Plant spacing setting method, system and equipment of rice transplanter and medium

Abstract

The invention relates to a plant spacing setting method, system and device of a rice transplanter and a medium, and the method comprises the steps: obtaining meteorological prediction data, a water demand interval of a growth cycle of a to-be-planted crop in a preset time period, soil humidity, terrain elevation data and historical environment data of each sampling region, and a historical crop remote sensing index of the crop under the historical environment data; calculating an environmental influence coefficient of each sampling area; determining a moisture convergence path network of the target planting area; determining a soil humidity change sequence of each sampling area in a preset time period according to the meteorological prediction data and the moisture convergence path network; performing numerical value superposition on the soil humidity change values in the soil humidity change sequence and the corresponding soil humidity to obtain a soil humidity sequence; and calculating a water stress risk value of the growth cycle, and determining the planting distance of each sampling area. The rationality of the planting density is improved by setting the plant spacing of the rice transplanter.

Description

Technical Field

[0001] This application relates to the field of rice transplanter spacing setting technology, specifically to a method, system, equipment, and medium for setting the spacing of a rice transplanter. Background Technology

[0002] As the material foundation for human survival and development, the stability of crop production and yield per unit area are the cornerstones for ensuring social supply. Among the many agronomic measures in crop cultivation, planting density is a core regulatory parameter that directly determines the structure of the field population, the allocation and utilization efficiency of resources, and ultimately affects the formation of economic output.

[0003] Existing technologies divide a large field into several sampling areas with different physical characteristics, such as highlands, slopes, and lowlands, by analyzing the digital elevation model (DEM) or soil survey map of the farmland. Subsequently, based on long-term accumulated agronomic experience, an optimal planting spacing is preset for each sampling area. For example, a denser planting spacing is used in lowlands that are generally considered to have better water and fertilizer conditions in order to pursue higher yields.

[0004] However, in actual planting, the distribution of water in farmland is not only affected by topography and static soil properties, but also by a combination of dynamic environmental factors such as meteorological changes, rainfall intensity and frequency, irrigation practices, and inter-regional water migration paths. For example, within a sampling area with a preset plant spacing, if heavy rainfall occurs, water between high and low areas may be redistributed through surface runoff or soil infiltration, causing temporary waterlogging in the originally drier high areas, while low-lying areas dry out quickly due to good drainage. This planting density strategy based on static properties is difficult to dynamically respond to the actual spatiotemporal changes in water availability, leading to a situation where water stress and resource waste coexist in some areas, thus reducing the rationality of planting density. Summary of the Invention

[0005] This application provides a method, system, equipment, and medium for setting the plant spacing of a rice transplanter, which solves the problem of resource waste caused by fixed plant spacing in rice transplanters and improves the resource utilization rate of planted land.

[0006] The first aspect of this application provides a method, system, device, and medium for setting plant spacing in a rice transplanter. The method includes: acquiring meteorological forecast data for a target planting area within a preset time period; acquiring the water requirement range of the growth cycle of the crop to be planted within the preset time period; acquiring soil moisture and topographic elevation data for multiple sampling areas within the target planting area, wherein the sampling areas are divided by the target planting area according to preset rules; acquiring historical environmental data of the crop to be planted in the target planting area within a historical time period, and historical remote sensing indices of the crop to be planted under the historical environmental data; performing correlation analysis between the historical environmental data and the historical crop remote sensing indices to calculate an environmental impact coefficient for each sampling area, wherein the environmental impact coefficient characterizes the influence of the planting environment on crop growth. The impact level is assessed; a water collection path network for the target planting area is determined based on the topographic elevation data, the water collection path network including multiple target water flow paths, which are used to characterize the flow trend of water on the land surface; a soil moisture change sequence for each sampling area within the preset time period is determined based on the meteorological forecast data and the water collection path network; the soil moisture change values ​​in the soil moisture change sequence are sequentially superimposed with the soil moisture corresponding to each sampling area in chronological order to obtain a soil moisture sequence for each sampling area within the preset time period; a water stress risk value for the growth cycle is calculated based on the soil moisture sequence and the water requirement interval; and the planting spacing for each sampling area is determined based on the water stress risk value and the environmental impact coefficient.

[0007] Optionally, the historical environmental data and the historical crop remote sensing index are correlated to calculate the environmental impact coefficient of each sampling area. Specifically, this includes: identifying anomalous areas, where the anomalous areas are the sampling areas where the data fluctuation coefficient of the historical crop remote sensing index is greater than a preset fluctuation threshold; performing terrain feature clustering analysis on the anomalous areas to obtain the terrain feature similarity between the anomalous areas, and identifying the anomalous areas where the terrain feature similarity is greater than a preset similarity threshold as anomalous areas of the same category; acquiring standard climate data for the target category of anomalous areas, constructing a standard local microclimate model for the target category of anomalous areas, where the target category of anomalous areas can be any category of anomalous area; and calculating the environmental impact coefficient of each sampling area based on the standard local microclimate model and the historical environmental data.

[0008] Optionally, the environmental impact coefficient of each sampling area is calculated based on the standard local microclimate model and the historical environmental data. Specifically, this includes: calculating the deviation parameter between the historical environmental data of the abnormal area and the environmental feature template in the standard local microclimate model; correcting the historical environmental data of the abnormal area according to the deviation parameter to obtain target historical environmental data; performing a multiple regression analysis on the target historical environmental data and the historical crop remote sensing index to obtain a first impact weight of the target historical environmental data on crop growth; weighting the first impact weight with the target historical environmental data corresponding to each abnormal area to obtain a first environmental impact coefficient for each abnormal area; for normal areas, performing a multiple regression analysis on the historical environmental data and the historical crop remote sensing index to obtain a second impact weight of the historical environmental data on crop growth; weighting the second impact weight with the historical environmental data corresponding to each normal area to obtain a second environmental impact coefficient for each normal area; and obtaining the environmental impact coefficient based on the first environmental impact coefficient and the second environmental impact coefficient. The normal areas are all sampling areas in the target planting area except for the abnormal areas.

[0009] Optionally, determining the water collection path network of the target planting area based on the terrain elevation data specifically includes: calculating the ratio of the elevation difference between the target sampling area and the sampling interval between adjacent sampling areas in a preset direction based on the terrain elevation data, to obtain the slope value of the target sampling area in each preset direction, wherein the target sampling area is any sampling area in the terrain elevation data; taking the preset direction corresponding to the maximum slope value of the target sampling area in each preset direction as the water flow direction of the target sampling area; connecting the target sampling area with the downstream sampling area corresponding to the target sampling area based on the water flow direction to obtain the target water flow path, wherein the downstream sampling area is the sampling area adjacent to the target sampling area in the water flow direction; traversing each sampling area in the terrain elevation data to obtain the water collection path network.

[0010] Optionally, calculating the water stress risk value of the growth cycle based on the soil moisture sequence and the water requirement interval specifically includes: determining whether there is a continuous waterlogging period in the soil moisture sequence, wherein the continuous waterlogging period is a period of time in which the soil moisture value at multiple consecutive time points in the soil moisture sequence is greater than a preset soil saturation water content; if the continuous waterlogging period exists, calculating the time interval between the target time point and the end time point of the target continuous waterlogging period, determining the soil permeability decay coefficient at the target time point, multiplying the soil moisture value at the target time point by the soil permeability decay coefficient to obtain a corrected soil moisture value, replacing the soil moisture value corresponding to the target time point in the soil moisture sequence with the corrected soil moisture value, and obtaining the target soil moisture sequence, wherein the target continuous waterlogging period is any... The continuous waterlogging period is defined as a time point that occurs after the target continuous waterlogging period but not within any of the continuous waterlogging periods. In the target soil moisture sequence, a water deficit value for a first target soil moisture value is calculated, where the first target soil moisture value is the target soil moisture value in the target soil moisture sequence that is less than the minimum water demand threshold of the water demand range. A water surplus value for a second target soil moisture value is calculated, where the second target soil moisture value is the target soil moisture value in the target soil moisture sequence that is greater than the maximum water demand threshold of the water demand range. A first water stress contribution value for the first target soil moisture value and a second water stress contribution value for the second target soil moisture value are calculated, and the water stress risk value is obtained based on the first water stress contribution value and the second water stress contribution value.

[0011] Optionally, the calculation of a first water stress contribution value for the first target soil moisture value and a second water stress contribution value for the second target soil moisture value, and the determination of the water stress risk value based on the first and second water stress contribution values, specifically includes: obtaining a first crop growth stage coefficient corresponding to the first target soil moisture value and a second crop growth stage coefficient corresponding to the second target soil moisture value for the crop to be planted within the growth cycle, wherein the first and second crop growth stage coefficients are used to characterize the sensitivity of the crop to water stress within the growth cycle; calculating the product of the water deficit value and the first crop growth stage coefficient to obtain a first water stress contribution value for each first target soil moisture value; calculating the product of the water surplus value and the second crop growth stage coefficient to obtain a second water stress contribution value for each second target soil moisture value; and weighted summing of the first and second water stress contribution values ​​to obtain the water stress risk value.

