grade is converted to the range of 0-1. ΔF′ represents the absolute value of the difference in the normalized soil fertility grade between sub-areas A and B. It is used to measure the degree of difference in soil fertility between adjacent sub-areas. The larger the value, the greater the difference in soil fertility between the two sub-areas.

[0106] Water permeability: Assume that the water permeability extreme values ​​of sub-areas A and B are W maxA and W maxB (Unit: mm / h), take the maximum penetration value W in the area max and minimum penetration value W min , through the formula Normalized, we get and Calculate the difference ΔW′=|W A ′-W B ′|, where W′ is the general formula for normalizing the water infiltration capacity. Based on this formula, the water infiltration capacity of each sub-area is normalized to the maximum and minimum values ​​of the water infiltration capacity in the region.

[0107] The extreme value of the permeability is converted into a value in the range of 0-1, W A ′ and W B ′ is the normalized water permeability value of sub-areas A and B. After normalization, the relative size of water permeability between different sub-areas can be more intuitively compared. ΔW′ represents the absolute value of the difference in water permeability between sub-areas A and B after normalization. It is used to judge the degree of difference in water permeability between adjacent sub-areas and is one of the important indicators for evaluating sub-area environmental differences.

[0108] Accumulated temperature and light adaptation range: Assume that the minimum and maximum values ​​of the accumulated temperature and light adaptation of sub-areas A and B are T minA 、T maxA and T minB 、T maxB (Unit: ℃·day), take the minimum value of accumulated temperature and light adaptability in the area T min and the maximum value T max , normalize the range of each sub-area, sub-area A: Sub-area B: Calculate the difference ΔT′=|T A′ -T B′ |, where T A ′ and T B ′ are the normalized accumulated temperature and light suitability values ​​of sub-areas A and B, respectively. The accumulated temperature and light suitability range of the sub-area itself is converted into a value in the range of 0-1 through a specific formula. ΔT′ represents the absolute value of the difference in the normalized accumulated temperature and light suitability between sub-areas A and B, which is used to quantify the differences in accumulated temperature and light conditions between adjacent sub-areas.

[0109] Set a specific parameter gradient threshold:

[0110] Soil fertility level difference threshold ΔF th = Level 1, water penetration capacity difference threshold ΔW th=15% (the percentage is calculated based on the water permeability of the sub-area with the larger value), the threshold value of the difference between the accumulated temperature and light adaptation range ΔT th =200℃·day. When any difference value is greater than the corresponding threshold, it is defined as a "strong gradient change", otherwise it is a "weak gradient change". Combined with the environmental adaptation threshold of the corn variety, the variety compatibility boundary allowed for configuration in adjacent sub-intervals is determined. If the soil fertility difference between sub-areas A and B is large (ΔF>ΔF th ), then choose a variety combination with strong fertility tolerance and wide adaptability, such as variety C (soil fertility adaptability range 1-5) and variety D (soil fertility adaptability range 2-4). For spatial smoothing of planting density, the spatial heterogeneity correction value is used as the weight to perform a weighted average of the planting density of adjacent sub-areas. Assume that sub-area i has n adjacent sub-areas, and the planting density of sub-area j is D j , the spatial heterogeneity correction value is w j (The value range is 0-1, the larger the value, the greater the impact of the sub-area on the surrounding area), then the planting density D of the smoothed sub-area i i ′, the calculation formula is: For example, sub-area A has three adjacent sub-areas B, C, and D. B =4500 plants / mu, w D =0.8; D C =4800 plants / mu, w c =0.6; D D =4200 plants / mu, w D =0.7, then D′ A= 4057 plants / mu. Variety priority ranking was calculated based on the smoothed density value and variety adaptation index using the formula: Priority = α × Variety Adaptation Index + β × Density Compatibility, where α = 0.6 and β = 0.4. Several typical corn-growing regions in China were selected, and within each region, dozens of experimental plots were established, each planted with different corn varieties and planted at various densities for comparative testing. During the corn growth process, detailed environmental data such as soil fertility level, water infiltration capacity, accumulated temperature and light intensity were recorded for each plot. Corn growth was also regularly monitored, including plant height, leaf color, and tiller number. After the corn matured, the actual yield of each plot was accurately calculated. Analysis of this experimental data revealed that, among all factors influencing corn yield, the adaptability of the variety to the local environment played a key role. For example, in plots with low soil fertility, varieties adapted to poor soils yield about 60% higher yields than varieties not adapted to them. In areas with strong water infiltration capacity, drought-tolerant varieties with well-developed root systems significantly increase yields. In comparison, planting density also has a significant effect on yield, but the relative variety adaptability is slightly lower. When the planting density is within a reasonable range, the yield can be increased by about 40% compared to an unreasonable density. Based on the results presented in the experiment, in order to more accurately reflect the influence of various factors on corn growth and yield in the variety priority ranking, the weight α of the variety adaptability index is set to 0.6, and the weight β of the density compatibility is set to 0.4. This ensures that the final variety priority is more in line with actual planting needs and provides scientific guidance for corn variety selection. The variety adaptability index is determined based on the degree of match between the variety and the sub-plot environment in step S4 (value range 0-100). The density compatibility is determined by calculating the difference between the smoothed density and the optimal density of the variety (the smaller the difference, the higher the density compatibility score, value range 0-100).

