Farmland planting method and system based on layout optimization, medium and product

Abstract

A farmland planting method and system based on layout optimization, a medium and a product, the method comprising: acquiring environmental basic data of a target farmland and canopy morphological parameters, root morphological parameters and initial planting parameters of a crop to be planted; constructing a crop space distribution model; respectively calculating a canopy light interception potential index and a root nutrient competition index; constructing a resource coupling evaluation function based on the canopy light interception potential index and the root nutrient competition index; adjusting initial planting parameters in the crop spatial distribution model, updating the crop spatial distribution model, and iteratively calculating a function value of a resource coupling evaluation function based on the updated crop spatial distribution model to perform iterative optimization; and when a preset iteration termination requirement is met, iteration is stopped, and a planting control instruction is generated based on a target planting parameter in the target crop spatial distribution model corresponding to the maximum function value of the resource coupling evaluation function. The reasonability of spatial configuration of farmland crops can be optimized.

Description

Technical Field

[0001] This application relates to the field of farmland layout optimization technology, specifically to a farmland planting method, system, medium, and product based on layout optimization. Background Technology

[0002] With the development of intelligent and precision agriculture technologies, how to achieve a dual improvement in crop yield and resource utilization efficiency on limited arable land resources has become one of the key research focuses in the agricultural field. Especially in mixed or intercropping planting models, the spatial competition among different crops for resources such as nutrients, water, and light is receiving increasing attention. Rational planning of crop spatial layout helps improve land utilization, reduce resource waste, and promote synergistic crop growth, thereby achieving a win-win situation for both ecological and economic benefits.

[0003] In existing technologies, the planting location, density, and combination of different crops are typically determined based on experience or traditional agronomic knowledge. For example, tall crops are intercropped with short crops to utilize vertical space resources. However, planting patterns involving multiple crops in combination or intercropping require consideration of the dynamic competition among crops in terms of light acquisition and root absorption. If the layout allocation is based solely on experience or traditional agronomic knowledge, it is difficult to achieve the coupled optimization of crop spatial layout and resource utilization efficiency, leading to planting strategies that rely on experience-based judgments and affecting the rationality of farmland crop spatial configuration. Summary of the Invention

[0004] This application provides a farmland planting method, system, medium, and product based on layout optimization, which solves the technical problem that existing technologies rely on experience-based judgment and are difficult to achieve coupled optimization of crop spatial layout and resource utilization efficiency, thereby improving the rationality of farmland crop spatial configuration.

[0005] The first aspect of this application provides a farmland planting method based on layout optimization, the method comprising: Acquire basic environmental data of the target farmland and canopy morphology parameters, root morphology parameters and initial planting parameters of the crops to be planted. The basic environmental data includes spatial distribution data of soil nutrients and solar radiation meteorological data of the area. The crops to be planted include highland crops and lowland crops. Based on the environmental data, canopy morphology parameters, root morphology parameters, and initial planting parameters, a crop spatial distribution model is constructed. This crop spatial distribution model is used to characterize the three-dimensional spatial distribution of the target farmland. Based on the crop spatial distribution model, the canopy light interception potential index and root nutrient competition index between the high-lying crop and the low-lying crop were calculated respectively. A resource coupling evaluation function is constructed based on the canopy light interception potential index and the root nutrient competition index. Based on the preset optimization objective and preset optimization algorithm, the initial planting parameters in the crop spatial distribution model are adjusted and the crop spatial distribution model is updated. Based on the updated crop spatial distribution model, the function value of the resource coupling evaluation function is iteratively calculated to perform iterative optimization. When the preset termination iteration requirement is met, the iteration stops. Based on the target planting parameters in the target crop spatial distribution model corresponding to the maximum function value of the resource coupling evaluation function, a planting control command is generated. The planting control command is used to drive agricultural planting machinery to perform planting operations.

[0006] Optionally, a crop spatial distribution model is constructed based on the environmental baseline data, the canopy morphology parameters, the root morphology parameters, and the initial planting parameters, specifically including: Analyze the vertical distribution characteristics of the environmental basic data, and based on the vertical distribution characteristics, divide the vertical space of the target farmland within the preset spatial area into the top photosynthetic zone, the middle growth zone, and the soil root zone; The planar coordinates of the high-lying crop and the low-lying crop in the target farmland are determined based on the initial planting parameters. Based on the canopy morphology parameters, a first three-dimensional canopy bounding box for the high-lying crop and a second three-dimensional canopy bounding box for the low-lying crop are constructed. Based on the planar coordinate position and preset mapping rules, the first canopy bounding box is mapped to the top photosynthetic zone and the middle growth zone, the second canopy bounding box of the low-lying crop is mapped to the middle growth zone, and the root morphology parameters are mapped to the soil root zone to obtain the crop spatial distribution model.

[0007] Optionally, based on the crop spatial distribution model, the canopy light interception potential index and root nutrient competition index between the high-lying crop and the low-lying crop are calculated respectively, specifically including: Acquire the solar trajectory data of the target farmland within a preset growth cycle and the corresponding radiation intensity data of the solar trajectory data; The solar trajectory data is discretized to obtain instantaneous incident vectors with multiple time steps; Based on the crop spatial distribution model and multiple instantaneous incident vectors, the transmission paths of light passing through the top photosynthetic zone and the middle growth zone at different times are constructed respectively; The effective optical path length and canopy porosity of each transmission path through the high-level crop canopy are calculated respectively, and the canopy light interception potential index is determined in combination with the radiation intensity data; Calculate the root overlap volume based on the crop spatial distribution model to determine the interspecific interaction area within the soil root zone; The root nutrient competition index is determined based on the interspecific interaction region.

[0008] Optionally, the effective optical path length and canopy porosity of each transmission path through the upper crop canopy are calculated, and the canopy light interception potential index is determined in conjunction with the radiation intensity data, specifically including: Based on the crop spatial distribution model, the canopy geometric boundary of the high-lying crop is determined, and the geometric intercept length of each transmission path within the canopy geometric boundary is calculated. The leaf tilt angle distribution characteristics of the tall crops are extracted from the canopy morphology parameters, and the average leaf tilt angle, which characterizes the average light-blocking capacity of the canopy, is determined based on the leaf tilt angle distribution characteristics. Based on the geometric projection relationship between the instantaneous incident vector and the average leaf tilt angle at each time step, the instantaneous projection weight coefficient is calculated. The instantaneous projection weight coefficient is used to characterize the projection ratio of a unit leaf area in the direction of light incidence. The effective optical path length is obtained by weighting the geometric intercept length based on the instantaneous projection weight coefficient. The effective optical path length characterizes the physical blocking strength of light rays passing through the leaf tissue in the direction of the instantaneous incident vector. Based on the effective optical path length and the leaf volume density in the canopy morphology parameters, the light transmittance probability of the tall crop in each of the transmission path directions is calculated using a preset light attenuation physical model to obtain the canopy porosity. Using the radiation intensity data as weights, the canopy porosity of each transmission path is weighted and summed to obtain the canopy light interception potential index.

[0009] Optionally, the root nutrient competition index is determined based on the interspecific interaction region, specifically including: The ratio of the preset theoretical nutrient requirement of the interspecific interaction area to the available nutrient content in the soil nutrient spatial distribution data is calculated to obtain the nutrient supply-demand ratio. A nutrient stress weighting coefficient is constructed based on the nutrient supply-demand ratio, wherein when the theoretical nutrient demand is greater than the available soil nutrient content, the nutrient stress weighting coefficient is greater than one. The root nutrient competition index is obtained by weighting the root overlap volume based on the nutrient stress weighting coefficient.

[0010] Optionally, a resource coupling evaluation function is constructed based on the canopy light interception potential index and the root nutrient competition index, specifically including: Obtain the light response weighting coefficient of the crop to be planted to light resources and the nutrient response weighting coefficient to nutrient resources; The total root volume of the soil root zone is obtained, and the ratio of the root nutrient competition index to the total root volume is determined as the normalized nutrient competition index, which is used to eliminate dimensional differences. The product of the light response weighting coefficient and the canopy light interception potential index is determined as the light ecological benefit item; The product of the nutrient response weighting coefficient and the normalized nutrient competition index is determined as the nutrient competition penalty term; The resource coupling evaluation function is constructed based on the light ecological benefit term and the nutrient competition penalty term.

[0011] Optionally, based on a preset optimization objective and a preset optimization algorithm, the initial planting parameters in the crop spatial distribution model are adjusted, and the crop spatial distribution model is updated, specifically including: Based on the row spacing and plant spacing constraints in the initial planting parameters, a parameter feasible region for the crop to be planted in the farmland plane is constructed. The parameter feasible region is used to limit the physical adjustment boundary of the planting layout. Based on the preset optimization algorithm and the preset optimization objective, a parameter perturbation vector is generated within the parameter feasible region. The parameter perturbation vector includes the row spacing adjustment step size and the plant spacing adjustment step size. The parameter perturbation vector is superimposed on the initial planting parameters in the crop spatial distribution model to obtain candidate planting parameters, and it is verified whether the candidate planting parameters are located within the parameter feasible region. If the verification is successful, the updated planar coordinate positions of the high-position crop and the low-position crop are regenerated based on the candidate planting parameters; Based on the updated planar coordinate position, the canopy morphology parameters and root morphology parameters of the high-lying crops and the low-lying crops are remapped to the vertical space corresponding to the crop spatial distribution model, so as to update the crop spatial distribution model.

[0012] In a second aspect, embodiments of this application provide a layout-optimized farmland planting system, which includes one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions, and the one or more processors invoke the computer instructions to cause the layout-optimized farmland planting system to perform the method described in the first aspect and any possible implementation thereof.