[0012] Optionally, the planting spacing for each sampling area is determined based on the water stress risk value and the environmental impact coefficient. Specifically, this includes: multiplying the water stress risk value by the environmental impact coefficient of each sampling area to obtain a comprehensive stress risk coefficient for each sampling area, wherein the comprehensive stress risk coefficient is used to characterize the degree of adverse impact on crop growth within the sampling area; multiplying a preset standard plant spacing by the reciprocal of the comprehensive stress risk coefficient to obtain an initial plant spacing for each sampling area, wherein the preset standard plant spacing is the minimum plant spacing requirement for the crop to be planted under a preset standard growth environment; and rounding the initial plant spacing up to the nearest achievable setting of the rice transplanter to obtain the planting spacing.

[0013] A second aspect of this application provides a rice transplanter spacing setting system, comprising: a first acquisition module for acquiring meteorological forecast data of a target planting area within a preset time period; a second acquisition module for acquiring water requirement intervals of the growth cycle of the crop to be planted within the preset time period; a third acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas within the target planting area, wherein the sampling areas are divided by the target planting area according to preset rules; a fourth acquisition module for acquiring historical environmental data of the crop to be planted in the target planting area within a historical time period, and historical crop remote sensing index of the crop to be planted under the historical environmental data; and an analysis module for performing correlation analysis between the historical environmental data and the historical crop remote sensing index, and calculating an environmental impact coefficient for each sampling area, wherein the environmental impact coefficient is used to characterize the degree of influence of the planting environment on crop growth; and a first acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas within the target planting area, wherein the sampling areas are divided by preset rules; and a fourth acquisition module for acquiring historical environmental data of the crop to be planted within a historical time period, and historical crop remote sensing index of the crop to be planted under the historical environmental data; and a first acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas within the target planting area, wherein the sampling areas are divided by preset rules; and a second acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas within the target planting area, wherein the sampling areas are divided by preset rules; and a third acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas within the target planting area, wherein the sampling areas are divided by preset rules; and a fourth acquisition module for acquiring historical environmental data of the crop to be planted within a historical time period, and historical crop remote sensing index of the crop to be planted within the historical environmental data, wherein the historical crop remote sensing index of the crop to be planted is acquired by acquiring soil moisture and topographic elevation data of multiple sampling areas, wherein the sampling areas are divided by preset rules; and a fourth acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas, wherein the sampling areas are divided by preset rules; and a fifth acquisition module for acquiring soil moisture and topographic elevation data of multiple sampling areas The system comprises three modules: a first module for determining the water collection path network of the target planting area based on the topographic elevation data, wherein the water collection path network includes multiple target water flow paths, which characterize the flow trend of water on the land surface; a second module for determining the soil moisture change sequence of each sampling area within a preset time period based on the meteorological forecast data and the water collection path network; a first calculation module for superimposing the soil moisture change values ​​in the soil moisture change sequence with the corresponding soil moisture of each sampling area in chronological order to obtain the soil moisture sequence of each sampling area within the preset time period; a second calculation module for calculating the water stress risk value of the growth cycle based on the soil moisture sequence and the water demand interval; and a third module for determining the planting spacing of each sampling area based on the water stress risk value and the environmental impact coefficient.

[0014] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the foregoing.

[0015] A fourth aspect of this application provides a computer-readable storage medium storing instructions that, when executed, perform the method described in any of the preceding descriptions.

[0016] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: 1. By dividing the target planting area into multiple sampling areas and acquiring corresponding meteorological forecast data, crop water requirement ranges, soil moisture, topographic elevation data, and historical environmental and remote sensing parameters, the system can spatially identify the differences in micro-regions. Furthermore, by correlating historical environmental data with historical remote sensing parameters and calculating environmental impact coefficients, the system can quantify the specific impact of environmental conditions on crop growth in each region, establishing a hierarchical basis for regional growth potential. Finally, by combining topographic elevation data to construct a water collection path network, the system clarifies the migration trend of water under topographic undulations, and, in conjunction with meteorological forecast data, extrapolates soil moisture change sequences, which are then overlaid with current soil moisture levels. A complete soil moisture sequence is obtained, which dynamically reflects the soil moisture change process in each sampling area over time. Based on this, the water stress risk value is calculated using the soil moisture sequence and water requirement range, and the plant spacing is set in conjunction with the environmental impact coefficient. This makes the plant spacing not only consider spatial heterogeneity, but also dynamically adapt to changes in water supply and demand over time. By predicting future water change trends and adjusting the plant spacing, the problem of traditional plant spacing based on static topography or soil property experience being unable to respond to water redistribution caused by factors such as rainfall, runoff, or evaporation is avoided. This effectively reduces the risk of local water stress or fertilizer and water waste, and improves the rationality of planting density and crop water use efficiency.

[0017] 2. By analyzing the volatility of historical crop remote sensing indices, abnormal areas with volatility exceeding a preset threshold in historical data were identified. Furthermore, topographic feature clustering analysis was introduced to classify these abnormal areas. This allowed for the construction of a standard local microclimate model based on similar topographic features, achieving unified modeling of environmental characteristics in abnormal areas with similar topographic backgrounds. This effectively avoided interference from local environmental fluctuations caused by topographic differences on the remote sensing parameter analysis results. Furthermore, by comparing the environmental feature templates in the standard local microclimate model with historical environmental data of the abnormal areas, deviation parameters were calculated and the historical data was corrected to obtain target historical environmental data that better reflects the actual climate background. This improved the accuracy of extracting the relationship between environmental factors and crop growth in subsequent multiple regression analysis.

[0018] 3. By employing slope orientation, dynamic simulation of water flow paths at the microscale was achieved, reconstructing the impact of topographic conditions on water migration patterns. Compared to traditional methods based on empirical modeling or fixed flow direction assumptions, this approach can adaptively construct high-precision water migration channels according to actual topographic changes, exhibiting higher adaptability and accuracy, especially under varying or complex terrain conditions. The establishment of the water accumulation path network not only provides fundamental support for subsequent water accumulation analysis and spatiotemporal distribution modeling of water resources, but also enables the precise identification of areas with abnormal crop growth caused by water accumulation by combining remote sensing parameters and environmental data, thereby enhancing the regional discrimination capability and hydrological coupling analysis depth of crop remote sensing monitoring from the source. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the system architecture of an embodiment of a rice transplanter plant spacing setting method or a rice transplanter plant spacing setting system applied in this application. Figure 2 This is a flowchart illustrating a method for setting the plant spacing of a rice transplanter according to an embodiment of this application; Figure 3 This is a schematic diagram of the plant spacing setting system of a rice transplanter according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of the electronic device in the embodiments of this application.

[0020] Explanation of reference numerals in the attached drawings: 301, First acquisition module; 302, Second acquisition module; 303, Third acquisition module; 304, Fourth acquisition module; 305, Analysis module; 306, First determination module; 307, Second determination module; 308, First calculation module; 309, Second calculation module; 310, Third determination module; 401, Processor; 402, Communication bus; 403, User interface; 404, Network interface; 405, Memory. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0022] Figure 1 An exemplary system architecture 100 is shown, which can be applied to an embodiment of a plant spacing setting method or a plant spacing setting system for a rice transplanter according to this application.

[0023] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Terminal devices 101, 102, and 103 are deployed on-site in the planting area and include, but are not limited to, agricultural machinery terminals (such as rice transplanter control systems), agricultural weather stations, remote sensing drones, and soil sensor terminals. These terminal devices can collect real-time weather forecast data, soil moisture data, and terrain elevation data of the target planting area within a preset time period and upload them to the server 105 for centralized processing. Simultaneously, the terminal devices can also be used to display the plant spacing settings fed back by the server and control the rice transplanter for precise operation. The network 104 provides a data transmission link, supporting efficient and stable data communication between the terminal devices and the server. In some scenarios, an edge computing architecture can be adopted, deploying lightweight servers or cache nodes locally to reduce latency. The server 105 can be a server providing various services, such as a backend server for processing the data displayed on the terminal devices 101, 102, and 103. The backend server can analyze and process the received data and feed the processing results back to the terminal devices.

[0024] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included. In particular, if the target data does not need to be obtained remotely, the above system architecture may exclude the network and include only terminal devices or servers.

[0025] Figure 2 This is a flowchart illustrating a method for setting the plant spacing of a rice transplanter in an embodiment of this application.

[0026] Please see Figure 2 This application provides a method for setting the plant spacing of a rice transplanter, the method comprising: S201. Obtain meteorological forecast data for the target planting area within a preset time period; S202. Obtain the water requirement range of the crop to be planted during its growth cycle within a preset time period; S203. Obtain soil moisture and topographic elevation data of multiple sampling areas in the target planting area. The sampling areas are divided by the target planting area according to preset rules. S204. Obtain historical environmental data of crops to be planted in the target planting area within a historical time period, and historical remote sensing index of the crops to be planted under the historical environmental data; Based on meteorological service platforms, such as the National Meteorological Information Center or agricultural IoT systems, meteorological forecast data for the target planting area within a preset time period is retrieved and downloaded. The preset time period typically refers to the complete period from the start of the crop growth cycle to the end of harvest; for example, the growth cycle of rice is approximately 120 days. The meteorological forecast data includes daily precipitation, temperature, relative humidity, wind speed, and other information. These parameters directly affect crop transpiration rates and soil moisture evaporation, thus significantly influencing the crop's water supply and demand relationship.