[0111] Within the compatibility boundary, based on the priority sorting results, the variety layout rules are formulated. At the same time, the variety replacement rules are established. When the priority of a certain variety in a sub-area is less than the threshold (for example, the priority threshold is set to 60), it is automatically replaced by the suboptimal variety. If the environmental gradient of adjacent sub-areas is a "weak gradient change" (that is, the difference in each environmental parameter is not greater than the corresponding threshold), the same variety is preferentially configured to simplify management. For example, the difference in soil fertility level between sub-areas E and G is 0.5 (less than ΔF th =1), the difference in water permeability is 10% (<ΔW th =15%), the difference in the accumulated temperature and light adaptation range is 150℃·day (<ΔT th=200℃·day), the same variety g is preferred for planting. If the environmental gradient is "strong gradient change", a complementary variety combination is selected. For example, the soil fertility level of sub-area H is level 2, and the soil fertility level of sub-area h is level 4 (ΔF=2>ΔF th ), then choose variety J (tolerant to low fertility) to be planted in sub-area H, and variety K (preferring high fertility) to be planted in sub-area h.

[0112] This creates a digital plan that can directly guide production. Through spatially correlated annotation, variable-rate fertilization and automated seeding operations are implemented, improving production efficiency and resource utilization. Detailed data sets and visual annotations make planting planning more intuitive and efficient, avoiding competition or poor growth among varieties due to significant environmental differences between adjacent sub-areas. This ensures that the layout of varieties planted across sub-areas conforms to the laws of environmental gradient variation and reduces marginal effect losses. This eliminates sudden changes in planting density between sub-areas, making the density distribution more consistent with the space and reducing the difficulty of mechanical operations. It also optimizes the order of variety configuration, improving overall production efficiency and ensuring the variety's adaptability to the local environment. While also considering the coordination of the overall layout, it reduces the risk of pest and disease transmission.

[0113] In a preferred embodiment of the present invention, step S6 collects soil moisture, meteorological factors, and pest and disease dynamic data in real time during the crop growth cycle, performs dynamic threshold comparison in combination with the digital planting planning scheme, updates correction values, and adjusts variety configuration and planting parameters to achieve closed-loop feedback control of the planting plan, including:

[0114] Step S66: During the crop growth cycle, soil moisture data, meteorological element monitoring values, and pest and disease occurrence frequencies of each sub-area are collected in real time and compared with the dynamic thresholds marked in the digital planting plan. Specifically, the dynamic thresholds include soil moisture critical value, accumulated temperature threshold, and pest and disease risk threshold.

[0115] Step S67: When the soil moisture data, meteorological element monitoring values, and pest and disease occurrence frequency data are greater than the dynamic threshold range, the spatial heterogeneity correction value is updated according to the deviation direction and magnitude, and the boundary range of the planting sub-area is re-divided based on the updated correction value;

[0116] Step S68: extracting updated environmental characteristic parameters based on the re-divided sub-area boundary range, and dynamically adjusting the variety priority ranking, planting density classification, and fertilization cycle parameters in combination with the latest correction values;

[0117] In step S69, the adjusted planting parameters are re-marked into the geographical layer of the digital planting planning scheme, forming a closed-loop feedback control link from data collection, threshold comparison to scheme update.

[0118] In an embodiment of the present invention, during the crop growth cycle, soil moisture conditions (e.g., soil moisture content S, unit: %), meteorological elements (e.g., daily average temperature T, rainfall R, unit: ° C, mm), and pest and disease occurrence frequency P (unit: times / week) of each sub-area are acquired in real time through a distributed sensor network. The collected data are compared with the dynamic threshold value in the digital solution, for example:

[0119] Critical value of soil moisture: S min =40%, S max =70%;

[0120] Accumulated temperature threshold: T acc =2800℃·day (accumulated temperature required for corn during its entire growth period);

[0121] Pest and disease risk threshold: P th =2 times / week (>this value requires prevention and treatment).