[0013] Thirdly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a layout-optimized farmland planting system, cause the layout-optimized farmland planting system to perform the method described in the first aspect and any possible implementation thereof.

[0014] Fourthly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a layout-optimized farmland planting system, cause the layout-optimized farmland planting system to perform the method described in the first aspect and any possible implementation thereof.

[0015] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: 1. By integrating crop canopy morphology parameters, root morphology parameters, and soil nutrient spatial distribution data and solar radiation meteorological data of the target farmland, a crop spatial distribution model that reflects the distribution characteristics of different crops in three-dimensional space was constructed. Based on this, canopy light interception potential index and root nutrient competition index were introduced to establish a quantifiable resource coupling evaluation mechanism. Then, by using preset optimization objectives and optimization algorithms, the initial planting parameters were continuously adjusted and iterated, enabling the model to dynamically optimize the spatial layout of different crops. This achieves coordinated allocation and efficient utilization of key resources such as light and nutrients for multiple crops, improving the rationality of farmland crop spatial configuration.

[0016] 2. By incorporating the vertical distribution characteristics of the target farmland environmental data when constructing the crop spatial distribution model, the pre-defined spatial area is divided into the top photosynthetic zone, the middle growth zone, and the soil root zone. Combined with the initial planting parameters, the distribution positions of high-rise and low-rise crops in the planar coordinate system are determined. Then, a three-dimensional canopy bounding box is constructed based on the canopy morphology parameters and mapped to the corresponding spatial area. This enables the constructed crop spatial distribution model to accurately characterize the positional relationship and geometric morphology of different crops in the vertical spatial structure, providing a structured basis for the subsequent quantitative analysis of resource competition. Building upon this foundation, by incorporating solar trajectory data and corresponding radiation intensity information, solar illumination is modeled temporally. Combined with instantaneous incidence vectors at multiple time steps, a path model for light traversing the top photosynthetic zone and the middle growth zone is constructed. This further calculates the propagation path length and porosity of light within the crop canopy, accurately reflecting the shading of light resources from lower-lying crops by higher-lying crops, thus quantifying the canopy light interception potential of lower-lying crops. Simultaneously, a root overlap model is established within the soil root zone based on root morphology parameters, identifying interspecific interaction areas and determining root nutrient competition indicators. This allows for the dynamic quantification of competition among crops in the two key resource dimensions of light and nutrients. Through these processes, the accuracy and completeness of crop spatial distribution modeling are significantly improved. Furthermore, this provides a reliable basis for establishing subsequent resource coupling evaluation functions and optimizing planting parameters, enabling the system to more scientifically assess the resource synergy potential among crops, thereby promoting the intelligent and refined process of layout optimization in multi-crop mixed planting models.

[0017] 3. By further refining the geometric description of the canopy structure of tall crops based on the crop spatial distribution model, canopy geometric boundary information is extracted and combined with the solar incident path to calculate the geometric intercept length of light rays intersecting with the crop canopy during transmission. This allows for a quantitative expression of the shading effect of each incident path in three-dimensional space. Furthermore, by introducing the leaf tilt angle distribution characteristics of tall crops, the average leaf tilt angle, representing the light-receiving capacity per unit leaf area under different incident directions, is calculated. Based on the geometric relationship between the leaf tilt angle and the instantaneous incident vector, a projection weighting coefficient is constructed to weight and correct the geometric intercept length, obtaining an effective optical path length that better reflects physical shading characteristics. Then, combined with leaf volumetric density parameters, a light attenuation physical model is used to accurately calculate the light transmission probability of light rays passing through the canopy, obtaining canopy porosity under different path conditions. Finally, using radiation intensity data as a weighting factor, the canopy porosity of all paths is weighted and integrated to form a canopy light interception potential index that reflects the amount of light energy that low-lying crops can obtain. The above calculation process not only significantly improves the accuracy and directional discrimination ability of canopy shading modeling, but also makes the quantitative assessment of the light environment of low-lying crops more objective and reliable, providing a solid data foundation for subsequent resource coupling evaluation, thereby helping to achieve the rational allocation and layout optimization of light resources for various crops within the spatial structure. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of a farmland planting method based on layout optimization in an embodiment of this application; Figure 2 This is a flowchart illustrating the calculation of the canopy light interception potential index and the root nutrient competition index in the embodiments of this application; Figure 3 This is a schematic diagram of a farmland planting system based on layout optimization in an embodiment of this application.

[0019] Explanation of reference numerals in the attached drawings: 301, Central Processing Unit; 302, Read-Only Memory; 303, Random Access Memory; 304, Bus; 305, Input / Output Interface; 306, Input Section; 307, Output Section; 308, Storage Section; 309, Communication Section; 310, Driver; 311, Removable Media. Detailed Implementation

[0020] 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.

[0021] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0022] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0023] Figure 1 This is a schematic flowchart of a farmland planting method based on layout optimization in an embodiment of this application.

[0024] Please see Figure 1 This application provides an embodiment of a farmland planting method based on layout optimization, the method comprising: S101. Obtain basic environmental data of the target farmland and canopy morphology parameters, root morphology parameters and initial planting parameters of the crops to be planted. The basic environmental data includes spatial distribution data of soil nutrients and solar radiation meteorological data of the area. The crops to be planted include high-rise crops and low-rise crops.

[0025] In the process of optimizing farmland planting layout, in order to construct a three-dimensional model that can truly reflect the spatial distribution relationship of crops and the resource competition mechanism, it is first necessary to obtain basic input data that is highly related to the planting environment and crop growth characteristics of the target area.

[0026] The environmental baseline data primarily describes the spatial and temporal distribution characteristics of natural resources outside farmland, specifically including spatial distribution data of soil nutrients and solar radiation meteorological data. Soil nutrient spatial distribution data refers to two-dimensional or three-dimensional distribution maps of major nutrients such as nitrogen, phosphorus, and potassium within the farmland area, obtained through gridded sampling of the target farmland and combined with rapid soil detection technologies (such as near-infrared spectroscopy and visible light reflectance analysis). This data characterizes the resource accessibility of different crop root systems in the soil and forms the basis for subsequent analysis of root competition relationships. Solar radiation meteorological data refers to information on the variation of solar radiation intensity and solar altitude angle in a specific area throughout the year or a specific growth cycle, obtained based on meteorological stations or remote sensing satellite data. This data, combined with solar motion models, can be used to calculate the incident direction and intensity of light on the ground at any given time, serving as a core input for constructing crop canopy illumination models.

[0027] The crops to be planted are divided into two categories: high-mountain crops and low-mountain crops. In the process of crop spatial distribution modeling, to effectively express the differences in growth distribution and resource acquisition levels among different crops in vertical space, the crops to be planted are divided into high-mountain crops and low-mountain crops based on their plant type characteristics and canopy space occupancy during the growing season. High-mountain crops refer to those whose main canopy structure is distributed in the upper layer of the farmland's vertical space, typically possessing greater plant height, upright stem structure, and strong light competition ability; common examples include corn, sorghum, and sunflower. Low-mountain crops, on the other hand, refer to those whose canopy structure is mainly concentrated in the middle and lower layers of space, with shorter overall plant height, denser canopy, and wide but shallow root systems; representative crops include soybeans, peanuts, and wheat.

[0028] This classification is based not only on the absolute value of plant height but also on the effective shading height area of ​​the canopy and the relative height variation trend during the growth cycle. For example, if the upper edge of the canopy of one crop is consistently higher than that of another crop during the same growth period, and a significant shading relationship is formed for most of the time, the former is classified as a high-mountain crop, and the latter as a low-mountain crop. Furthermore, this classification also considers the ecological function role of crops in mixed cropping patterns. For instance, high-mountain crops typically provide shade and regulate temperature and humidity, while low-mountain crops largely rely on the microclimate created by high-mountain crops for their growth.

[0029] High-rise crops are those whose plant height is significantly higher than other crops during their growth cycle, and whose canopy is mainly distributed in the upper space, such as corn and sorghum. Low-rise crops are those whose plant height is lower, and whose canopy is mainly concentrated in the middle space, such as soybeans and peanuts. The combined planting of high-rise and low-rise crops aims to utilize the vertical space resources of farmland to increase the overall output per unit area.

[0030] Crop canopy morphology parameters describe the spatial structure of the aboveground parts of the crop, mainly including maximum canopy width, canopy height, leaf area density, and leaf tilt angle distribution. These parameters can be obtained through field measurements, image recognition, and lidar scanning, and are used to subsequently construct a three-dimensional canopy structure model. Root morphology parameters describe the structural characteristics of the crop's underground root system, mainly including maximum root depth, root horizontal expansion radius, and root density distribution function, and are used to estimate the root distribution volume in the soil and its overlap with other crops.

[0031] Initial planting parameters refer to the crop planting layout plan before optimization and adjustment, mainly including crop variety information, planting density, row spacing, plant spacing, and planting location coordinates. These parameters can be derived from human experience or from historical operation records or agricultural machinery operation paths, and serve as the initial input for subsequent spatial layout optimization.

[0032] S102. Based on the environmental baseline data, the canopy morphology parameters, the root morphology parameters, and the initial planting parameters, a crop spatial distribution model is constructed. The crop spatial distribution model is used to characterize the three-dimensional spatial distribution of the target farmland.