[0027] Based on crop water requirement models published by agricultural research institutions, the water requirement range of the crop to be planted during the preset time period is obtained. This range is usually set according to different growth stages of the crop (such as budding, tillering, jointing, heading, and maturity), with the daily water requirement per unit area expressed in millimeters per day.

[0028] The target planting area is divided into multiple sampling areas according to certain spatial rules. These rules can be set based on plot area, topographic relief, irrigation conditions, and existing remote sensing resolution. Common methods include K-means clustering based on the NDVI (Normalized Difference Vegetation Index) trend of remote sensing imagery, or regular grid partitioning to divide the area into square units with sides of 50 meters. Each sampling area serves as an independent environmental assessment unit. Based on these sampling areas, current soil moisture data is obtained for each area. This data can be collected in real-time by deployed soil sensors or extracted from satellite imagery using remote sensing inversion algorithms. Soil moisture is a core parameter determining whether crops are under water stress, directly affecting the water absorption capacity of crop roots. Furthermore, topographic elevation information is extracted using high-precision topographic data, which can be obtained through UAV low-altitude photogrammetry or public geographic information system platforms. Topographic elevation data provides the foundation for subsequent water runoff path modeling, determining the direction and trend of surface runoff. Furthermore, it is necessary to acquire historical environmental data and historical remote sensing indices of crops grown in the target planting area within a preset historical time period. Historical environmental data includes historical meteorological data, historical soil moisture, and historical fertilization and irrigation records. Historical crop remote sensing indices can be obtained through inversion from historical remote sensing images, including NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index). These remote sensing parameters can be used to characterize physiological characteristics such as crop health status, biomass changes, and photosynthetic efficiency. In this embodiment, all types of data acquired are formatted using unified data interface standards (such as GeoJSON, NetCDF, and CSV) and uniformly input into the system's data processing module to ensure data consistency and traceability in subsequent analysis stages.

[0029] S205. Correlation analysis is performed between historical environmental data and historical crop remote sensing indices to calculate the environmental impact coefficient for each sampling area. The environmental impact coefficient is used to characterize the degree of influence of the planting environment on crop growth. To further improve the accuracy and environmental adaptability of plant spacing settings, it is necessary to quantitatively characterize the relationship between historical environment and crop growth. Therefore, in step S205, historical environmental data and historical crop remote sensing indices are correlated to calculate the environmental impact coefficient for each sampling area. The environmental impact coefficient is used to characterize the degree of positive or negative impact and the volatility of specific environmental conditions on crop growth performance. By introducing this environmental impact coefficient, not only can areas sensitive to historical environment on crop growth be identified, but also a theoretical basis can be provided for setting differentiated plant spacing in different areas. This may include steps S2051-S2054: S2051. Identify abnormal areas. Abnormal areas are sampling areas where the data fluctuation coefficient of historical crop remote sensing index is greater than a preset fluctuation threshold. In step S2051, based on the acquired historical crop remote sensing index data, time-series analysis is performed on each sampling area after the target planting area is divided. The remote sensing index uses the Normalized Difference Vegetation Index (NDVI) as the main parameter. The NDVI is an important indicator reflecting vegetation cover and photosynthetic activity, calculated based on red and near-infrared reflectance. The analysis method is as follows: extract the NDVI values ​​of each sampling area over multiple consecutive historical planting cycles to form a time series, and calculate its fluctuation coefficient, i.e., the ratio of standard deviation to mean. To avoid interference from short-term weather fluctuations or data noise, the time series is first smoothed using a sliding window. Then, the fluctuation coefficient is compared with an empirically set preset fluctuation threshold to identify sampling areas with fluctuation coefficients greater than the threshold. The preset fluctuation threshold is determined by statistically analyzing the overall distribution of the remote sensing index fluctuation coefficients over multiple historical planting cycles within the target planting area, selecting the upper quartile of the fluctuation coefficient as the anomaly discrimination criterion to ensure the identification of sampling areas with significantly high fluctuations. These areas were marked as anomalous, meaning that crop growth in these areas is unstable due to environmental factors and may have hidden risks such as water stress, insufficient light, or soil problems, requiring further analysis of their causes.

[0030] S2052. Perform terrain feature clustering analysis on the abnormal areas to obtain the terrain feature similarity between the abnormal areas, and identify the abnormal areas with terrain feature similarity greater than the preset similarity threshold as abnormal areas of the same category. In step S2052, topographic feature clustering analysis is performed on the identified anomalous areas to determine whether a topographically dominated environmental disturbance pattern exists. To this end, topographic structural elements for each anomalous area are extracted, including average elevation, slope (surface tilt angle), aspect (slope orientation), topographic location index, and surface curvature. These parameters can all be calculated using GIS analysis tools based on a high-resolution digital elevation model. Principal component analysis is used to reduce the dimensionality of the multidimensional topographic parameters, retaining the first two to three principal components as clustering input. Subsequently, the K-means clustering algorithm is used to classify the anomalous areas and calculate the topographic feature similarity between areas. Similarity is defined as the reciprocal of the Euclidean distance between cluster centers; when this value is higher than a preset similarity threshold, they are considered to belong to the same category. The preset similarity threshold is based on the topographic feature clustering results of a large number of historical anomalous areas, verified by manual annotation to ensure consistency with the clustering classification, and the silhouette coefficient is used to evaluate the clustering quality. Finally, a similarity threshold value that results in high intra-cluster similarity and large inter-cluster differences is selected, typically set to around 0.85. The anomaly regions identified in this way share similar terrain control mechanisms, making it easier to normalize their climate response characteristics in subsequent models.

[0031] S2053. Obtain standard climate data for the target category of anomaly region and construct a standard local microclimate model for the target category of anomaly region. The target category of anomaly region can be any category of anomaly region. To model the environmental causes of remote sensing index fluctuations in anomalous regions with similar topographic features, and thus provide a generalizable and interpretable basis for calculating environmental impact coefficients, it is necessary to construct a representative standard local microclimate model based on anomalous regions of the target category. This model can characterize the coupling mechanism between topography and climate factors at the regional scale, explain the changing trends of remote sensing indices under specific environmental structures, and provide a climate simulation foundation for subsequent inversion of environmental impact coefficients.

[0032] During implementation, the first step is to select areas from any category of anomaly regions that possess high remote sensing monitoring integrity, convenient meteorological data acquisition, and typical terrain structure as target anomaly regions. These areas must have readily available daily or hourly measured meteorological data, including parameters such as temperature, precipitation, wind speed, relative humidity, and solar radiation intensity. This data can be collected through meteorological stations deployed at or near farmland boundaries, or obtained by interpolation using high-resolution meteorological reanalysis products (such as ERA5 or GLDAS) based on latitude and longitude grids.

[0033] While acquiring meteorological data, it is also necessary to extract detailed topographic parameters of the target category of anomaly areas, including but not limited to elevation, slope, aspect, topographic curvature, and topographic humidity index. These parameters are calculated using spatial analysis tools within a GIS platform based on a digital elevation model, accurately reflecting the influence of topography on microclimate factors such as wind field, water vapor movement, and solar radiation incidence angle. After data preparation, a local microclimate modeling method based on physical processes is used to model the target area. ENVI-met or MICROMET microclimate simulation models are preferred, as both are microscale meteorological modeling tools capable of simulating aerodynamics, heat exchange, and water vapor transport processes locally. Model inputs include topographic parameters, land use type (e.g., paddy fields, irrigation canals, forest belts), surface albedo, soil type and initial moisture state, as well as time-series meteorological driving data. The model simulates and analyzes the regulatory effects of different topographic units on wind speed, water vapor transport, temperature distribution, and radiation flux by solving non-hydrostatic fluid dynamics equations and energy balance equations.

[0034] The model outputs a standard local microclimate model, which includes three-dimensional spatially distributed layers of temperature, humidity, wind speed, and solar radiation flux distributions. The resolution is typically 1 to 5 meters, and the time step can be refined to the 10-minute level. After cross-validation with historical remote sensing data of the target area, the model results can be used to explain the environmental driving mechanisms of remote sensing index fluctuations. By constructing a standard local microclimate model, the changing trends of climate factors in environmentally sensitive areas can be predicted and attributed using the coupling law of topography and meteorology, without relying on the deployment of meteorological stations in each region. This significantly improves the spatial adaptability and physical interpretability of environmental impact coefficient calculations, providing a highly reliable environmental input basis for the subsequent precise setting of planting density and spacing.

[0035] S2054. Calculate the environmental impact coefficient of each sampling area based on the standard local microclimate model and historical environmental data.