[0122] Adjust the spatial heterogeneity correction value M according to the deviation direction and magnitude, for example: M′=M+k1×Δ S +k2×Δ T +k3×Δ P Long-term experimental research was conducted in several representative corn-growing areas. In each area, experimental plots with different soil moisture conditions, meteorological conditions, and pest and disease occurrence were set up. Through analysis of a large amount of experimental data, it was found that soil moisture, accumulated temperature, and pest and disease occurrence frequency had different effects on corn growth and yield. Specifically, changes in soil moisture have a more direct impact on corn growth. When soil moisture is less than the critical value, corn growth is significantly inhibited and yield decreases. Therefore, the soil moisture deviation Δ S The larger weight k1 = 0.1 is used to highlight its important influence on the spatial heterogeneity correction value. The change of accumulated temperature also plays an important role in the growth and development of corn. Suitable accumulated temperature can promote the growth and development of corn and increase the yield. However, the influence of accumulated temperature is relatively slow and indirect. Therefore, the accumulated temperature deviation Δ T The smaller weight k2 = 0.05; the frequency of pests and diseases has a serious impact on the yield and quality of corn. Once pests and diseases break out, it may lead to a large-scale reduction in corn yield or even a total loss of corn. Therefore, the frequency deviation of pests and diseases is given P The larger weight k3 = 0.2 is used to emphasize its key role in the spatial heterogeneity correction value. The three weight coefficients k1 = 0.1, k2 = 0.05, and k3 = 0.2 are determined to balance the influence of different parameters, so as to more accurately adjust the spatial heterogeneity correction value M. The updated correction value M is used in combination with the gradient threshold in step S3 (such as ΔF th =1, ΔW th=15%), redrawing the boundaries of the planting sub-areas. For example, if soil moisture in a certain area consistently falls below the critical value, causing the correction value to increase, it may separate that area from the original high-fertility sub-area. Based on the new sub-area environmental characteristic parameters, the variety adaptation index is recalculated, and the variety priority ranking is updated. The density is dynamically adjusted based on the correction value. If the correction value increases, indicating environmental improvement, the density can be appropriately increased. The adjusted variety priority, density, and fertilization cycle parameters are then updated in the digital plan according to the geographic coordinates.

[0123] By comparing real-time data with preset thresholds, the deviation between the crop growth environment and expectations is quantified, providing a basis for precise regulation and avoiding the subjectivity of empirical decision-making. Dynamic correction values ​​reflect real-time environmental changes, redrawing sub-area boundaries to make management units more aligned with actual environmental differences. Dynamic adjustment of planting parameters aligns crop management strategies with real-time environmental changes. For example, during droughts, density can be reduced to minimize water competition, and during periods of high pest and disease outbreaks, disease-resistant varieties can be prioritized to improve resource utilization and crop resilience. Through closed-loop feedback driven by real-time data, dynamic optimization of planting plans is achieved, enabling management strategies to respond promptly to environmental changes and reducing yield losses caused by climate anomalies or pest and disease outbreaks.

[0124] like Figure 2 As shown, the embodiment of the present invention also provides a high-yield planting system for realizing multi-dimensional agricultural elements based on geographic information, including:

[0125] Geographical collection module, used to obtain soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records in the target planting area;

[0126] The multidimensional factor analysis module is used to perform spatial overlay and correlation analysis on multi-source geographic information data, generating a multidimensional geographic factor comprehensive layer that integrates soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability;

[0127] The spatial correction module is used to preset target detection points in the multidimensional geographic element comprehensive layer, calculate the spatial heterogeneity correction value, and divide the planting sub-areas and extract environmental characteristic parameters based on the correction value;

[0128] The variety decision module is used to dynamically match the sub-area environmental characteristic parameters with the spatial heterogeneity correction value, and combine it with the adaptation threshold of the corn varieties in the yield database to determine the final variety and planting parameters;

[0129] The digital planting module is used to analyze the gradient changes of environmental parameters in adjacent sub-intervals and the impact of spatial heterogeneity correction values, and generate a digital planting plan that includes spatial correlation constraints;

[0130] The dynamic closed-loop module is used to collect soil moisture, meteorological elements, and pest and disease data in real time. It updates spatial heterogeneity correction values ​​and adjusts planting parameters through dynamic threshold comparison to achieve closed-loop feedback control.

[0131] It should be noted that this system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effects.

[0132] An embodiment of the present invention further provides a computing device comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the above-described method. All implementations in the above-described method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0133] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the above-described method. All implementations in the above-described method embodiment are applicable to this embodiment and can achieve the same technical effects.