[0033] Step S102, based on the environmental baseline data of the target farmland and combined with canopy morphology parameters, root morphology parameters, and initial planting parameters of different crops, constructs a crop spatial distribution model to express the spatial structural characteristics of crops within a unified spatial coordinate system. This model not only presents the planar arrangement of crops but also reflects their canopy cover level and root distribution depth in the vertical space of the farmland. Therefore, it is necessary to comprehensively consider the vertical distribution characteristics of environmental resources and the structural characteristics of the crops themselves, functionally partitioning the farmland space and mapping the canopy and root structures of different crops to the corresponding areas, thereby establishing a crop distribution model with three-dimensional spatial semantics. This provides a calculable spatial basis for subsequent analysis of light and nutrient resource competition. Specifically, this may include the following steps: Analyze the vertical distribution characteristics of the environmental basic data, and based on the vertical distribution characteristics, divide the vertical space of the target farmland within the preset spatial area into the top photosynthetic zone, the middle growth zone, and the soil root zone; The planar coordinates of the high-lying crop and the low-lying crop in the target farmland are determined based on the initial planting parameters. Based on the canopy morphology parameters, a first three-dimensional canopy bounding box for the high-lying crop and a second three-dimensional canopy bounding box for the low-lying crop are constructed. Based on the planar coordinate position and preset mapping rules, the first canopy bounding box is mapped to the top photosynthetic zone and the middle growth zone, the second canopy bounding box of the low-lying crop is mapped to the middle growth zone, and the root morphology parameters are mapped to the soil root zone to obtain the crop spatial distribution model.

[0034] In constructing a crop spatial distribution model, to ensure the model possesses resource stratification perception capabilities, it is necessary to first analyze the vertical distribution characteristics of the target farmland's environmental baseline data. The solar radiation meteorological data and soil nutrient spatial distribution data included in the environmental baseline data correspond to the upper-layer light resource distribution and lower-layer soil resource distribution in vertical space, respectively. By analyzing the attenuation changes of solar radiation at different heights, combined with the actual shading height range of the crop canopy, the space above the farmland can be divided into the top photosynthetic zone and the middle growth zone. Simultaneously, based on the changing trends of effective nutrient concentrations at various depths in the soil profile, the depth range of the main root activity area is determined, and the underground part is divided into the soil root zone. The top photosynthetic zone refers to the spatial area that mainly receives direct sunlight and is dominated by the high-level crop canopy; the middle growth zone is the area where low-level crop leaves are densely distributed and light is significantly affected by shading; the soil root zone accommodates the crop root structure and is the foundational layer for analyzing nutrient acquisition efficiency and root interaction. This functional vertical partitioning not only helps in the subsequent establishment of light interception simulation and root competition models based on spatial location, but also allows the spatial distribution relationships of different types of crops to be clearly expressed and used for calculation.

[0035] After completing the vertical spatial division, the planar coordinate positions of high-lying and low-lying crops in the crop spatial distribution model need to be determined based on the initial planting parameters. The initial planting parameters include row spacing, plant spacing, sowing start coordinates, planting density, and crop type information. These parameters are the initial configuration data for the planting layout, typically derived from agricultural machinery operation path records or planting design schemes. Based on a standardized two-dimensional coordinate system (such as a Cartesian coordinate system with the lower left corner of the farmland as the origin), the planar coordinates of each individual crop are calculated sequentially according to the row and plant spacing rules and the crop arrangement order. Independent coordinate sets are generated for high-lying and low-lying crops to establish the correspondence between species stratification and spatial distribution in the model. This process provides a basic coordinate framework for subsequent spatial structure modeling and also provides controllable variables for feasible region perturbation and optimization.

[0036] Based on the known planar coordinates of the crop, a three-dimensional canopy bounding box is constructed using crop canopy morphology parameters. These parameters include canopy height, canopy radius, maximum canopy width, leaf density, and leaf tilt angle distribution, describing the spatial morphology of the canopy region occupied by the crop. The three-dimensional canopy bounding box is a simplified geometric model representing the canopy structure, typically approximated using cylindrical, ellipsoidal, or polyhedral forms, effectively representing the spatial extent of a single crop. The first three-dimensional canopy bounding box for taller crops is constructed with a relatively high spatial volume in the vertical direction based on its canopy height and width parameters, while the second three-dimensional canopy bounding box for lower crops is relatively shorter and mostly concentrated in the middle and lower layers. This type of bounding box can serve not only as the spatial boundary for ray tracing and projection occlusion analysis but also for simulating canopy overlap and spatial occlusion behavior.

[0037] Subsequently, based on the planar coordinates of the crops and preset mapping rules, the three-dimensional canopy bounding box is mapped to the aforementioned vertical functional areas, achieving precise positioning of the crop structure in three-dimensional space. The mapping rules are a set of spatial alignment standards set according to the spatial centroid position of the crop type and its canopy height. For example, the upper edge of the canopy of tall crops preferentially covers the top photosynthetic zone, while its lower canopy extends to cover the middle growth zone; the canopy of low-lying crops is mainly mapped to the middle growth zone to avoid spatial coupling with tall crops in the top layer area. Simultaneously, root morphology parameters are also used to construct the spatial structure of the underground root system. Key parameters include maximum root depth, horizontal expansion radius, and root density distribution function. By generating a root bounding box centered on the planar coordinates and combining root parameters, and mapping it to the soil root zone, the complete layout of the crop in the entire three-dimensional space is achieved. The resulting crop spatial distribution model can be used for subsequent functional modules such as illumination simulation, root overlap analysis, and resource coupling evaluation, serving as the core modeling foundation for optimizing farmland spatial planting.

[0038] It should be noted that the spatial division of the top photosynthetic zone, the middle growth zone, and the soil root zone described in this embodiment is not a physical, absolute, and static division of the vertical space of farmland, but rather a logical hierarchical approach established based on the needs of crop structure modeling and functional simulation. This hierarchical approach is designed to better express the hierarchical and functional differentiation of resource utilization (such as light, space, and nutrients) by different crop organs in the vertical space during the modeling process, thereby facilitating the zonal representation and efficient calculation of processes such as light transmission simulation, canopy shading analysis, and root overlap calculation.

[0039] In practical applications, crop height, canopy distribution, and root extension exhibit continuity and variability. It's possible for lower-lying crops to partially penetrate the middle layer and enter the top layer, or for lower leaves of higher-lying crops to extend into the middle layer. Such phenomena are permissible in the model and do not limit its expressive power due to logical layering. Spatial layering serves only as an auxiliary delineation of functional regions during the modeling process, facilitating the classification and calculation of resource acquisition behaviors in different parts of the crop. The model itself still uses continuous spatial coordinates for three-dimensional representation and does not artificially sever crop structure or restrict the naturalness of its growth simulation.

[0040] For example, in a maize-soybean intercropping system, if a soybean variety's main stem height exceeds 1 meter in the later stages of its growth, its canopy tip may have entered the top photosynthetic zone, but most of its leaf area remains concentrated in the middle growth zone. In this case, the model can still dynamically adjust its coverage ratio in each functional zone through bounding box volume scaling, without needing to reclassify crop types or modify the spatial hierarchy. This approach not only maintains the structural continuity of the model but also ensures the accuracy and applicability of the simulation results.

[0041] S103. Based on the crop spatial distribution model, calculate the canopy light interception potential index and root nutrient competition index between the high-lying crop and the low-lying crop, respectively.

[0042] After constructing the crop spatial distribution model, in order to further reveal the resource acquisition capabilities and competitive relationships among different crops under spatial layout conditions, it is necessary to quantitatively assess the resource utilization between tall and short crops based on this model. Therefore, in step S103, the canopy light interception potential index and root nutrient competition index are introduced as key evaluation parameters. The canopy light interception potential index is used to measure the actual solar radiation energy that short crops can acquire in the middle growth zone, reflecting their light resource utilization potential under the shading effect of tall crop canopies; the root nutrient competition index is used to assess the degree of spatial overlap of different crop roots in the soil root zone, thereby determining their interaction intensity under limited soil nutrient conditions. Figure 2 This is a flowchart illustrating the calculation of the canopy light interception potential index and the root nutrient competition index in this application embodiment. The following is a summary of the process. Figure 2 Step S103 will be explained in detail.

[0043] S201. Obtain the solar trajectory data of the target farmland within a preset growth cycle and the radiation intensity data corresponding to the solar trajectory data.

[0044] Solar trajectory data refers to the angular path formed by the sun's movement across the sky under specific geographical location and time conditions, including the changes in solar altitude and azimuth angles over time. This type of data is typically calculated using astronomical algorithm models (such as the Solar Position Algorithm, SPA) combined with the latitude and longitude coordinates, altitude, and daily time points within the target farmland's growth cycle. Meanwhile, radiation intensity data refers to the solar radiation energy received per unit area per unit time, commonly measured in W / m². This data can be obtained through meteorological station measurements, satellite remote sensing data inversion, or historical climate database extrapolation, and must be synchronized with solar angle data to ensure temporal resolution in the illumination simulation.

[0045] This step is based on the following logic: The effectiveness of crop canopy in intercepting solar radiation is closely related to the sun's position in the sky, and the sun's position changes over time, with its altitude and azimuth angles determining the angle of incidence of light. Simultaneously, the intensity of solar radiation per unit time directly affects the actual light energy received by the crop. Therefore, illumination simulation must be based on a dynamic solar trajectory, combined with light intensity data, to realistically reproduce illumination conditions at different times. This approach can not only simulate instantaneous illumination distribution but also accumulate to obtain the total amount of light energy acquired by the crop throughout its entire growth cycle, providing the necessary spatiotemporal basis for calculating light interception potential indicators.

[0046] At the operational level, the start and end times of the growth cycle are first determined based on the sowing and harvesting periods of the target crop. This time period is then divided into hourly or smaller time intervals, forming a set of time nodes. Subsequently, using each time node as input, the solar position calculation module is invoked, and combined with the geographical coordinates of the farmland, the corresponding solar altitude angle and azimuth angle are calculated to obtain complete solar trajectory data. Next, by accessing historical data from local agricultural meteorological stations or third-party meteorological service platforms, total solar radiation intensity data matching the aforementioned time nodes is obtained and time-series processed to establish a radiation intensity curve synchronized with the solar angle.