[0036] In step S2054, to quantitatively model the environmental impact of each sampling area within the target planting region, an environmental impact coefficient for each sampling area needs to be calculated based on the established standard local microclimate model and historical environmental data. This environmental impact coefficient aims to reflect the combined effect of environmental factors on crop growth and guides the subsequent differentiated setting of plant spacing parameters. Since different regions exhibit significant differences in topography, climate response characteristics, and remote sensing performance, different regression models and impact weighting systems need to be established for abnormal and normal regions to ensure spatial adaptability of the model and the effectiveness of the calculation results. The process may include the following steps: Based on the environmental feature template in the standard local microclimate model, calculate the deviation parameter between the historical environmental data of the anomalous area and the environmental feature template, and correct the historical environmental data of the anomalous area according to the deviation parameter to obtain target historical environmental data; perform multiple regression analysis on the target historical environmental data and the historical crop remote sensing index to obtain a first influence weight of the target historical environmental data on crop growth, and perform weighted calculation on the first influence weight and the target historical environmental data corresponding to each anomalous area to obtain a first environmental influence coefficient for each anomalous area; for normal areas, perform multiple regression analysis on the historical environmental data and the historical crop remote sensing index to obtain a second influence weight of the historical environmental data on crop growth, and perform weighted calculation on the second influence weight and the historical environmental data corresponding to each normal area to obtain a second environmental influence coefficient for each normal area; obtain the environmental influence coefficient based on the first environmental influence coefficient and the second environmental influence coefficient, wherein the normal areas are all the sampling areas in the target planting area excluding the anomalous areas.

[0037] In the specific implementation process, the historical environmental data first needs to be corrected based on the environmental characteristic template in the standard local microclimate model. The standard local microclimate model provides the ideal distribution structure of each microclimate factor in a typical category of anomaly region. This structure is the environmental characteristic template, which includes the spatial distribution mean and variation range of factors such as temperature, humidity, wind speed, and precipitation within a specific time period. The template is then compared factor by factor with the original historical environmental data of the corresponding anomaly region, and the deviation parameter is calculated. The deviation parameter is defined as the standardized deviation value of the environmental factor in the historical environmental data relative to the template mean. To eliminate systematic errors caused by local microclimate differences, this deviation parameter is used as a correction coefficient and applied inversely to the historical environmental data, thereby obtaining target historical environmental data that is closer to the standard climate response structure. The significance of this is that it makes the environmental data of the anomaly region more consistent and comparable, avoiding interference with the stability of regression analysis due to local extreme values. For example, if the average summer wind speed in an anomaly region is consistently higher than the template value by 2 m / s, the wind speed data can be adjusted down to the standard response range through deviation correction.

[0038] Multiple regression analysis was performed between the corrected target historical environmental data and historical crop remote sensing indices to construct a functional relationship between environmental factors and crop growth status. Two remote sensing indices, NDVI and EVI, were used in joint modeling to reflect vegetation cover intensity and photosynthetic efficiency, respectively. The regression model was either a linear superposition model or a ridge regression model to enhance the handling of multicollinearity factors. Through model training, the first influence weight of each environmental factor in the target historical environmental data was obtained. This weight represents the relative contribution rate of a unit change in the factor to the change in the remote sensing index. For example, if the regression results show that the weight of temperature is 0.42 and that of precipitation is 0.30, then the impact of temperature change on crop growth is significantly higher than that of precipitation. Subsequently, this first influence weight was weighted and calculated with the corresponding target historical environmental data in the anomalous areas to obtain the first environmental influence coefficient for each anomalous sampling area. This coefficient comprehensively reflects the long-term influence intensity of the historical environment on crop growth in that area while preserving the regional differences.

[0039] For normal regions, due to their relatively small fluctuations in historical remote sensing indices, no bias correction is needed, and the original historical environmental data can be directly used for modeling. Similarly, using NDVI and EVI as response variables, a multiple regression model for environmental factors is constructed to obtain the second influence weight. Standard linear regression or partial least squares regression (PLSR) can be used here to improve modeling efficiency when the sample size is large. This second influence weight is then weighted with the historical environmental data corresponding to each normal region to obtain the second environmental influence coefficient. Because normal regions exhibit more stable environmental response characteristics, this coefficient typically has smaller numerical dispersion and can serve as a reference for stable growth zones.

[0040] Finally, the first and second environmental impact coefficients are integrated to form an environmental impact coefficient map of the entire sampling area, enabling a spatial quantitative expression of different environmental response structures within the planting area. This coefficient will serve as a key input parameter in subsequent plant spacing settings and transplanting path planning, guiding the appropriate increase of plant spacing in areas of high environmental stress to alleviate competitive pressure, and the reasonable reduction of plant spacing in stable growth areas to increase yield per unit area, thus achieving the optimal balance between dense crop planting and environmental adaptation.

[0041] For example, in a planting area, the anomalous sampling area A12 had an NDVI fluctuation coefficient of 0.31 in historical remote sensing data, exceeding the set threshold. After correcting its wind speed and radiation data using a standard local microclimate model, regression analysis yielded first-influence weights of 0.40, 0.35, and 0.25 for temperature, wind speed, and precipitation, respectively. Combined with the target historical environmental data for this area, its first environmental impact coefficient was calculated to be 0.68. The adjacent normal area B04 was directly modeled based on the original environmental data; precipitation contributed the most to the influence weights, resulting in a second environmental impact coefficient of 0.52. Therefore, area A12 experiences more significant environmental stress, and planting density should be appropriately reduced in the planting strategy to improve the resource acquisition capacity of individual plants.

[0042] S206. Based on the topographic elevation data, determine the water collection path network of the target planting area. The water collection path network includes multiple target water flow paths, which are used to characterize the flow trend of water on the ground surface. To reveal the spatial migration paths and accumulation trends of water within the target planting area, a water collection path network needs to be constructed based on topographic elevation data to accurately reflect the directionality and aggregation of surface runoff and potential soil moisture migration. This network structure consists of multiple target water flow paths, each representing the natural flow trajectory of water from high-potential-energy areas to low-potential-energy areas. Constructing this network is crucial for understanding the causes of uneven water distribution within the region, identifying areas prone to flooding or drought, and optimizing plant spacing. During implementation, the water flow direction needs to be accurately derived by combining the slope changes of adjacent sampling areas, and further, a complete water collection structure is formed through traversal and connection. The process may include the following steps: calculating the ratio of the elevation difference between the target sampling area and the sampling interval between the target sampling area and adjacent sampling areas in a preset direction based on the terrain elevation data, to obtain the slope value of the target sampling area in each preset direction, wherein the target sampling area is any sampling area in the terrain elevation data; taking the preset direction corresponding to the maximum slope value of the target sampling area in each preset direction as the water flow direction of the target sampling area; connecting the target sampling area with the downstream sampling area corresponding to the target sampling area based on the water flow direction to obtain the target water flow path, wherein the downstream sampling area is the sampling area adjacent to the target sampling area in the water flow direction; traversing each sampling area in the terrain elevation data to obtain a water collection path network.

[0043] In the specific implementation process, the slope value between any sampling area in the terrain elevation data and its surrounding adjacent sampling areas is first calculated. To ensure directional consistency, an eight-neighborhood model is used as the preset directional system. That is, for each sampling area, the slope value between it and its adjacent areas in eight directions (up, down, left, right, upper left, upper right, lower left, and lower right) is calculated. The slope value is calculated by dividing the elevation difference in that direction by the sampling interval. The sampling interval is determined by the remote sensing image resolution or the terrain data raster size, and is usually between 5 meters and 30 meters. For example, if the elevation difference between the sampling area and its adjacent area in the lower right direction is 1.2 meters, and the sampling interval is 10 meters, then the slope value in that direction is 0.12. In this way, the set of slope values ​​for the sampling area in all preset directions is obtained.

[0044] Based on the slope calculation results above, the direction with the largest slope value is extracted as the water flow direction for this sampling area. This direction represents the path along which water is most likely to flow under natural conditions, because water tends to flow downstream in the direction with the largest slope under the influence of gravity. If multiple directions have the same maximum slope value, the decision can be made based on the priority of the main direction (e.g., considering due south, southeast, etc. first) to ensure consistency and predictability in direction selection. This water flow direction is recorded as the outflow direction attribute of this sampling area.

[0045] After determining the water flow direction in all sampling areas, each sampling area is connected to its adjacent downstream sampling areas based on the water flow direction to construct the target water flow path. This connection operation essentially establishes a directed link from upstream to downstream in the data structure, forming a sequence of water flow path nodes. By traversing all sampling areas and connecting the paths, a complete water collection path network is obtained. This network not only includes the starting point, nodes it passes through, and the ending point of each water flow path, but can also further identify the main water flow path and tributary paths by calculating the cumulative catchment area, assisting in the determination of catchment depressions, drainage channels, and potential water accumulation points.

[0046] For example, in a planting area dataset constructed using a 10-meter resolution DEM, the maximum slope of sampling area C05, located in the southwest direction (0.18), is the largest among the eight directions. The system marks this as the southwest direction for water flow and connects it to the adjacent area C06 in that direction. Through recursive connections of multiple areas, a continuous target water flow path is formed from the high ground C01 to the low ground C10. The confluence of multiple paths constitutes the main water catchment channel within the area. This network structure can be directly used in subsequent planting strategy formulation to identify wet and waterlogged areas requiring increased plant spacing or well-drained areas requiring increased planting density, achieving precise control of the spatial coupling relationship between water potential and plant potential.

