Method for optimizing crop planting layout

Abstract

The application discloses a kind of crop planting layout optimization methods.The optimization method includes: obtaining flood simulation data, farmland inundation data, future climate scenario data and crop-related parameters;Determine the key indicators of crop planting layout optimization, the key indicators include crop planting area and crop type spatial allocation;The constraint condition of crop planting layout is constructed, wherein the constraint condition includes constructing crop climate suitability constraint, constructing resource and safety constraint, and constructing space and flood risk constraint;Flood simulation data, farmland inundation data, future climate scenario data and crop-related parameters are imported into the constraint condition, and optimization parameters are generated based on the key indicators and the preset multi-objective intelligent optimization algorithm, and the optimization parameters form the crop planting layout optimization scheme.The technical scheme of the application can effectively meet the climate adaptability and risk prevention and control needs of agricultural production in flood-prone areas.

Description

Technical Field

[0001] This invention relates to the field of crop cultivation technology, and more specifically to a method for optimizing crop planting layout. Background Technology

[0002] Against the backdrop of global warming, frequent extreme precipitation events have exacerbated watershed flooding, leading to reduced crop yields and disrupted agricultural production layouts, severely threatening food security and sustainable agricultural development. Current crop planting layout planning relies heavily on empirical decisions, lacking accurate predictions of flood risks under future climate scenarios. Furthermore, existing optimization schemes often detach from the correlation between planting structure ratios and spatial implementation, failing to coordinate and balance economic, social, and ecological benefits with flood control and disaster reduction needs. This results in poor adaptability and insufficient operability of the optimization schemes, failing to meet the climate adaptability and risk prevention requirements of agricultural production in flood-prone areas. Summary of the Invention

[0003] In view of the deficiencies in the existing technology, the present invention provides an optimization method for crop planting layout that can effectively meet the needs of climate adaptability and risk prevention and control in agricultural production in flood-prone areas.

[0004] This application provides a method for optimizing crop planting layout, the optimization method comprising:

[0005] Acquire flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters, including crop flood tolerance parameters, water requirement parameters, yield parameters, ecological impact coefficients, and suitable growth parameters;

[0006] Determine the key indicators for optimizing crop planting layout, including crop planting area and spatial allocation of crop types;

[0007] The constraints for crop planting layout are constructed, including constraints on crop climate suitability, constraints on resources and security, and constraints on space and flood risk.

[0008] The flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters are imported into the constraints. Based on the key indicators and a preset multi-objective intelligent optimization algorithm, optimization parameters are generated, and a crop planting layout optimization scheme is formed according to the optimization parameters.

[0009] In one aspect, the steps for constructing crop climate suitability constraints include:

[0010] The suitable temperature range, soil compatibility parameters, and precipitation requirement thresholds for crops are obtained. The soil compatibility parameters include the pH range and organic matter content threshold.

[0011] To obtain data on temperature changes, soil properties, and precipitation distribution under future climate scenarios;

[0012] Based on the crop's suitable temperature range, soil compatibility parameters, and precipitation requirement threshold, and combined with temperature change data, soil characteristic data, and precipitation distribution data under future climate scenarios, the crop's climate suitability index in the target area is calculated according to a preset quantitative formula, wherein the quantitative formula is: S I = T c ×0.4 + S c ×0.3+R c ×0.3, where S I T represents the climate suitability index. c S represents the temperature adaptability coefficient. c R represents the soil compatibility coefficient. c Represents the precipitation adaptability coefficient;

[0013] The climate suitability index being greater than a preset suitability threshold is set as a crop climate suitability constraint. The preset suitability threshold is set based on the suitability level corresponding to the average annual yield of crops in the target area.

[0014] In one aspect, the steps for establishing resource and security constraints include:

[0015] A constraint is established that the water consumption for crop cultivation is less than or equal to the available agricultural water resources in the region. The available agricultural water resources in the region are calculated based on the county-level administrative unit, combined with the exploitable surface water and groundwater, and after deducting the water reserved for ecological environment and other departments.

[0016] A constraint is established that the proportion of grain crop planting area is greater than or equal to a preset safe proportion, wherein the preset safe proportion is set at 60% for major grain-producing areas and 40% for non-major grain-producing areas;

[0017] A constraint is established that the ecological impact index of crop planting is less than or equal to a preset ecological threshold, wherein the preset ecological threshold is set to 0.5 for food crops and 0.4 for cash crops.

[0018] In one aspect, the steps for establishing resource and security constraints also include:

[0019] Determine the parameter thresholds corresponding to resource utilization, food security, and ecological protection, wherein the parameter thresholds include a preset security ratio and a preset ecological threshold;

[0020] By combining the available agricultural water resources in the region with the water requirements of each crop, the maximum cultivable area of ​​each crop is calculated separately according to crop type.

[0021] Based on the crop planting area ratio and yield parameters, the total grain output of the region is calculated, and the lower limit of the grain crop planting area is determined by combining the preset safe proportion.

[0022] The regional ecological impact index is calculated by summing the products of crop planting area and ecological impact coefficient, thus forming ecological impact constraints.

[0023] By comparing the actual planting area of ​​each crop with the maximum arable area, the planting area of ​​grain crops with the lower limit, and the ecological impact index with the preset ecological threshold, resource and security constraints are formed.

[0024] In one aspect, the steps for constructing spatial and flood risk constraints include:

[0025] Establish a constraint that the spatial clustering degree of crop planting at a preset grid scale is greater than or equal to a preset clustering degree threshold;

[0026] Establish a constraint that the flood risk coefficient of the crop planting area is less than or equal to a preset risk threshold;

[0027] The flood risk coefficient is calculated based on a correlation formula between flood depth, inundation duration, and crop flood tolerance sensitivity.