[0047] For example, in a typical farmland at 35 degrees north latitude, assuming the planting cycle for corn and soybeans is from May 1st to September 30th, the effective sunlight period is selected from 8:00 AM to 6:00 PM each day. Ten time points are calculated daily, with hourly intervals. At each time point, the solar altitude angle and azimuth angle are calculated using a solar position model, along with the corresponding radiation intensity (e.g., at 10:00 AM, the radiation intensity is 720 W / m², the solar altitude angle is 45°, and the azimuth angle is 110°). This process is repeated to ultimately form a complete sequence of solar trajectory and light intensity data for the growing cycle, providing realistic and dynamic boundary conditions for subsequent light propagation path construction and light interception simulation. This method ensures the accuracy and timeliness of the model's light input, thereby improving the reliability of canopy light interception analysis results and the scientific rigor of agricultural layout optimization.

[0048] S202. Discretize the solar trajectory data to obtain instantaneous incident vectors with multiple time steps.

[0049] The solar trajectory data consists of the angle values ​​of the sun's position in the sky over a continuous time period. Essentially, it is a continuous function recording the sun's altitude and azimuth angles at different points in time. Since the crop spatial distribution model used for subsequent light transmission calculations is a discrete three-dimensional geometric model, the solar trajectory needs to be transformed from a continuously changing angular form into a discrete set of directional light incident vectors in order to perform progressive ray tracing and penetration analysis within the spatial model.

[0050] In practical processing, the time range is first selected based on the crop's growth cycle and the effective sunshine window, for example, from 6:00 AM to 6:00 PM daily as the analysis period. The time step is then set according to accuracy requirements, such as every half hour or hour as a time node. For each selected time point, a solar angle calculation model (such as the Solar Position Algorithm SPA) is used to obtain the solar altitude angle and azimuth angle at that moment, and these are converted into a three-dimensional spatial direction vector, denoted as the instantaneous incident vector. The direction vector is generated using a conversion formula from spherical coordinates to rectangular coordinates, where the solar altitude angle determines the vertical component of the vector, and the azimuth angle controls the horizontal direction of the vector. The resulting set of instantaneous incident vectors accurately represents the incident direction of sunlight at different time points, providing an angular basis for the interaction between sunlight and the crop canopy.

[0051] Discretization not only transforms the continuous solar motion process into a computable discrete input, but also ensures the sensitivity of the simulation system under different illumination conditions, thereby improving the timeliness and dynamism of canopy illumination analysis. Furthermore, this processing method facilitates a one-to-one correspondence with radiation intensity data, enabling the construction of time-series light energy input scenarios. This allows subsequent calculations of light interception indices to accurately reflect the energy distribution over different time periods.

[0052] For example, if a farmland is discretized at 1-hour intervals, and its solar altitude angle at 10:00 AM on June 21st is 60° and azimuth angle is 120°, then according to the spherical coordinate transformation formula, its instantaneous incident vector can be obtained as vector V=(x, y, z), where x=cos(60°)·sin(120°), y=cos(60°)·cos(120°), and z=sin(60°). After standardization, this vector can be used for ray tracing in a spatial model to simulate the path of sunlight incident from a specific direction to the crop canopy at that moment. By performing similar processing at each time point, a complete sequence of instantaneous incident vectors is finally obtained, laying the computational foundation for multi-time period illumination analysis.

[0053] S203. Based on the crop spatial distribution model and multiple instantaneous incident vectors, construct the transmission paths of light passing through the top photosynthetic zone and the middle growth zone at different times.

[0054] Because crop canopy structures have complex three-dimensional volume distribution characteristics, and different crop types have different vertical positions and densities in space, light will experience phenomena such as shading, scattering, and transmission during its passage. Therefore, it is necessary to construct dynamic light transmission paths based on real geometric models and light directions to accurately reflect the distribution of light energy in vertical space.

[0055] In the specific implementation process, the crop spatial distribution model is first treated as a voxelized three-dimensional spatial grid model. A voxel refers to a small, uniform cubic unit that divides the three-dimensional space. Each voxel unit can record whether its area is occupied by the crop canopy. In this spatial model, the hierarchical position of the canopy bounding boxes of high-mountain and low-mountain crops in vertical space is clearly defined. That is, the canopy bounding boxes of high-mountain crops span the top photosynthetic zone and the middle growth zone, while the canopy bounding boxes of low-mountain crops are mainly concentrated in the middle growth zone.

[0056] Then, the instantaneous incident vector at each time step is read sequentially. The instantaneous incident vector is a unit vector representing the spatial direction of sunlight at a certain moment, usually calculated from the solar altitude angle and azimuth angle, and is used to guide the direction of light propagation in the model. Starting from each incident vector, light rays are emitted from the top of the model along that direction, and a voxel-based ray tracing algorithm (such as the DDA algorithm or a 3D extension of the Bresenham algorithm) is used for voxel-by-voxel traversal. During the traversal, the path length of the light rays in different vertical partitions (i.e., the top photosynthetic zone and the middle growth zone) is recorded, and it is determined whether the path passes through the canopy area. If a voxel unit is marked as crop canopy, it is considered that the voxel obstructs the light to a certain extent. The light intensity is attenuated according to the canopy density and thickness parameters, and the effective length of the penetration path is accumulated.

[0057] To ensure the spatial accuracy of the path construction, the incident rays are typically arrayed with a certain spatial resolution. This involves generating multiple uniformly distributed incident points at the top of the crop model as light emission sources to simulate the overall illumination distribution of the entire farmland at that time step. By constructing and traversing paths for each incident point, the complete illumination transmission network at that time point is finally obtained in the entire spatial model.

[0058] Through the above implementation method, it is possible to construct the light transmission paths in the top photosynthetic zone and the middle growth zone at different time points, and assign attribute parameters such as traversal length, traversal density, and traversal area to each path. This processing effect makes it possible to subsequently calculate the light shading impact of taller crops on lower crops, and also provides structural input for the effective light energy actually received by lower crops.

[0059] For example, at a specific time point, such as 10:00 AM, if the solar altitude angle is 45° and the azimuth angle is 135°, the corresponding instantaneous incident vector is V = (0.5, 0.5, 0.707). Multiple incident points are generated at 0.5-meter intervals at the top of the crop spatial distribution model. Light rays are emitted from each point along the direction of vector V, and the number of high-level crop canopy voxels encountered by the light rays in the top photosynthetic zone, as well as the degree of light intensity attenuation along the path, are recorded. If a path traverses 6 high-level crop voxels and 3 mid-level canopy voxels, the light interception potential of the mid-level growth zone can be quantitatively analyzed by combining radiation intensity data. This path construction method ensures the physical realism and spatial adaptability of the illumination simulation, and is a key technological foundation for optimizing the planting layout in precision agriculture.

[0060] S204. Calculate the effective optical path length and canopy porosity of each transmission path through the high-level crop canopy, and determine the canopy light interception potential index in combination with the radiation intensity data.

[0061] In step S204, to achieve a quantitative assessment of the actual light resource acquisition capacity of low-lying crops, it is necessary to conduct an in-depth analysis of the energy attenuation of light as it passes through the canopy of high-lying crops, based on the light transmission paths already constructed in the crop spatial distribution model. This allows for the accurate calculation of the light transmittance of each transmission path within the middle growth zone. Specifically, by identifying the geometric intercept length of each light ray within the canopy region of the high-lying crops and combining it with the leaf structure characteristics of the high-lying crops, the effective optical path length and canopy porosity in the transmission direction are further calculated. Canopy porosity is used to characterize the transmittance probability of light transmitted along this path. Based on the comprehensive light transmittance of all paths, combined with the radiant intensity data at each moment, the light energy acquisition situation within the space where the low-lying crops are located is assessed, i.e., the canopy light interception potential index. This can specifically include the following steps: Based on the crop spatial distribution model, the canopy geometric boundary of the high-lying crop is determined, and the geometric intercept length of each transmission path within the canopy geometric boundary is calculated. The leaf tilt angle distribution characteristics of the tall crops are extracted from the canopy morphology parameters, and the average leaf tilt angle, which characterizes the average light-blocking capacity of the canopy, is determined based on the leaf tilt angle distribution characteristics. Based on the geometric projection relationship between the instantaneous incident vector and the average leaf tilt angle at each time step, the instantaneous projection weight coefficient is calculated. The instantaneous projection weight coefficient is used to characterize the projection ratio of a unit leaf area in the direction of light incidence. The effective optical path length is obtained by weighting the geometric intercept length based on the instantaneous projection weight coefficient. The effective optical path length characterizes the physical blocking strength of light rays passing through the leaf tissue in the direction of the instantaneous incident vector. Based on the effective optical path length and the leaf volume density in the canopy morphology parameters, the light transmittance probability of the tall crop in each of the transmission path directions is calculated using a preset light attenuation physical model to obtain the canopy porosity. Using the radiation intensity data as weights, the canopy porosity of each transmission path is weighted and summed to obtain the canopy light interception potential index.