[0047] S207. Determine the soil moisture change sequence for each sampling area within a preset time period based on meteorological forecast data and water collection path network. To predict and analyze the dynamic changes in soil moisture in each sampling area within the target planting region over a predetermined time period, it is necessary to integrate meteorological forecast data with the established water runoff path network to generate a soil moisture change sequence for each sampling area. This sequence reflects the trend of soil moisture content in each area at different time points and serves as a crucial basis for determining the optimal plant spacing and adjusting planting density. Since soil moisture is influenced by multiple factors, including precipitation input, evaporation loss, topographic runoff, and infiltration, an integrated modeling approach is essential to fuse meteorological driving data with spatial water flow path information to achieve high-precision prediction.

[0048] In the specific implementation process, the first step is to acquire meteorological forecast data for a predetermined future time period. Meteorological elements include daily or hourly precipitation, temperature, wind speed, relative humidity, and solar radiation. Data sources can be numerical weather prediction products released by the National Meteorological Administration or gridded forecast data based on numerical models. The meteorological data undergoes spatial interpolation to ensure a one-to-one correspondence with the geographical location of the sampling area, guaranteeing that each sampling area has a complete meteorological driving data sequence.

[0049] Subsequently, a distributed soil moisture simulation model was constructed based on the water flow direction and connectivity provided by the water collection path network. This model uses the sampling area as the basic unit and employs the water balance principle to simulate the change in soil moisture over time. The soil moisture change in each sampling area consists of four parts: precipitation input, evapotranspiration loss, surface runoff input, and infiltration outflow. Precipitation input is directly derived from meteorological forecast data; evapotranspiration loss is calculated based on air temperature, wind speed, and radiation intensity, and estimated using the Penman-Monteith model; surface runoff input is accumulated based on the runoff volume of the upstream sampling area and the connectivity of the water flow path network; and infiltration outflow is calculated based on soil type and current moisture status, and estimated using the Green-Ampt model or a simplified soil water-capacity ratio model.

[0050] The model iterates along time steps (e.g., daily), updating soil moisture values ​​in the sampled area with each iteration to generate a complete time series output. To ensure simulation accuracy, initial soil moisture boundary conditions must be set in the model, which can be obtained by retrieving historical soil moisture data through remote sensing or by monitoring data from field sensors. The final generated soil moisture change sequence is expressed as a two-dimensional time-space array, with each sampled area corresponding to a set of continuous moisture values, reflecting the entire process from precipitation response to drainage recovery within a preset time period.

[0051] For example, when forecasting for sampling area D07, the 7-day meteorological forecast data showed that after 3 consecutive days of rainfall, the weather would turn sunny and dry. Based on its water catchment network, this area is located at the end of multiple upstream catchment pathways, receiving a large amount of surface runoff. Model calculations showed that soil moisture rapidly increased to saturation in the first 3 days, then slowly decreased from the 4th to the 7th day, but remained at a relatively high level. This sequence of moisture changes will directly affect the root aeration and water absorption capacity of crops in this area, suggesting that when sowing in this region, it is advisable to consider appropriately increasing plant spacing to reduce rhizosphere competition and lower the risk of disease.

[0052] S208. The soil moisture change values ​​in the soil moisture change sequence are sequentially superimposed with the soil moisture corresponding to each sampling area in chronological order to obtain the soil moisture sequence of each sampling area within a preset time period. In step S208, the soil moisture sequence is used to predict the moisture change process in each sampling area, reflecting the dynamic balance of water accumulation, loss, and regulation. It is a key input for subsequent soil moisture suitability assessment and plant spacing parameter matching. Since soil moisture changes have a strong time dependence and are constrained by the initial state, hourly or daily superposition calculations based on the current actual soil moisture level are necessary to truly reflect the moisture evolution process in each area.

[0053] First, the baseline soil moisture value for each sampling area is obtained. This baseline value can be derived from remote sensing inversion data, such as using microwave remote sensing or thermal infrared remote sensing for soil moisture inversion, or obtained through real-time monitoring by buried soil sensors. Each sampling area corresponds to only one initial soil moisture value, expressed as volumetric water content or percentage, serving as the starting point for the moisture sequence. Subsequently, a soil moisture change sequence based on meteorological forecast data and a water accumulation path network is invoked. This sequence represents the increase or decrease in moisture over time, with consistent units, indicating the trend of soil moisture change within each time step, including both increases (e.g., rainfall leading to wetness) and decreases (e.g., evaporation or drainage leading to dryness). The moisture change value for each sampling area is then progressively superimposed in chronological order, adding the moisture change value at time t to the cumulative moisture value at time t-1 to obtain the new moisture state, which is then used as the basis for calculations at the next time step. To prevent the superposition results from exceeding the actual soil water holding capacity, a threshold limit is applied to the results after each superposition step. The maximum value is usually set to the field water holding capacity, and the minimum value is the permanent wilting point. The part exceeding the range is corrected by infiltration or evaporation loss.

[0054] Through the above-mentioned hourly iterative overlay, a soil moisture sequence for each sampling area over the entire preset time period is generated, forming a two-dimensional temporal-spatial moisture matrix. Each sequence can clearly reflect the evolution of soil moisture status in the area over the next few days, exhibiting a typical cyclical pattern of wetting-saturation-drying-recovery under the influence of factors such as rainfall, evaporation, and runoff.

[0055] For example, in sampling area E03, the current baseline soil moisture value is 24%, and the subsequent 7-day moisture change sequence is +3%, +5%, -1%, -2%, -3%, +1%, -2%. After daily overlay, the complete moisture sequence is obtained as 27%, 32%, 31%, 29%, 26%, 27%, 25%. This sequence shows a trend of initial wetness followed by dryness, indicating that planting operations should be considered before and after the peak moisture level in the sowing plan, and drainage channels should be arranged in advance to reduce the risk of waterlogging damage. Through this overlay calculation process, the predicted soil moisture results can be fully integrated with the actual conditions to construct a dynamic moisture model that conforms to the current soil conditions, significantly improving the accuracy of the prediction and its guiding role, and providing a spatiotemporally consistent basis for precise control of sowing parameters.

[0056] S209. Calculate the water stress risk value of the growth cycle based on the soil moisture sequence and water requirement range; To achieve a quantitative assessment of water suitability during the crop growth cycle, it is necessary to calculate the water stress risk value within a preset growth cycle based on the soil moisture sequence and crop water requirement range for each sampling area. The water stress risk value reflects the comprehensive impact of soil moisture on crop root water uptake capacity, physiological activity, and yield formation, encompassing both waterlogging stress caused by excessive water and drought stress caused by insufficient water. Since the soil moisture sequence may include prolonged periods of continuous waterlogging at saturation, and the decreased soil permeability after waterlogging affects subsequent water infiltration and drainage, the soil moisture sequence needs to be dynamically corrected before risk analysis. Based on the correction results, water deficit, water surplus, and their corresponding stress contributions are calculated, ultimately forming a complete water stress risk value. This may include steps S2091-S2095: S2091. Determine whether there is a continuous waterlogging period in the soil moisture sequence. A continuous waterlogging period is a time period in the soil moisture sequence where the soil moisture value at multiple consecutive time points is greater than the preset soil saturation moisture content. In step S2091, to identify the time periods of waterlogging stress, it is necessary to extract continuous waterlogging periods from the soil moisture sequence. A waterlogging period is defined as a time period during which the soil moisture value exceeds a preset soil saturation moisture content for multiple consecutive time points. The preset soil saturation moisture content is the maximum moisture content that the soil can retain under natural conditions, generally determined based on soil texture type; for example, it is approximately 45% for loam and over 50% for clay. By traversing the humidity values ​​at each time point in the humidity sequence and recording the start and end positions of the time periods where the moisture content is continuously greater than the saturation moisture content, all continuous waterlogging periods can be identified. For example, if the humidity values ​​from day 2 to day 5 in the humidity sequence all exceed 50%, then these four days constitute a continuous waterlogging period.

[0057] S2092. If the continuous waterlogging period exists, calculate the time interval between the target time point and the end time point of the target continuous waterlogging period, determine the soil permeability attenuation coefficient of the target time point, multiply the soil moisture value of the target time point by the soil permeability attenuation coefficient to obtain the corrected soil moisture value, replace the soil moisture value corresponding to the target time point in the soil moisture sequence with the corrected soil moisture value to obtain the target soil moisture sequence, wherein the target continuous waterlogging period is any of the continuous waterlogging periods, and the target time point is a time point after the target continuous waterlogging period but not within any of the continuous waterlogging periods; After identifying a continuous waterlogging period, to avoid inflated humidity data caused by water accumulation, it is necessary to correct the humidity values ​​after the continuous waterlogging period. After waterlogging, soil pores become filled with water, reducing drainage and causing the actual humidity to decrease more slowly than the model's prediction; therefore, a correction mechanism is needed. Each continuous waterlogging period is selected as the target continuous waterlogging period. Starting from its end time, each target time point not in another continuous waterlogging period is searched, marked, and prepared for humidity value correction. This process ensures that the impact of waterlogging is locally controlled while avoiding redundant corrections. To implement humidity correction, the time interval between the target time point and the end time of the target continuous waterlogging period needs to be calculated, and the soil permeability decay coefficient is determined accordingly. The permeability decay coefficient is used to simulate the gradual recovery process of soil aeration and water infiltration capacity after waterlogging; this coefficient increases with time. An exponential function or a piecewise linear function can be used to define the decay coefficient; for example, 0.85 on the first day, 0.90 on the second day, and approaching 1 each day. The original humidity value at the target time point is multiplied by the corresponding permeability attenuation coefficient to obtain the corrected humidity value, thereby reducing the risk of overestimation due to oversaturation. For example, if the humidity is 48% on the first day after the waterlogging period ends and the attenuation coefficient is 0.85, the corrected humidity is 40.8%.