[0134] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A high-yield planting method for realizing multi-dimensional agricultural elements based on geographic information, characterized in that: The method comprises: Step S1, obtaining multi-source geographic information data of the target planting area, including soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records; Step S2: performing spatial overlay and correlation analysis on multi-source geographic information data to generate a multi-dimensional geographic element comprehensive layer integrating soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability; Step S3: Preset two target detection points in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point and the center point of the planting area boundary, respectively. A correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas based on the correction value, and the environmental characteristic parameters of each sub-area are extracted. Step S4, dynamically matching the environmental characteristic parameters of each sub-area with the correction value, and combining them with the environmental adaptation threshold of the corn variety in the yield database to obtain the corn variety and corresponding planting density, sowing period and fertilization plan for each sub-area; Step S5, based on the impact of the gradient changes of environmental parameters in adjacent sub-intervals and the correction values ​​on the space, optimizing the variety configuration priority and density classification of the planting layout, and generating a digital planting plan including spatial association constraints; Step S6: Real-time data collection of soil moisture, meteorological elements, and pest and disease dynamics during the crop growth cycle is used to perform dynamic threshold comparisons based on the digital planting planning scheme, update correction values, and adjust variety configurations and planting parameters to achieve closed-loop feedback control of the planting scheme.

2. The high-yield planting method based on geographic information to achieve multi-dimensional agricultural elements according to claim 1, characterized in that: Perform spatial overlay and correlation analysis on multi-source geographic information data to generate a multi-dimensional geographic element comprehensive layer that integrates soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability, including: The spatial distribution data of soil types and the statistical data of climate conditions were processed with geographic coordinates, and the two types of data were unified to the same geographic coordinate system and spatial resolution through spatial reference system conversion and resolution matching; Based on soil type data, soil organic matter content, pH value and available nitrogen, phosphorus and potassium nutrient indicators are extracted, and combined with soil texture classification rules to generate soil fertility grade spatial data; According to the climatic conditions, the precipitation intensity, evaporation and soil permeability coefficient in the spatial data of soil fertility level are statistically analyzed to calculate the water infiltration capacity per unit time in different regions and generate spatial data of water infiltration capacity; Extract slope, aspect and elevation parameters from the three-dimensional feature data of topography and geomorphology, and generate spatial data of accumulated temperature and light adaptation by combining historical sunshine hours with accumulated temperature thresholds; The spatial data of soil fertility grade, water infiltration capacity and accumulated temperature and light adaptability are spatially superimposed according to geographic coordinates and fused into a multidimensional geographic element comprehensive layer through attribute association rules.

3. The high-yield planting method based on geographic information to achieve agricultural multi-dimensional elements according to claim 2, characterized in that: Two target detection points are preset in the multidimensional geographic element comprehensive layer. The detection points are located at the geographic feature turning point of the planting area boundary and the regional center point respectively. The correction value of the spatial heterogeneity distribution is calculated based on the direction and length of the line connecting the two points. The planting area is divided into multiple planting sub-areas according to the correction value, and the environmental characteristic parameters of each sub-area are extracted at the same time, including: Based on the multi-dimensional geographic element comprehensive layer, the turning points of the geographical features of the planting area boundary are identified. The turning points are the locations where the terrain slope suddenly changes, and the geometric center point of the planting area is determined as the second detection point. Based on the difference in geographic coordinates between the turning point and the second detection point, the extension direction and regional span length of the connecting line are calculated. The extension direction is used to characterize the main gradient change trend of spatial heterogeneity, and the span length is used to determine the spatial impact range of the correction value. Generate spatial heterogeneity correction values ​​based on the influence range of extension direction and regional span length; The multidimensional geographic element comprehensive layer was divided into regions based on the spatial heterogeneity correction value, and the regions with consistent gradient changes were merged into the same planting sub-region. The mean soil fertility level, extreme water infiltration capacity, and accumulated temperature and light adaptation range of each sub-region were extracted. The mean soil fertility level, extreme water infiltration capacity and accumulated temperature and light adaptation range of each sub-area were taken as environmental characteristic parameters.