[0062] In determining the canopy geometric boundary of the tall crops based on the crop spatial distribution model and calculating the geometric intercept length of each transmission path within the canopy geometric boundary, it is first necessary to clarify that the canopy geometric boundary refers to the three-dimensional spatial outline defined by the crop canopy morphology parameters, often expressed in the form of a bounding box to represent the spatial extent occupied by the crop canopy. Through the first three-dimensional canopy bounding box of the tall crops mapped in the crop spatial distribution model, the specific spatial extent of each individual tall crop within the top photosynthetic zone and the middle growth zone can be accurately obtained. Based on the above bounding box information, combined with the instantaneous incident vector generated at each time step, the starting and ending coordinates of each ray within the canopy boundary are determined using a geometric line and cube intersection determination algorithm, thereby calculating the geometric intercept length of the path within the canopy volume. This length is one of the fundamental parameters for subsequently evaluating the light penetration ability of the canopy, and can accurately reflect the distance the light is blocked by the crop in space. For example, at a certain point in time, a ray of light enters from the top of the model. If the coordinates of its intersection point with the bounding box of a high-level crop are (1, 2, 3) to (1, 2, 6), then the geometric intercept length of the transmission path is 3 meters.

[0063] After obtaining the geometric intercept length, the leaf tilt angle distribution characteristics are further extracted from the canopy morphology parameters of tall crops. Leaf tilt angle describes the angle between a single leaf and the horizontal plane, and the tilt angle distribution characterizes the probability density of leaf arrangement in different directions within the crop canopy. This information can be obtained through measured data or crop growth models, and is usually described in the form of a statistical distribution, such as leaf tilt angle following a Beta distribution or a normal distribution. By weighted averaging of all leaf tilt angle distributions, a single average leaf tilt angle value is obtained. This value simplifies the subsequent calculation of the influence of leaf direction on illumination along the light transmission path, representing the overall average light interception direction performance of the canopy.

[0064] Next, based on the geometric projection relationship between the instantaneous incident vector and the aforementioned average blade tilt angle at each time step, the instantaneous projection weighting coefficient is calculated. This coefficient is essentially the cosine of the angle between the incident light and the blade surface, reflecting the proportion of the effective projected area per unit leaf area under a given incident direction. Its calculation principle can be derived from the vector projection formula; if the angle between the light direction and the blade normal is large, more light energy can be intercepted, and the corresponding projection weighting coefficient is also large. This coefficient is used to weight and correct the geometric intercept length, ensuring that the path length considers not only spatial distance but also the degree of physical density obstruction of light as it passes through the blade.

[0065] After projection correction, the geometric intercept length is multiplied by the corresponding projection weighting coefficient to obtain the effective optical path length. The effective optical path length quantifies the spatial shading effect encountered by light rays passing through canopy leaf tissue at a specific time point and incident direction, actually reflecting the physical intensity of light being blocked by leaves in that direction. This parameter is a core intermediate variable in the propagation of light radiation in the canopy; a larger value indicates a higher leaf area density traversed per unit path, weaker light penetration, and consequently, reduced canopy transmittance. The effective optical path length directly serves as an input variable for subsequent calculations of transmittance probability and light energy distribution, determining whether the light intensity received by lower-lying crops is sufficient. For example, at 10 AM, the solar incidence angle is high. If the average leaf tilt angle of higher-lying crops tends to be horizontal, the corresponding projection weighting coefficient is larger, resulting in a significant increase in the effective optical path length after multiplication, leading to a decrease in light flux density in the middle layer.

[0066] Subsequently, based on the effective optical path length and leaf volume density in the canopy morphology parameters, and combined with a preset light attenuation physical model, the light transmittance probability of tall crops in each light ray direction is calculated. Leaf volume density is the total leaf area per unit volume, reflecting the canopy's ability to intercept light. The light attenuation model generally adopts the Beer-Lambert law, mathematically expressed as: transmittance = exp(-k·LAD·Leff), where k is the empirical attenuation coefficient, LAD is the leaf volume density, and Leff is the effective optical path length. Through this model, the canopy porosity in each path direction can be obtained, i.e., the probability that light rays along that path can still reach the middle growth zone after passing through the canopy.

[0067] Finally, the canopy porosity results for all paths are weighted and superimposed with the radiant intensity data at the corresponding time steps to obtain the canopy light capture potential index for the middle growing zones where high-rise and low-rise crops are located. The radiant intensity data provides the light energy weight for each path at that time point, ensuring that the weighted result takes into account both spatial structure and temporal dynamics. This index is ultimately used to measure the comprehensive light resource intensity available to low-rise crops at multiple time scales. For example, in a certain region, if the canopy porosity of a path is 0.4 and the corresponding radiant intensity is 500 W / m², then the light energy contributed by that path to low-rise crops is 200 W / m². The complete light capture potential is obtained by weighted summation of all paths. This index provides a quantitative basis for subsequent optimization of planting layout, ensuring a more efficient vertical allocation of light resources between high-rise and low-rise crops.

[0068] S205. Calculate the root overlap volume based on the crop spatial distribution model to determine the interspecific interaction area within the soil root zone.

[0069] In multi-crop co-cultivation systems, high-plant and low-plant crops not only compete for light resources above ground but also overlap and compete for limited soil nutrient resources below ground. Therefore, it is necessary to accurately characterize the spatial interactions of different crop root systems in a spatial model. Root overlap volume, as an important spatial parameter for measuring the interspecific root competition potential, reflects the spatial encroachment of crop roots in both vertical and horizontal dimensions and is the basis for calculating the degree of rhizosphere resource sharing.

[0070] In practice, a three-dimensional root volume model must first be constructed using root morphology parameters mapped to the soil root zone in the crop spatial distribution model. Root morphology parameters include taproot length, lateral root divergence angle, root vertical depth, and maximum horizontal extension radius, which define the natural extension shape of the crop root system in three-dimensional space. During modeling, the root system of each crop is expressed as an analytical geometry with a certain volumetric structure, such as an ellipsoid, cone, or a voxel ensemble model based on empirical fitting, to facilitate subsequent volume calculations based on spatial intersection.

[0071] After completing the geometric modeling of the root systems of all top- and bottom-crop crops, a three-dimensional spatial Boolean operation method is used to determine whether there is an intersection between the root system geometries of each crop. For crop groups with spatial overlap, the spatial intersection volume is further calculated, which is the root overlap volume. This calculation can be implemented using a spatial discretization method based on octree voxel partitioning. By dividing the soil root zone into a high-resolution voxel grid, each voxel records the probability or density of being occupied by one or more crop roots. When two or more crop roots overlap in the same voxel unit, they are marked as interspecific interaction voxels, and their volume contributions are accumulated to finally obtain the root overlap volume value between each pair of crops.

[0072] After determining the root overlap volume, the regions with strong root spatial interactions are further identified by combining crop species, root distribution characteristics, and soil nutrient content in the overlapping areas. These regions are defined as interspecific interaction regions. This region is a key input for subsequent assessment of root nutrient competition intensity and can be used to quantify the interference relationships of different crop roots on the absorption of the same nutrient resource within a specific region.

[0073] For example, within a planting unit, the topsoil crop is corn, and the bottomsoil crop is soybean. Corn roots are distributed vertically in the soil, while soybean roots are distributed shallowly and broadly. After constructing the root system model, if there is an overlapping area between the horizontal extensions of the two crops within a depth range of 0.2 meters to 0.5 meters, and the root overlap volume is found to be 0.03 cubic meters through voxel statistics, then this area is marked as an interspecific interaction area. This area can be used to calculate the nutrient competition weight within this area, and then input into the resource coupling evaluation function to participate in the overall planting layout optimization analysis.

[0074] Through the above implementation methods, it is possible to achieve precise modeling of the competition relationship of crop rhizosphere spatial resources, providing data support for the synergistic optimization of aboveground light resources and underground nutrient resources, thereby improving the resource utilization efficiency and yield stability of the intercropping system.

[0075] S206. Determine the root nutrient competition index based on the interspecific interaction region.

[0076] In step S206, to scientifically assess the intensity of resource competition between high-lying and low-lying crops within the underground root space, it is necessary to further quantify the supply and demand imbalance of nutrient resources based on the identified interspecific interaction areas, thereby calculating a root nutrient competition index. This index reflects the degree of competition among different crop roots for limited available nutrients within a shared soil area and is an important basis for evaluating the rationality of crop allocation. Specifically, the following steps may not be included: The ratio of the preset theoretical nutrient requirement of the interspecific interaction area to the available nutrient content in the soil nutrient spatial distribution data is calculated to obtain the nutrient supply-demand ratio. A nutrient stress weighting coefficient is constructed based on the nutrient supply-demand ratio, wherein when the theoretical nutrient demand is greater than the available soil nutrient content, the nutrient stress weighting coefficient is greater than one. The root nutrient competition index is obtained by weighting the root overlap volume based on the nutrient stress weighting coefficient.

[0077] In the specific implementation process, the first step is to calculate the preset theoretical nutrient requirements within the determined interspecific interaction area. The theoretical nutrient requirement refers to the total nutrient absorption demand predicted by crop growth models or agricultural experience data within this area, based on the spatial range shared by the roots of both tall and short-tree crops. This value is typically calculated based on parameters such as the crop's growth stage, average nutrient requirement per unit root volume, and root hair density. For example, for a corn-soybean co-cultivation system, the total requirement can be calculated based on empirical data showing that corn requires 150g of nitrogen per cubic meter of root system during the jointing stage and soybean requires 90g of phosphorus per cubic meter during the pod-setting stage, combined with the overlapping root volume. Simultaneously, the available soil nutrient content corresponding to this interspecific interaction area is extracted from soil nutrient spatial distribution data. This data, derived from soil sensor arrays or soil sampling and testing results, reflects the concentration of nutrients that can be directly absorbed by plant roots within this area. The ratio of the theoretical nutrient requirement to the available nutrient content in the soil is used to calculate the nutrient supply-demand ratio. This ratio is used to measure the degree of scarcity of local nutrient resources and is a basic indicator for judging the interspecific rhizosphere competitive pressure.