[0058] S2093. In the target soil moisture sequence, calculate the water deficit value of the first target soil moisture value. The first target soil moisture value is the target soil moisture value in the target soil moisture sequence that is less than the minimum water demand threshold of the water demand range. After completing the humidity correction, in step S2093, all humidity points below the minimum value of the crop water requirement range need to be identified as the first target soil moisture values, and their corresponding water deficit values ​​are calculated. The water requirement range is determined by the crop variety and growth stage; for example, the water requirement range for maize from jointing to tasseling is 25%-40%. The difference between each humidity value below 25% and 25% is taken as the water deficit value, reflecting the intensity of drought stress. For example, if the humidity on day 6 is 21%, the deficit value is 4%. This value will be used to quantitatively express the degree of subsequent stress impact.

[0059] S2094. Calculate the excess water value of the second target soil moisture value. The second target soil moisture value is the target soil moisture value in the target soil moisture sequence that is greater than the maximum water demand threshold of the water demand range. In step S2094, all humidity points exceeding the maximum value of the crop water requirement range are further identified as second target soil moisture values, and their corresponding excess water values ​​are calculated. Similar to the deficit value, any humidity value above 40% is considered excess water, and both constitute a stress source. The difference between each humidity value and 40% is used as the excess water value, reflecting the intensity of waterlogging stress. For example, if the humidity on day 3 is 46%, the excess value is 6%, which will be used subsequently to calculate the contribution of waterlogging stress.

[0060] S2095. Calculate the first water stress contribution value of the first target soil moisture value and the second water stress contribution value of the second target soil moisture value, and obtain the water stress risk value based on the first water stress contribution value and the second water stress contribution value.

[0061] To quantitatively assess the risk of water stress in crops throughout their entire growth cycle, the first and second target soil moisture values ​​identified in the previous stage need to be converted into their corresponding water stress contribution values. These contribution values ​​measure the impact of different types of water anomalies (i.e., water deficit and water excess) on crop growth at different time points. Since the sensitivity of crops to water varies significantly at different growth stages, a crop growth stage coefficient is introduced as a moderating factor to weight each soil moisture anomaly value, thereby achieving a time-sensitive correction for the degree of water stress. By calculating all water stress contribution values ​​and performing a weighted sum, a water stress risk value reflecting the intensity of water stress throughout the entire growth cycle is finally obtained. This may include the following steps: Obtain the first crop growth stage coefficient corresponding to the first target soil moisture value and the second crop growth stage coefficient corresponding to the second target soil moisture value of the crop to be planted within the growth cycle. The first crop growth stage coefficient and the second crop growth stage coefficient are used to characterize the sensitivity of the crop to water stress within the growth cycle. Calculate the product of the water deficit value and the first crop growth stage coefficient to obtain the first water stress contribution value for each first target soil moisture value. Calculate the product of the water excess value and the second crop growth stage coefficient to obtain the second water stress contribution value for each second target soil moisture value. Perform a weighted summation of the first water stress contribution value and the second water stress contribution value to obtain the water stress risk value.

[0062] In the specific implementation process, the crop growth stage coefficient of the crop to be planted within its corresponding growth cycle is first obtained. This coefficient is an empirical parameter used to characterize the crop's sensitivity to water stress at different growth stages. Growth stages are typically divided into seedling stage, jointing stage, heading stage, grain-filling stage, and maturity stage. Different stages have different physiological water requirements, resulting in different coefficient values. For example, for rice, the water requirement is relatively low during the seedling and grain-filling stages, with coefficients set at 0.6-0.7, while the heading stage is extremely sensitive to water, with coefficients reaching over 1.0. During the acquisition of the soil moisture sequence, each first-target soil moisture value and second-target soil moisture value can be matched to its corresponding growth stage by the correspondence between its time point and the crop's growth history, thereby determining its corresponding first-crop growth stage coefficient and second-crop growth stage coefficient.

[0063] After obtaining the growth stage coefficient for each soil moisture anomaly point, the water deficit value corresponding to each first target soil moisture value is multiplied by its first crop growth stage coefficient to obtain the first water stress contribution value at that time point. This product reflects the actual impact of drought stress on crop growth at the current growth stage. If it is a highly sensitive stage, its contribution value will be significantly amplified. For example, if the soil moisture on day 12 is 21%, which is lower than the lower limit of water requirement of 25%, the deficit value is 4%, the corresponding stage is the heading stage, and the coefficient is 1.0, then the first water stress contribution value at that time point is 4 × 1.0 = 4.0.

[0064] Similarly, the excess water value of each second target soil moisture value is calculated by multiplying it by the corresponding second crop growth stage coefficient to obtain the second water stress contribution value at each time point. This value is used to measure the degree of impact of waterlogging stress on crop oxygen uptake capacity, root respiration, and disease susceptibility. If waterlogging occurs during the seedling or heading stage, it often poses a significant threat to yield formation; therefore, the growth stage coefficient is usually higher at this stage. For example, if the humidity is 46% on day 4, exceeding the upper limit of the water requirement range of 40%, the excess value is 6%, and the seedling stage has a growth stage coefficient of 0.8, then the second water stress contribution value at this time point is 6 × 0.8 = 4.8.

[0065] After calculating the contribution values ​​of the first and second water stresses at all time points, the two values ​​are weighted and summed to form a comprehensive water stress risk value. The weighting method can be linear superposition or different weight coefficients can be set according to the sensitivity of different stress types. For example, drought stress can be weighted at 0.6 and waterlogging stress at 0.4, indicating that the crop's greater sensitivity to drought is considered. A higher final water stress risk value indicates more unsuitable water conditions during the growth cycle, requiring more significant cultivation adjustments in actual production, such as increasing plant spacing, improving drainage capacity, or delaying sowing.

[0066] For example, in sampling area F08, three primary target soil moisture values ​​and two secondary target soil moisture values ​​were identified during the growth cycle. The calculated contributions of primary water stress were 3.2, 4.0, and 2.6, and the contributions of secondary water stress were 4.8 and 3.6, respectively. With a drought weight of 0.6 and a waterlogging weight of 0.4, the final water stress risk value was: (3.2 + 4.0 + 2.6) × 0.6 + (4.8 + 3.6) × 0.4 = 9.84. This risk value will serve as a key reference indicator for environmental adjustment factors in subsequent plant spacing settings, guiding an appropriate reduction in planting density in this area to mitigate the adverse effects of water stress.

[0067] S210. The planting spacing of each sampling area is determined based on the water stress risk value and the environmental impact coefficient.

[0068] In step S210, to achieve differentiated planting spacing control for different sampling areas, it is necessary to comprehensively judge the degree of adverse impact on crop growth in each area based on the water stress risk value calculated above and the environmental impact coefficient of each area, and adjust the standard plant spacing accordingly. Plant spacing is a key parameter affecting crop population structure, individual plant resource utilization efficiency, and stress resistance; its dynamic adjustment is of great significance for improving crop adaptability and ensuring yield. This may include the following steps: multiplying the water stress risk value by the environmental impact coefficient of each sampling area to obtain a comprehensive stress risk coefficient for each sampling area, which characterizes the degree of adverse impact on crop growth within the sampling area; multiplying the preset standard plant spacing by the reciprocal of the comprehensive stress risk coefficient to obtain the initial plant spacing for each sampling area, where the preset standard plant spacing is the minimum plant spacing requirement for the crop to be planted under a preset standard growth environment; and rounding the initial plant spacing up to the nearest achievable setting of the rice transplanter to obtain the planting spacing.

[0069] To ensure numerical stability and logical consistency during the adjustment process and to avoid parameter distortion caused by extreme risk values, a normalization mechanism needs to be introduced during the calculation to standardize the water stress risk values. In practice, the water stress risk value for each sampling area is first obtained from the preceding steps. Since this value is based on the cumulative contribution of drought and waterlogging stress throughout the entire growth cycle, its value may be much greater than 1. If it is directly used in subsequent reciprocal calculations, it may lead to an unreasonable amplification of the initial plant spacing, thus violating the target of plant spacing control. Therefore, the original water stress risk value needs to be normalized. Normalization uses a minimum-maximum standardization method, with a preset theoretical maximum stress risk value R_max as the normalization upper limit, for example, R_max can be set to 20. The ratio of the original risk value R_i to R_max for each area is calculated to obtain the normalized risk value R_norm_i, calculated as: R_norm_i = R_i / R_max. After normalization, the value of R_norm_i is limited to between 0 and 1, which clearly expresses the relative position of water stress in the region within the theoretical risk range, thus providing a unified dimensional basis for subsequent multi-parameter fusion.