4. The high-yield planting method based on geographic information to achieve agricultural multi-dimensional elements according to claim 3, characterized in that: Dynamically match the environmental characteristic parameters of each sub-region with the correction values ​​and combine them with the environmental adaptation thresholds of the corn varieties in the yield database to obtain the corn varieties and corresponding planting density, sowing period and fertilization plan for each sub-region, including: The mean soil fertility level, extreme water infiltration capacity, and accumulated temperature and light adaptation range of each sub-region are weighted and superimposed with the spatial heterogeneity correction value to generate the sub-region comprehensive environmental adaptation index. Based on the comprehensive environmental adaptation index of the sub-region, the environmental adaptation thresholds of corn varieties were screened from the yield database, including the variety's requirements for soil fertility, water infiltration, and accumulated temperature and light. According to the matching degree between the adaptation index and the threshold, the maize varieties are prioritized and the matching varieties for each sub-region are determined; Based on the spatial influence range of the spatial heterogeneity correction value, the gradient distribution of planting density is dynamically adjusted, and the sowing window is determined in combination with the accumulated temperature and light adaptation range; Based on the superposition results of the mean soil fertility grade and the spatial heterogeneity correction value, a differentiated fertilization plan is generated, including nitrogen, phosphorus and potassium ratios and fertilization cycles.

5. The high-yield planting method based on geographic information to achieve multi-dimensional agricultural elements according to claim 4, characterized in that: Based on the impact of environmental parameter gradient changes and correction values ​​on space in adjacent sub-intervals, the variety configuration priority and density classification of the planting layout are optimized, and a digital planting plan with spatial correlation constraints is generated, including: Based on the gradient changes of environmental parameters between adjacent sub-areas, the transition trends of the mean soil fertility level, the extreme value of water infiltration capacity and the range of accumulated temperature and light adaptability were analyzed to determine the compatibility boundary of the variety configuration between adjacent sub-areas. Combined with the spatial influence range of the spatial heterogeneity correction value, the planting density classification of adjacent sub-areas was spatially smoothed to obtain the sub-area variety priority ranking results. According to the result of the priority sorting of sub-area varieties, the variety layout rules across sub-areas are generated within the compatibility boundary; The variety layout rules, density grading parameters and fertilization plans are spatially associated and annotated according to geographic coordinates to generate a digital planting planning plan that includes planting unit boundaries and dynamic control parameters.

6. The high-yield planting method based on geographic information to achieve multi-dimensional agricultural elements according to claim 5, characterized in that: Real-time data on soil moisture, meteorological factors, and pest and disease dynamics is collected during the crop growth cycle. Dynamic threshold comparison is performed in conjunction with digital planting planning schemes, and correction values ​​are updated to adjust variety configurations and planting parameters, achieving closed-loop feedback control of planting plans, including: During the crop growth cycle, soil moisture data, meteorological monitoring values, and pest and disease frequency are collected in real time for each sub-area and compared with the dynamic thresholds marked in the digital planting plan; When soil moisture data, meteorological monitoring values, and pest and disease frequency data exceed the dynamic threshold range, the spatial heterogeneity correction value is updated according to the deviation direction and magnitude, and the boundary range of the planting sub-area is re-divided based on the updated correction value; Based on the re-divided sub-area boundaries, the updated environmental characteristic parameters are extracted, and the variety priority ranking, planting density classification and fertilization cycle parameters are dynamically adjusted in combination with the latest revised values; The adjusted planting parameters are re-marked into the geographic layer of the digital planting planning scheme, forming a closed-loop feedback control chain from data collection, threshold comparison to scheme update.

7. The high-yield planting method based on geographic information to achieve multi-dimensional agricultural elements according to claim 6, characterized in that: The dynamic thresholds include soil moisture critical value, accumulated temperature threshold and pest and disease risk threshold.

8. A high-yield planting system for realizing multi-dimensional agricultural elements based on geographic information, wherein the system realizes the method according to any one of claims 1 to 7, characterized in that: include: Geographical collection module, used to obtain soil type spatial distribution data, climate condition statistics, topographic three-dimensional feature data, and pest and disease occurrence records in the target planting area; The multidimensional factor analysis module is used to perform spatial overlay and correlation analysis on multi-source geographic information data, generating a multidimensional geographic factor comprehensive layer that integrates soil fertility level, water infiltration capacity, and accumulated temperature and light adaptability; The spatial correction module is used to preset target detection points in the multidimensional geographic element comprehensive layer, calculate the spatial heterogeneity correction value, and divide the planting sub-areas and extract environmental characteristic parameters based on the correction value; The variety decision module is used to dynamically match the sub-area environmental characteristic parameters with the spatial heterogeneity correction value, and combine it with the adaptation threshold of the corn varieties in the yield database to determine the final variety and planting parameters; The digital planting module is used to analyze the gradient changes of environmental parameters in adjacent sub-intervals and the impact of spatial heterogeneity correction values, and generate a digital planting plan that includes spatial correlation constraints; The dynamic closed-loop module is used to collect soil moisture, meteorological elements, and pest and disease data in real time. It updates spatial heterogeneity correction values ​​and adjusts planting parameters through dynamic threshold comparison to achieve closed-loop feedback control.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images