[0078] Based on the nutrient supply-demand ratio, a nutrient stress weighting coefficient is further constructed. This coefficient is a weighting parameter used to adjust the intensity of root spatial conflict. Its physical meaning is: when nutrient supply is less than demand (i.e., the supply-demand ratio is greater than 1), the system is under stress, and the root competition penalty weight in that area should be increased; therefore, the weighting coefficient is set to a value greater than 1. Conversely, when supply is sufficient (i.e., the supply-demand ratio is less than or equal to 1), the system is in a surplus state, and the weighting coefficient is set to 1 or slightly less than 1 to weaken the competition weight in that area. The specific calculation formula can use linear or nonlinear function mapping. For example, let the weighting coefficient α = 1 + β(supply-demand ratio - 1), where β is an empirical coefficient of regulation sensitivity, typically ranging from 0.5 to 2. Through this weighting mechanism, the planting model imposes additional penalties on competitive behavior in resource-scarce areas, thereby guiding the layout optimization algorithm to avoid high-intensity competition areas and improving overall resource utilization efficiency.

[0079] By combining the aforementioned weighting coefficients, the root overlap volume is weighted to obtain a root nutrient competition index, which serves as a quantitative parameter reflecting the degree of resource competition among roots in a specific spatial interaction area. This index considers not only the spatial overlap of roots (i.e., geometric overlap volume) but also the resource supply and demand tension within that space, giving it greater physiological realism and optimization guidance capabilities. During model optimization, this index is input into the resource coupling evaluation function, forming the two core components of the objective function together with the canopy light interception potential index. For example, in a certain interaction area, the overlap volume between maize and soybean roots is 0.04 cubic meters, the effective nitrogen concentration in the area is 120g, while the theoretical demand is 180g, resulting in a supply-demand ratio of 1.5. Therefore, the nutrient stress weighting coefficient is set to 1.25, and the final root nutrient competition index is 0.04 × 1.25 = 0.05 cubic meter equivalent. This value will prompt the algorithm to try adjusting the planting density or row spacing configuration in subsequent optimizations, alleviate the conflict of underground resources in the area, and improve the overall system stability and yield potential.

[0080] S104. Construct a resource coupling evaluation function based on the canopy light interception potential index and the root nutrient competition index.

[0081] In step S104, to achieve a comprehensive benefit assessment of the crop planting layout scheme, it is necessary to uniformly quantify the utilization efficiency of aboveground canopy light resources and the nutrient competition relationship in the underground root system, and construct a resource coupling evaluation function to measure the overall merits of system resource utilization under different planting parameter configurations. This function must not only reflect the changes in light ecological benefits caused by the shading effect of higher-lying crops on lower-lying crops, but also consider the nutrient competition effect caused by the spatial overlap of roots in the soil. Therefore, it is necessary to integrate two key parameters: the canopy light interception potential index and the root nutrient competition index. To ensure the comparability of the two types of indicators in the function, the root nutrient competition index needs to be normalized, and light response weight coefficients and nutrient response weight coefficients are introduced according to crop type to characterize the crop's sensitivity and dependence on different resources. By constructing light ecological benefit terms and nutrient competition penalty terms separately, and integrating them into a resource coupling evaluation function, a basis for the objective function can be provided for subsequent iterative optimization. Specifically, this may include the following steps: Obtain the light response weighting coefficient of the crop to be planted to light resources and the nutrient response weighting coefficient to nutrient resources; The total root volume of the soil root zone is obtained, and the ratio of the root nutrient competition index to the total root volume is determined as the normalized nutrient competition index, which is used to eliminate dimensional differences. The product of the light response weighting coefficient and the canopy light interception potential index is determined as the light ecological benefit item; The product of the nutrient response weighting coefficient and the normalized nutrient competition index is determined as the nutrient competition penalty term; The resource coupling evaluation function is constructed based on the light ecological benefit term and the nutrient competition penalty term.

[0082] In constructing the resource coupling evaluation function, the first step is to obtain the response weight coefficients of the crop to light and nutrient resources. These two coefficients reflect the crop's sensitivity to and dependence on light and nutrients during its growth process, respectively. The light response weight coefficient is typically derived from studies of crop photosynthetic characteristics, such as the response curves of photosynthetic rates under different light intensities, which can be obtained through field trials or fitting literature data. The nutrient response weight coefficient, on the other hand, is based on the yield variation patterns of crops under different nutrient supply levels, reflecting its sensitivity to nutrient stress. The introduction of these weight coefficients aims to enable the evaluation function to adapt to the physiological characteristics of different crop species, thereby achieving a more universal and accurate resource allocation assessment.

[0083] After obtaining the response weight coefficients, the root nutrient competition index needs to be normalized to eliminate the dimensional differences between it and the canopy light interception potential index. Specifically, the previously calculated root nutrient competition index is divided by the total root volume in the soil root zone to obtain a dimensionless normalized nutrient competition index. This index reflects the competition intensity per unit root volume, thus making it comparable to the light interception index in the evaluation function. This step is crucial for constructing a unified evaluation model, avoiding weight imbalances caused by different physical quantities in the function.

[0084] Based on the above standardization process, the following steps construct a light-based ecological benefit term and a nutrient competition penalty term. The light-based ecological benefit term is obtained by multiplying the canopy light interception potential index by a light response weighting coefficient, representing the potential yield gain of crops due to light resource acquisition under the current planting layout. The nutrient competition penalty term, on the other hand, is obtained by multiplying the normalized nutrient competition index by a nutrient response weighting coefficient, representing the negative impact on crop growth caused by underground resource competition due to root overlap. In this way, positive ecological benefits and negative competition losses are unified into a comprehensive indicator system.

[0085] Ultimately, the resource coupling evaluation function is constructed by subtracting the nutrient competition penalty term from the light ecological benefit term, forming a numerical expression that can be used to optimize the objective function. A higher value of this function indicates a more rational resource allocation under the current planting layout, where crops can fully utilize light while effectively avoiding competition for underground nutrients, thus guiding the layout optimization algorithm to approach the optimal solution in the search space. For example, in a certain iteration, in the maize-soybean intercropping system, the canopy light interception potential index of the upper crops is 0.82, the light response weighting coefficient is 1.2, and the light benefit term is 0.984; the root nutrient competition index is 0.06, the total root volume is 0.4, the normalized competition index is 0.15, and the nutrient response weighting coefficient is 1.5, resulting in a competition penalty term of 0.225. The final resource coupling evaluation function value is 0.984 − 0.225 = 0.759, which serves as the performance index input to the optimization algorithm under the current layout. In subsequent iterations, the algorithm will continuously adjust the planting parameters to improve this function value until it approaches the optimal configuration.

[0086] S105. Based on the preset optimization objective and preset optimization algorithm, adjust the initial planting parameters in the crop spatial distribution model and update the crop spatial distribution model. Based on the updated crop spatial distribution model, iteratively calculate the function value of the resource coupling evaluation function to perform iterative optimization.

[0087] In step S105, to achieve the optimal configuration of crop planting layout, it is necessary to systematically optimize and adjust the existing initial planting parameters based on the constructed crop spatial distribution model. This process aims to maximize the value of the resource coupling evaluation function and improve light utilization efficiency and nutrient allocation coordination by continuously modifying the planting position relationships of crops in planar space. To this end, the system will adjust the initial planting parameters by perturbation according to preset optimization objectives (such as maximizing crop synergistic yield or resource utilization efficiency) and preset optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.), and update the crop spatial distribution model structure accordingly. After each model update, the resource coupling evaluation function value needs to be recalculated, and the trend of function changes during the optimization process is iteratively compared to gradually approach the optimal solution. Specifically, this may include the following steps: Based on the row spacing and plant spacing constraints in the initial planting parameters, a parameter feasible region for the crop to be planted in the farmland plane is constructed. The parameter feasible region is used to limit the physical adjustment boundary of the planting layout. Based on the preset optimization algorithm and the preset optimization objective, a parameter perturbation vector is generated within the parameter feasible region. The parameter perturbation vector includes the row spacing adjustment step size and the plant spacing adjustment step size. The parameter perturbation vector is superimposed on the initial planting parameters in the crop spatial distribution model to obtain candidate planting parameters, and it is verified whether the candidate planting parameters are located within the parameter feasible region. If the verification is successful, the updated planar coordinate positions of the high-position crop and the low-position crop are regenerated based on the candidate planting parameters; Based on the updated planar coordinate position, the canopy morphology parameters and root morphology parameters of the high-lying crops and the low-lying crops are remapped to the vertical space corresponding to the crop spatial distribution model, so as to update the crop spatial distribution model.

[0088] To continuously improve the objective function value, the spatial layout of crops needs to be adjusted with controllable perturbations. The first step in this process is to construct the parameter feasible region. The "parameter feasible region" refers to the range of legal combinations of row spacing and plant spacing within the farmland plane, provided that agricultural machinery operation specifications and crop growth do not interfere with each other. Row spacing constraints are typically determined based on the canopy spread, ventilation and light requirements of the crop variety, and the width of agricultural machinery operations. For example, the minimum row spacing for corn must not be less than 60cm, while for soybeans it can be as small as 30cm. Plant spacing constraints are set based on the individual plant growth space requirements and the target planting density. By setting these boundary conditions, unrealistic parameter perturbations during the optimization process can be avoided, ensuring that all generated planting schemes are agronomically feasible and mechanically executable. In practice, the system reads the maximum and minimum row spacing and plant spacing values ​​from the crop configuration file and establishes a two-dimensional parameter space within the farmland geometric boundary for parameter sampling and feasibility verification in subsequent optimization.