[0070] Subsequently, the normalized water stress risk value R_norm_i is multiplied by the corresponding regional environmental impact coefficient E_i to obtain the comprehensive stress risk coefficient C_i. This comprehensive coefficient is used to quantitatively characterize the overall stress intensity faced by crops during crop growth in the sampling area; a larger value indicates a more unfavorable environment: C_i = R_norm_i × E_i. After calculating the comprehensive stress risk coefficient, to achieve differentiated adjustment of the standard plant spacing, the standard plant spacing D_std is multiplied by the reciprocal of C_i to obtain the initial plant spacing D_init_i for the region. Since the reciprocal function has a monotonically decreasing characteristic, it can realize the agronomic logic that the higher the stress, the lower the density. To prevent C_i from approaching 0 and causing the reciprocal to become too large, a minimum threshold for C_i is set in actual operation, such as 0.1, as a safety lower limit: D_init_i=D_std×(1 / max(C_i,0.1)), where max(C_i,0.1) refers to the maximum value between C_i and 0.1, ensuring that the basic density requirement is maintained even in the best environment and avoiding excessive sparse planting.

[0071] Considering the practical limitations of mechanized agricultural operations, the initial plant spacing D_init_i needs to be rounded up to the nearest achievable setting by the rice transplanter to obtain the final plant spacing D_final_i. Rice transplanters typically support multiple fixed settings, such as 12cm, 14cm, 16cm, 18cm, and 20cm. The system selects the minimum usable value not less than D_init_i through table lookup or interpolation to ensure the feasibility and stability of field operations.

[0072] Please see Figure 3 This is a schematic diagram of the structure of a plant spacing setting system for a rice transplanter provided in an embodiment of this application. The plant spacing setting system 300 for a rice transplanter specifically includes: a first acquisition module 301, used to acquire meteorological forecast data of the target planting area within a preset time period; The second acquisition module 302 is used to acquire the water requirement range of the growth cycle of the crop to be planted within the preset time period. The third acquisition module 303 is used to acquire soil moisture and topographic elevation data of multiple sampling areas in the target planting area, wherein the sampling areas are divided by the target planting area according to preset rules; The fourth acquisition module 304 is used to acquire historical environmental data of the crop to be planted in the target planting area during a historical time period, and the historical crop remote sensing index of the crop to be planted under the historical environmental data. Analysis module 305 is used to perform correlation analysis between the historical environmental data and the historical crop remote sensing index, and calculate the environmental impact coefficient of each sampling area. The environmental impact coefficient is used to characterize the degree of influence of the planting environment on crop growth. The first determining module 306 is used to determine the water collection path network of the target planting area based on the terrain elevation data. The water collection path network includes multiple target water flow paths, which are used to characterize the flow trend of water on the ground surface. The second determining module 307 is used to determine the soil moisture change sequence of each sampling area within the preset time period based on the meteorological forecast data and the moisture collection path network. The first calculation module 308 is used to superimpose the soil moisture change value in the soil moisture change sequence with the soil moisture corresponding to each sampling area in chronological order to obtain the soil moisture sequence of each sampling area within the preset time period. The second calculation module 309 is used to calculate the water stress risk value of the growth cycle based on the soil moisture sequence and the water demand range. The third determining module 310 is used to determine the planting spacing of each sampling area based on the water stress risk value and the environmental impact coefficient.

[0073] Optionally, the analysis module 305 is specifically used for: identifying anomalous areas, wherein the anomalous areas are the sampling areas where the data fluctuation coefficient of the historical crop remote sensing index is greater than a preset fluctuation threshold; performing terrain feature clustering analysis on the anomalous areas to obtain the terrain feature similarity between the anomalous areas, and determining the anomalous areas where the terrain feature similarity is greater than a preset similarity threshold as anomalous areas of the same category; acquiring standard climate data of the target category anomalous areas, constructing a standard local microclimate model of the target category anomalous areas, wherein the target category anomalous areas can be any category of anomalous areas; and calculating the environmental impact coefficient of each sampling area based on the standard local microclimate model and the historical environmental data.

[0074] Optionally, the analysis module 305 is further specifically used for: calculating the deviation parameter between the historical environmental data of the abnormal area and the environmental feature template based on the environmental feature template in the standard local microclimate model, and correcting the historical environmental data of the abnormal area according to the deviation parameter to obtain target historical environmental data; performing multiple regression analysis on the target historical environmental data and the historical crop remote sensing index to obtain the first influence weight of the target historical environmental data on crop growth, and weighting the first influence weight with the target historical environmental data corresponding to each abnormal sampling area to obtain the first environmental influence coefficient of each abnormal sampling area; for normal areas, performing multiple regression analysis on the historical environmental data and the historical crop remote sensing index to obtain the second influence weight of the historical environmental data on crop growth, and weighting the second influence weight with the historical environmental data corresponding to each normal area to obtain the second environmental influence coefficient of each normal area, and obtaining the environmental influence coefficient according to the first environmental influence coefficient and the second environmental influence coefficient, wherein the normal areas are all the sampling areas in the target planting area except for the abnormal areas.

[0075] Optionally, the first determining module 306 is specifically used for: calculating the ratio of the elevation difference between the target sampling area and the sampling interval between the target sampling area and the sampling areas adjacent to the target sampling area in a preset direction based on the terrain elevation data, to obtain the slope value of the target sampling area in each preset direction, wherein the target sampling area is any sampling area in the terrain elevation data; taking the preset direction corresponding to the maximum slope value of the target sampling area in each preset direction as the water flow direction of the target sampling area; connecting the target sampling area with the downstream sampling area corresponding to the target sampling area based on the water flow direction to obtain the target water flow path, wherein the downstream sampling area is the sampling area adjacent to the target sampling area in the water flow direction; traversing each sampling area in the terrain elevation data to obtain a water collection path network.

[0076] Optionally, the second calculation module 309 is specifically used for: determining whether there is a continuous waterlogging period in the soil moisture sequence, wherein the continuous waterlogging period is a time period in which the soil moisture values ​​at multiple consecutive time points in the soil moisture sequence are greater than a preset soil saturation water content; if the continuous waterlogging period exists, calculating the time interval between the target time point and the end time point of the target continuous waterlogging period, determining the soil permeability attenuation coefficient of the target time point, multiplying the soil moisture value of the target time point by the soil permeability attenuation coefficient to obtain a corrected soil moisture value, replacing the soil moisture value corresponding to the target time point in the soil moisture sequence with the corrected soil moisture value, thereby obtaining the target soil moisture sequence, wherein the target continuous waterlogging period is any of the continuous waterlogging periods, and the target time... The point is a time point that is after the target continuous waterlogging period but not within any of the continuous waterlogging periods; in the target soil moisture sequence, the water deficit value of the first target soil moisture value is calculated, where the first target soil moisture value is the target soil moisture value in the target soil moisture sequence that is less than the minimum water demand threshold of the water demand range; the water surplus value of the second target soil moisture value is calculated, where the second target soil moisture value is the target soil moisture value in the target soil moisture sequence that is greater than the maximum water demand threshold of the water demand range; the first water stress contribution value of the first target soil moisture value and the second water stress contribution value of the second target soil moisture value are calculated, and the water stress risk value is obtained based on the first water stress contribution value and the second water stress contribution value.

[0077] Optionally, the second calculation module 309 is further specifically used for: obtaining a first crop growth stage coefficient corresponding to the first target soil moisture value and a second crop growth stage coefficient corresponding to the second target soil moisture value of the crop to be planted within the growth cycle, wherein the first crop growth stage coefficient and the second crop growth stage coefficient are used to characterize the sensitivity of the crop to water stress within the growth cycle; calculating the product of the water deficit value and the first crop growth stage coefficient to obtain a first water stress contribution value for each first target soil moisture value; calculating the product of the water excess value and the second crop growth stage coefficient to obtain a second water stress contribution value for each second target soil moisture value; and weighted summing the first water stress contribution value and the second water stress contribution value to obtain the water stress risk value.

[0078] Optionally, the third determining module 310 is specifically used for: multiplying the water stress risk value by the environmental impact coefficient of each sampling area to obtain a comprehensive stress risk coefficient for each sampling area, wherein the comprehensive stress risk coefficient is used to characterize the degree of adverse impact on crop growth in the sampling area; multiplying the preset standard plant spacing by the reciprocal of the comprehensive stress risk coefficient to obtain the initial plant spacing for each sampling area, wherein the preset standard plant spacing is the minimum plant spacing requirement for the crop to be planted under a preset standard growth environment; and rounding the initial plant spacing up to the nearest gear value achievable by the rice transplanter to obtain the planting plant spacing.

[0079] It should be noted that the device provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0080] This embodiment also discloses an electronic device, as shown in the reference. Figure 4 The electronic device may include: at least one processor 401, at least one communication bus 402, a user interface 403, a network interface 404, and at least one memory 405. The communication bus 402 is used to enable communication between these components. The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The processor 401 may include one or more processing cores. The processor 401 connects to various parts of the server using various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and by calling data stored in the memory 405. The memory 405 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 405 may include a non-transitory computer-readable medium. The memory 405 can be used to store instructions, programs, code, code sets, or instruction sets. It should be noted that, for the sake of simplicity, the aforementioned method embodiments are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps may be performed in other orders or simultaneously.