[0089] Based on a clearly defined feasible region for the parameters, a pre-defined optimization algorithm and optimization objective are introduced to generate parameter perturbations. The pre-defined optimization algorithm can be an intelligent algorithm such as genetic algorithm, particle swarm optimization (PSO), or simulated annealing. These algorithms possess global search capabilities and are suitable for handling high-dimensional, multi-objective, and nonlinear optimization problems such as planting layout. The pre-defined optimization objective is typically set to maximize the resource coupling evaluation function value, i.e., seeking the optimal balance between light ecological benefits and nutrient competition penalties. To control the scale and direction of the perturbation, the system generates a parameter perturbation vector for each perturbation. This vector contains two components: row spacing adjustment step size and plant spacing adjustment step size, in meters or centimeters. The step size is adaptively adjusted according to the iteration progress of the optimization algorithm, initially larger to expand the search range and gradually decreasing later for refined convergence. The generation of the perturbation vector is based on the offset trend between the current planting parameters and historical optimal solutions, combined with a certain random factor to enhance the ability to escape local optima, thereby ensuring the diversity and stability of the search.

[0090] After obtaining the parameter perturbation vector, it is superimposed on the initial planting parameters in the current crop spatial distribution model to form candidate planting parameters. These candidate planting parameters represent the new set of row spacing and plant spacing configurations to be verified in the current iteration. It is then necessary to verify whether these parameters remain within the previously constructed parameter feasible region. The verification process involves checking each row spacing and plant spacing against upper and lower limits, and examining whether new planting points overlap or exceed field boundaries within the planar region. If any constraints are not met, the set of parameters is discarded, and the algorithm returns to regenerate the perturbation vector; if the verification passes, the next stage, parameter mapping, begins. This verification mechanism ensures that the perturbation process remains within agronomic boundaries, avoiding invalid computations and improving optimization efficiency.

[0091] The validated candidate parameters are used to regenerate the planting coordinates of tall and short crops on the farmland plane. The core of this step lies in rearranging the crop points according to a preset planting sequence strategy (such as equidistant, staggered, or striped configuration) using updated row and plant spacing values. In practice, the system starts from a reference point (e.g., the upper left corner of the field), sequentially generating planting points within the same row according to the updated plant spacing, and then generating the starting point of the next row based on the updated row spacing, forming a new two-dimensional coordinate matrix. This matrix fully reflects the crop distribution under the current candidate parameters and will be used for subsequent three-dimensional mapping and evaluation function calculations.

[0092] Based on the updated planar coordinates, the system needs to remap the canopy morphology parameters and root morphology parameters of both high-rise and low-rise crops to the vertical spatial regions defined by the crop spatial distribution model. The mapping process follows the principle of spatial structure partitioning, projecting the canopy bounding boxes of each crop onto the top photosynthetic zone and the middle growth zone according to their plant height and structural characteristics, respectively, and distributing the root morphology model to the soil root zone. The canopy bounding boxes are typically described using cuboid or ellipsoidal models, constructed based on parameters such as canopy height, canopy width, and leaf area density extracted from the database for each crop variety; the root model is represented by a root length density function or a three-dimensional root grid. By spatially mapping the two-dimensional coordinates to the three-dimensional structural parameters, the complete crop spatial distribution model update is achieved, providing accurate input for the next round of resource coupling evaluation function calculation.

[0093] For example, in one iteration, the initial row spacing for corn was 70cm. After the perturbation vector was generated, the row spacing was adjusted to 75cm. The system verified that this row spacing was within the feasible range of 60–80cm and that the new coordinates did not overlap. Then, the planting points for corn and soybeans were regenerated. Subsequently, the corn canopy height of 2.2m was mapped to the top and middle layers, the soybean canopy height of 0.8m was mapped to the middle layer, and root parameters were mapped to the soil layer. This updated model was used to calculate the resource coupling evaluation function. The calculation results were used to determine whether the current perturbation was better than the previous one, providing a basis for optimization iteration. Through continuous iteration of this process, the optimal planting parameter configuration was finally achieved.

[0094] After updating the crop spatial distribution model, to achieve the core objective of the layout optimization-based farmland planting method—improving the overall resource utilization efficiency and yield potential of the crop system—it is necessary to iteratively calculate the resource coupling evaluation function of the updated spatial distribution model. The key to this step is transforming the new planting layout into quantifiable performance indicators, so that the optimization algorithm can determine whether the current layout is superior to the historical layout and adjust the parameter perturbation strategy accordingly for the next round.

[0095] In practice, the canopy light interception potential index is first recalculated based on the updated positional relationship between tall and short crops in three-dimensional space. The system calls upon solar trajectory data, discretizes daily sunshine hours within a preset growth period, and generates multiple instantaneous incident vectors. For each incident vector, the path of light traversing the top photosynthetic zone and the middle growth zone is constructed, and the effective optical path length in the canopy is calculated by combining the geometric boundaries and leaf tilt angle distribution of the tall crop canopy. Furthermore, combining the projection relationship between the crop's leaf volumetric density, average leaf tilt angle, and incident light direction, a light attenuation model (such as Beer-Lambert's law) is used to estimate the light transmission probability along each path direction, i.e., canopy porosity. After weighting and summing the canopy porosity at all time points using radiant intensity, a new canopy light interception potential index is obtained, reflecting the light-receiving capacity of the short crops under different light conditions in the current layout.

[0096] Next, the spatial overlap of underground root systems is reassessed to obtain updated root nutrient competition indices. Using root morphology parameters mapped to the soil root zone, overlapping areas of different crop root systems are identified in a three-dimensional voxel model, forming interspecific interaction zones. Within these zones, the system calculates theoretical nutrient requirements and compares them with the ratio of available nutrient content in the soil nutrient spatial distribution data to obtain the nutrient supply-demand ratio. If nutrient demand exceeds supply, the system automatically adjusts the nutrient stress weighting coefficient to be greater than 1, thereby increasing the intensity of competition penalty in that zone. Finally, the root overlap volume is multiplied by the weighting coefficient to obtain a new root nutrient competition index.

[0097] After obtaining the canopy light interception potential index and the root nutrient competition index, the system introduces the light response weighting coefficient and nutrient response weighting coefficient of the crop to be planted. These two weighting parameters are preset based on the crop's physiological characteristics (such as photosynthetic rate curve and nutrient sensitivity) from pre-experimental data or literature. By multiplying the light response weighting coefficient by the light interception potential index, the light ecological benefit term is obtained; by multiplying the nutrient response weighting coefficient by the normalized value of the root nutrient competition index (i.e., divided by the total root volume), the nutrient competition penalty term is obtained. Subtracting the two gives the function value of the resource coupling evaluation function under the current iteration.

[0098] This function value serves as the objective function output of the optimization algorithm and is compared with historical best values. If the current function value is higher, it indicates that the new spatial layout is better in terms of resource synergy. The system will record this parameter configuration as the current optimal solution and use it as the basis for generating a new perturbation vector in the next iteration. If the function value deteriorates or does not improve significantly, the algorithm may adjust the step size or switch the search direction to avoid getting trapped in local optima.

[0099] For example, in a certain iteration, the updated crop spatial distribution model calculates the following: the canopy light interception potential index for low-lying crops is 0.78, the light response weighting coefficient is 1.1, and the light ecological benefit term is 0.858; the root overlap volume is 0.05 m³, the total root volume is 0.35 m³, the normalized value is 0.143, the nutrient response weighting coefficient is 1.4, and the nutrient competition penalty term is 0.200. Therefore, the resource coupling evaluation function value is 0.858 − 0.200 = 0.658. The system compares this value with the function value from the previous iteration to determine whether the current layout is a better solution.

[0100] S106. When the preset termination iteration requirement is met, the iteration stops. Based on the target planting parameters in the target crop spatial distribution model corresponding to the maximum function value of the resource coupling evaluation function, a planting control instruction is generated. The planting control instruction is used to drive agricultural planting machinery to perform planting operations.

[0101] Under the premise of meeting the preset termination iteration requirements, the spatial distribution model of the target crop corresponding to the maximum function value of the resource coupling evaluation function is extracted, and the target planting parameters are extracted from it to generate planting control instructions to drive agricultural planting machinery to accurately execute planting operations. The core significance of this step is to concretize the abstract optimization calculation results into operation instructions that agricultural machinery can recognize, realizing closed-loop control from digital model to actual field operation.

[0102] During implementation, the first step is to determine whether the current optimization iteration has reached the termination condition. Preset termination requirements typically include two types of conditions: first, function convergence, meaning the change in the resource coupling evaluation function value is below a set threshold over several consecutive iterations; second, iteration count limit, meaning the total number of iterations reaches a set upper limit. After each iteration, the system automatically checks whether the current function value has stabilized or whether the maximum allowed number of iterations has been reached. If either condition is met, a termination flag is triggered, stopping subsequent perturbations and model updates.

[0103] After termination, the system calls the crop spatial distribution model corresponding to the round with the largest resource coupling evaluation function value in the iteration history and extracts the target planting parameters. These target planting parameters specifically include row spacing, plant spacing, planar coordinate positions of high-rise and low-rise crops, as well as associated canopy and root system spatial mapping information. These parameters collectively define the precise planting location and structural configuration of crops in the field. During extraction, the system aligns the planar coordinate position information with the agricultural geographic information system (GIS) to ensure that the coordinate positioning completely matches the actual field boundaries, avoiding mechanical operation deviations due to coordinate discrepancies.

[0104] Planting control instructions are generated based on target planting parameters. These instructions are a set of operational commands that can be recognized and executed by agricultural machinery, typically including precise planting paths, planting point coordinates, crop type identification, sowing depth, and sowing rhythm. To achieve high-precision machinery control, the extracted target planting parameters need to be converted into a standardized agricultural machinery interface language (such as the ISOBUS instruction set) and, combined with a GPS navigation module, generated control frames containing timestamps, location codes, and action types. These control instructions are then sent to the field seeder or unmanned agricultural machinery via an agricultural IoT control terminal, ensuring that the machinery strictly follows the optimized results to complete the planting task during operation, thereby achieving consistency between planting layout and resource optimization.