[0081] The above description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure.

Claims

1. A method of setting plant spacing of a rice transplanter, characterized by, The method comprises: obtaining meteorological prediction data of a target planting area within a preset time period; obtaining a water requirement interval of a growth cycle of a to-be-planted crop within the preset time period; obtaining soil moisture and terrain elevation data of a plurality of sampling areas in the target planting area, the sampling areas being divided by a preset rule from the target planting area; obtaining historical environmental data of the target planting area in a historical time period in which the to-be-planted crop is planted, and a historical crop remote sensing index of the to-be-planted crop under the historical environmental data; performing correlation analysis on the historical environmental data and the historical crop remote sensing index to calculate an environmental influence coefficient of each sampling area, the environmental influence coefficient being used to represent the influence degree of a planting environment on crop growth; determining a water collection path network of the target planting area based on the terrain elevation data, the water collection path network comprising a plurality of target water flow paths, the target water flow paths being used to represent the flow trend of water on the ground; determining a soil moisture change sequence of each sampling area within the preset time period according to the meteorological prediction data and the water collection path network; performing numerical superposition of soil moisture change values in the soil moisture change sequence on soil moisture of each sampling area in time sequence to obtain a soil moisture sequence of each sampling area within the preset time period; calculating a water stress risk value of the growth cycle based on the soil moisture sequence and the water requirement interval; determining a planting plant distance of each sampling area based on the water stress risk value and the environmental influence coefficient.

2. The method of claim 1, wherein, The correlation analysis on the historical environmental data and the historical crop remote sensing index to calculate the environmental influence coefficient of each sampling area specifically comprises: identifying an abnormal area, the abnormal area being a sampling area with a data fluctuation coefficient of the historical crop remote sensing index greater than a preset fluctuation threshold; performing terrain feature clustering analysis on the abnormal area to obtain a terrain feature similarity between the abnormal areas, and determining the abnormal areas with a terrain feature similarity greater than a preset similarity threshold as abnormal areas of the same category; obtaining standard climate data of a target category abnormal area, constructing a standard local microclimate model of the target category abnormal area, the target category abnormal area being any category abnormal area; calculating the environmental influence coefficient of each sampling area based on the standard local microclimate model and the historical environmental data.

3. The method of claim 2, wherein, The calculation of the environmental influence coefficient of each sampling area based on the standard local microclimate model and the historical environmental data specifically comprises: based on an environmental feature template in the standard local microclimate model, calculating a deviation parameter of the historical environmental data of the abnormal area from the environmental feature template, and correcting the historical environmental data of the abnormal area according to the deviation parameter to obtain target historical environmental data; performing multiple regression analysis on the target historical environment data and the historical crop remote sensing index to obtain a first influence weight of the target historical environment data on crop growth, and performing weighted calculation on the first influence weight and the target historical environment data corresponding to each of the abnormal regions to obtain a first environment influence coefficient of each of the abnormal regions; for normal regions, performing multiple regression analysis on the historical environment data and the historical crop remote sensing index to obtain a second influence weight of the historical environment data on crop growth, performing weighted calculation on the second influence weight and the historical environment data corresponding to each of the normal regions to obtain a second environment influence coefficient of each of the normal regions, and obtaining the environment influence coefficient according to the first environment influence coefficient and the second environment influence coefficient, the normal regions being all the sampling regions in the target planting region except the abnormal regions.

4. The method of claim 1, wherein, The method further comprises the following steps of: calculating, based on the terrain elevation data, a ratio of an elevation difference between a target sampling region and a sampling region adjacent to the target sampling region in a preset direction to a sampling interval to obtain a slope value of the target sampling region in each of the preset directions, the target sampling region being any sampling region in the terrain elevation data; taking a preset direction corresponding to a maximum slope value among the slope values of the target sampling region in each of the preset directions as a water flow direction of the target sampling region; connecting the target sampling region and a downstream sampling region corresponding to the target sampling region based on the water flow direction to obtain a target water flow path, the downstream sampling region being a sampling region adjacent to the target sampling region in the water flow direction, and iteratively performing the above steps on each of the sampling regions in the terrain elevation data to obtain a water collection path network.

5. The method of claim 1, wherein, The method further comprises the following steps of: determining whether there is a continuous water accumulation period in the soil moisture sequence, the continuous water accumulation period being a time period in which soil moisture values at a plurality of time points in the soil moisture sequence are greater than a preset soil saturation water content; if there is the continuous water accumulation period, calculating a time interval between a target time point and an end time point of a target continuous water accumulation period, determining a soil permeability decay coefficient of the target time point, multiplying the soil moisture value of the target time point by the soil permeability decay coefficient to obtain a corrected soil moisture value, and replacing the soil moisture value corresponding to the target time point in the soil moisture sequence with the corrected soil moisture value to obtain a target soil moisture sequence, the target continuous water accumulation period being any of the continuous water accumulation periods, and the target time point being a time point after the target continuous water accumulation period and not within any of the continuous water accumulation periods; calculating a water deficit value of a first target soil moisture value in the target soil moisture sequence, the first target soil moisture value being a target soil moisture value in the target soil moisture sequence that is less than a minimum water requirement threshold of the water requirement interval; and calculate a water surplus value of a second target soil moisture value, the second target soil moisture value being the target soil moisture value greater than the maximum water requirement threshold of the water requirement interval in the target soil moisture sequence; calculate a first water stress contribution value of the first target soil moisture value and a second water stress contribution value of the second target soil moisture value, and obtain the water stress risk value based on the first water stress contribution value and the second water stress contribution value.

6. The method of claim 5, wherein, The calculation of the first water stress contribution value of the first target soil moisture value and the second water stress contribution value of the second target soil moisture value, and the obtaining of the water stress risk value based on the first water stress contribution value and the second water stress contribution value, specifically include: obtain a first crop growth stage coefficient corresponding to the first target soil moisture value and a second crop growth stage coefficient corresponding to the second target soil moisture value of the to-be-planted crop in the growth cycle, the first crop growth stage coefficient and the second crop growth stage coefficient being used to represent the sensitivity of the crop to water stress in the growth cycle; calculate the product of the water deficit value and the first crop growth stage coefficient to obtain the first water stress contribution value of each first target soil moisture value; calculate the product of the water surplus value and the second crop growth stage coefficient to obtain the second water stress contribution value of each second target soil moisture value; weight and sum the first water stress contribution value and the second water stress contribution value to obtain the water stress risk value.

7. The method of claim 1, wherein, The determination of the planting plant spacing of each sampling area based on the water stress risk value and the environmental impact coefficient specifically includes: multiply the water stress risk value by the environmental impact coefficient of each sampling area to obtain a comprehensive stress risk coefficient of each sampling area, the comprehensive stress risk coefficient being used to represent the degree of adverse influence on crop growth in the sampling area; multiply a preset standard plant spacing by the reciprocal of the comprehensive stress risk coefficient to obtain an initial plant spacing of each sampling area, the preset standard plant spacing being the minimum plant spacing requirement of the to-be-planted crop under a preset standard growth environment; round up the initial plant spacing to the nearest gear value that can be achieved by a rice transplanter to obtain the planting plant spacing.

8. A plant spacing setting system for a rice transplanter, characterized in that, It includes: The first acquisition module is used to acquire meteorological prediction data of a target planting area in a preset time period. The second acquisition module is used to acquire a water requirement interval of a growth cycle of a to-be-planted crop in the preset time period. The third acquisition module is used to acquire soil moisture and terrain elevation data of a plurality of sampling areas in the target planting area, the sampling areas being divided by a preset rule from the target planting area. The fourth acquisition module is used to acquire historical environmental data of the to-be-planted crop planted in the target planting area in a historical time period, and a historical crop remote sensing index of the to-be-planted crop under the historical environmental data. The analysis module is configured to analyze the historical environment data and the historical crop remote sensing index, and calculate an environment influence coefficient of each sampling area, the environment influence coefficient being used to represent an influence degree of a planting environment on crop growth. The first determination module is configured to determine a water collection path network of the target planting area based on the terrain elevation data, the water collection path network including a plurality of target water flow paths, the target water flow paths being used to represent water flow trends on the ground surface. The second determination module is configured to determine a soil moisture change sequence of each sampling area in the preset time period according to the weather forecast data and the water collection path network. The first calculation module is configured to sequentially perform numerical superposition of soil moisture change values in the soil moisture change sequence on soil moisture corresponding to each sampling area in time sequence, to obtain a soil moisture sequence of each sampling area in the preset time period. The second calculation module is configured to calculate a water stress risk value of the growth cycle based on the soil moisture sequence and the water requirement interval. The third determination module is configured to determine a planting plant distance of each sampling area based on the water stress risk value and the environment influence coefficient.

9. An electronic device, comprising: One or more processors and memories; The memory is coupled to the one or more processors, and is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the electronic device to perform the method according to any one of claims 1-7. The instructions, when executed on an electronic device, enable the electronic device to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium comprising instructions, characterized in that, ​

Images