[0105] For example, after multiple rounds of iterative optimization, the system finally determined the target planting parameters as follows: corn row spacing of 75cm and plant spacing of 28cm, soybean row spacing of 40cm and plant spacing of 20cm, with the corresponding resource coupling evaluation function value reaching the global maximum of 0.712. The system gridded the planting point coordinates of corn and soybeans within the field and generated path control instructions, including GPS coordinates, crop type, operating speed, and sowing density per unit area. After receiving the instructions, the agricultural machinery proceeded along the path and sowed at the designated location, ensuring that the optimization results were implemented one-to-one in the field. In this way, not only was the theoretically optimal planting layout implemented, but the level of intelligence and precision in agricultural operations was also improved.

[0106] Please see Figure 3 This is a schematic diagram of a farmland planting system based on layout optimization in an embodiment of this application.

[0107] It should be noted that, Figure 3 The structure of a farmland planting system based on layout optimization shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0108] like Figure 3 As shown, a layout-optimized farmland planting system includes a central processing unit 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage section 308 into a random access memory 303, such as executing the methods described in the above embodiments. The random access memory 303 also stores various programs and data required for system operation. The central processing unit 301, the read-only memory 302, and the random access memory 303 are interconnected via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0109] The following components are connected to the input / output interface 305: an input section 306 including audio input devices, push-button switches, etc.; an output section 307 including an LCD display, audio output devices, indicator lights, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 310 as needed so that computer programs read from it can be installed into the storage section 308 as needed.

[0110] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit 301, it performs the various functions defined in the present invention.

[0111] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, flash memory, optical fiber, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0113] Specifically, a layout-optimized farmland planting system according to this embodiment includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the layout-optimized farmland planting method provided in the above embodiment.

[0114] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the layout-optimized farmland planting system described in the above embodiments; or it may exist independently and not assembled into the layout-optimized farmland planting system. The storage medium carries one or more computer programs, which, when executed by a processor of the layout-optimized farmland planting system, cause the layout-optimized farmland planting system to implement the layout-optimized farmland planting method provided in the above embodiments.

Claims

1. A farmland planting method based on layout optimization, characterized in that, The method includes: Acquire basic environmental data of the target farmland and canopy morphology parameters, root morphology parameters and initial planting parameters of the crops to be planted. The basic environmental data includes spatial distribution data of soil nutrients and solar radiation meteorological data of the area. The crops to be planted include highland crops and lowland crops. Based on the environmental baseline data, the canopy morphology parameters, the root morphology parameters, and the initial planting parameters, a crop spatial distribution model is constructed. The crop spatial distribution model is used to characterize the three-dimensional spatial distribution of the target farmland. Based on the crop spatial distribution model, the canopy light interception potential index and root nutrient competition index between the high-lying crop and the low-lying crop were calculated respectively. A resource coupling evaluation function is constructed based on the canopy light interception potential index and the root nutrient competition index. Based on the preset optimization objective and preset optimization algorithm, the initial planting parameters in the crop spatial distribution model are adjusted and the crop spatial distribution model is updated. Based on the updated crop spatial distribution model, the function value of the resource coupling evaluation function is iteratively calculated to perform iterative optimization. When the preset termination iteration requirement is met, the iteration stops. Based on the target planting parameters in the target crop spatial distribution model corresponding to the maximum function value of the resource coupling evaluation function, a planting control command is generated. The planting control command is used to drive agricultural planting machinery to perform planting operations.

2. The method according to claim 1, characterized in that, The construction of the crop spatial distribution model based on the environmental baseline data, the canopy morphology parameters, the root morphology parameters, and the initial planting parameters specifically includes: Analyze the vertical distribution characteristics of the environmental basic data, and based on the vertical distribution characteristics, divide the vertical space of the target farmland within the preset spatial area into the top photosynthetic zone, the middle growth zone, and the soil root zone; The planar coordinates of the high-lying crop and the low-lying crop in the target farmland are determined based on the initial planting parameters. Based on the canopy morphology parameters, a first three-dimensional canopy bounding box for the high-lying crop and a second three-dimensional canopy bounding box for the low-lying crop are constructed. Based on the planar coordinate position and preset mapping rules, the first canopy bounding box is mapped to the top photosynthetic zone and the middle growth zone, the second canopy bounding box of the low-lying crop is mapped to the middle growth zone, and the root morphology parameters are mapped to the soil root zone to obtain the crop spatial distribution model.

3. The method according to claim 2, characterized in that, The calculation of canopy light interception potential and root nutrient competition indices between the high-lying and low-lying crops based on the crop spatial distribution model specifically includes: Acquire the solar trajectory data of the target farmland within a preset growth cycle and the corresponding radiation intensity data of the solar trajectory data; The solar trajectory data is discretized to obtain instantaneous incident vectors with multiple time steps; Based on the crop spatial distribution model and multiple instantaneous incident vectors, the transmission paths of light passing through the top photosynthetic zone and the middle growth zone at different times are constructed respectively; The effective optical path length and canopy porosity of each transmission path through the high-level crop canopy are calculated respectively, and the canopy light interception potential index is determined in combination with the radiation intensity data; Calculate the root overlap volume based on the crop spatial distribution model to determine the interspecific interaction area within the soil root zone; The root nutrient competition index is determined based on the interspecific interaction region.

4. The method according to claim 3, characterized in that, The calculation of the effective optical path length and canopy porosity of each transmission path through the upper crop canopy, and the determination of the canopy light interception potential index in conjunction with the radiation intensity data, specifically includes: Based on the crop spatial distribution model, the canopy geometric boundary of the high-lying crop is determined, and the geometric intercept length of each transmission path within the canopy geometric boundary is calculated. The leaf tilt angle distribution characteristics of the tall crops are extracted from the canopy morphology parameters, and the average leaf tilt angle, which characterizes the average light-blocking capacity of the canopy, is determined based on the leaf tilt angle distribution characteristics. Based on the geometric projection relationship between the instantaneous incident vector and the average leaf tilt angle at each time step, the instantaneous projection weight coefficient is calculated. The instantaneous projection weight coefficient is used to characterize the projection ratio of a unit leaf area in the direction of light incidence. The effective optical path length is obtained by weighting the geometric intercept length based on the instantaneous projection weight coefficient. The effective optical path length characterizes the physical blocking strength of light rays passing through the leaf tissue in the direction of the instantaneous incident vector. Based on the effective optical path length and the leaf volume density in the canopy morphology parameters, the light transmittance probability of the tall crop in each of the transmission path directions is calculated using a preset light attenuation physical model to obtain the canopy porosity. Using the radiation intensity data as weights, the canopy porosity of each transmission path is weighted and summed to obtain the canopy light interception potential index.

5. The method according to claim 3, characterized in that, The determination of the root nutrient competition index based on the interspecific interaction region specifically includes: The ratio of the preset theoretical nutrient requirement of the interspecific interaction area to the available nutrient content in the soil nutrient spatial distribution data is calculated to obtain the nutrient supply-demand ratio. A nutrient stress weighting coefficient is constructed based on the nutrient supply-demand ratio, wherein when the theoretical nutrient demand is greater than the available soil nutrient content, the nutrient stress weighting coefficient is greater than one. The root nutrient competition index is obtained by weighting the root overlap volume based on the nutrient stress weighting coefficient.

6. The method according to claim 1, characterized in that, The construction of the resource coupling evaluation function based on the canopy light interception potential index and the root nutrient competition index specifically includes: Obtain the light response weighting coefficient of the crop to be planted to light resources and the nutrient response weighting coefficient to nutrient resources; The total root volume of the soil root zone is obtained, and the ratio of the root nutrient competition index to the total root volume is determined as the normalized nutrient competition index, which is used to eliminate dimensional differences. The product of the light response weighting coefficient and the canopy light interception potential index is determined as the light ecological benefit item; The product of the nutrient response weighting coefficient and the normalized nutrient competition index is determined as the nutrient competition penalty term; The resource coupling evaluation function is constructed based on the light ecological benefit term and the nutrient competition penalty term.

7. The method according to claim 1, characterized in that, The step of adjusting the initial planting parameters in the crop spatial distribution model and updating the crop spatial distribution model based on a preset optimization objective and a preset optimization algorithm specifically includes: Based on the row spacing and plant spacing constraints in the initial planting parameters, a parameter feasible region for the crop to be planted in the farmland plane is constructed. The parameter feasible region is used to limit the physical adjustment boundary of the planting layout. Based on the preset optimization algorithm and the preset optimization objective, a parameter perturbation vector is generated within the parameter feasible region. The parameter perturbation vector includes the row spacing adjustment step size and the plant spacing adjustment step size. The parameter perturbation vector is superimposed on the initial planting parameters in the crop spatial distribution model to obtain candidate planting parameters, and it is verified whether the candidate planting parameters are located within the parameter feasible region. If the verification is successful, the updated planar coordinate positions of the high-position crop and the low-position crop are regenerated based on the candidate planting parameters; Based on the updated planar coordinate position, the canopy morphology parameters and root morphology parameters of the high-lying crops and the low-lying crops are remapped to the vertical space corresponding to the crop spatial distribution model, so as to update the crop spatial distribution model.

8. A farmland planting system based on layout optimization, characterized in that, The layout-optimized farmland planting system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the layout-optimized farmland planting system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on a layout-optimized farmland planting system, the layout-optimized farmland planting system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on a layout-optimized farmland planting system, the layout-optimized farmland planting system performs the method as described in any one of claims 1-7.

Images