[0028] The crop flood tolerance sensitivity is dynamically assigned based on crop type and is modified in combination with the drainage performance of arable land soil and the drainage efficiency of water conservancy facilities.

[0029] The spatial clustering degree is calculated based on the spatial location association relationship of the grid cells.

[0030] In one aspect, after the step of forming a crop planting layout optimization scheme based on the optimization parameters, the following steps are included:

[0031] The proposed planting layout optimization scheme was verified in multiple dimensions to determine whether it met all constraints. The verification indicators included a yield achievement rate of ≥90%, a flood loss reduction rate of ≥25%, and a water resource utilization rate of ≥80%.

[0032] If the conditions are not met, adjust the optimization parameters. If adjusting the optimization parameters is ineffective, re-optimize the parameter thresholds of the constraints.

[0033] If the conditions are met, then the planting layout optimization scheme is determined to be a practical application scheme.

[0034] In one aspect, the step of multi-dimensionally verifying the planting layout optimization scheme also includes:

[0035] Define an extreme climate scenario, which is based on a coupled-mode comparison plan high-emission scenario, in which the temperature rise exceeds a preset temperature and the precipitation fluctuation exceeds a preset first percentage.

[0036] An extreme flood scenario is defined as a high recurrence period flood, where the flood depth exceeds a preset second percentage.

[0037] Verify whether the proposed planting layout optimization scheme can still meet the constraints under the superposition of extreme climate and extreme flood scenarios;

[0038] If the conditions are not met under extreme circumstances, return to adjust the spatial allocation of crop planting area and crop type;

[0039] Regenerate the optimized solution and verify it again.

[0040] In one aspect, the step of generating optimization parameters based on the key indicators and a preset multi-objective intelligent optimization algorithm includes:

[0041] The optimization objectives are defined, including improving economic benefits, ensuring food security, controlling ecological impacts, and mitigating flood risks.

[0042] Differentiated weights are assigned to each of the aforementioned optimization objectives, and the weight assignment is dynamically adjusted based on the policy orientation of the target region and the priority of agricultural production.

[0043] The algorithm uses crop planting area and spatial allocation of crop types as decision variables, and embeds constraints related to crop climate suitability, resources and security, and spatial and flood risks.

[0044] Through iterative calculations using the algorithm, the crop planting area parameters and crop type spatial allocation parameters that satisfy all constraints and are optimal in synergy with the optimization objective are obtained, forming a set of optimization parameters.

[0045] In one aspect, the steps to obtain data on future climate scenarios include:

[0046] Multiple climate prediction models are selected, and the climate prediction models contain simulation data corresponding to different emission pathways;

[0047] We used the comprehensive correlation coefficient, standard deviation, and root mean square error to compare the fit between various climate prediction models and measured climate data of the target area.

[0048] Candidate patterns that meet the preset criteria are selected, and the comprehensive score of the candidate patterns is calculated to select the optimal pattern.

[0049] The climate sequence output by the optimal model is corrected by establishing a distribution mapping relationship between historical observation sequences and model sequences, and optimizing the data by combining climate change trend adjustment factors.

[0050] Extreme climate event data are extracted from the corrected sequence to form future climate scenario data for constructing constraints.

[0051] In one aspect, the optimization parameters include optimized crop planting area data and flood simulation results;

[0052] The step of forming an optimized crop planting layout scheme based on the optimized parameters also includes:

[0053] Receive the optimized crop planting area data and use the crop planting area data as the non-spatial quantity requirement input of the spatial layout model;

[0054] The flood simulation results and crop climate suitability constraints are obtained and used as spatial allocation guiding factors.

[0055] Output the initial suitability probability based on the spatial layout model;

[0056] Call the flood risk coefficient data, perform a risk correction operation on the initial suitability probability, and output the corrected suitability probability;

[0057] Input the conversion elasticity coefficient and calculate the overall allocation probability by combining it with the corrected suitability probability;

[0058] The system compares the spatial allocation area of ​​each crop with the target area in real time, and dynamically adjusts the overall allocation probability by iteratively adjusting variables until the allocated area matches the target area, and outputs the crop spatial layout optimization results.

[0059] The spatial layout optimization results are checked for consistency with the optimized crop planting area data. If the check passes, the results are integrated to form a complete crop planting layout optimization scheme. If the check fails, the suitability probability is returned for revision.

[0060] The beneficial effects of this invention are reflected in the following aspects: By integrating multi-dimensional core data on flood simulation, farmland inundation, future climate scenarios, and crops, it provides comprehensive and accurate basic support for optimizing planting layout, reducing the one-sidedness of experience-based decision-making; by clarifying the two key indicators of crop planting area and spatial allocation of crop types, it focuses on the core optimization direction, ensuring the pertinence of the solution; by constructing a triple constraint system of crop climate suitability, resources and security, and space and flood risk, it not only achieves the adaptation of crop growth and environment under future climate scenarios, but also takes into account the multiple needs of water resource utilization, food security, ecological protection, and flood risk prevention and control, reducing the limitations of single-factor optimization; by generating optimization parameters and forming layout schemes through multi-objective intelligent optimization algorithms, the schemes can not only adapt to the climate fluctuation characteristics of flood-prone areas, but also directly quantify and couple flood-causing factors through spatial and flood risk constraints, reducing the impact of disasters from the source. The resulting optimization schemes are scientific, adaptable, and operable, effectively meeting the climate adaptability and risk prevention and control needs of agricultural production in flood-prone areas. Attached Figure Description

[0061] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0062] Figure 1 This is a schematic diagram illustrating the process steps of the crop planting layout optimization method of this application;

[0063] Figure 2 This is a schematic diagram of the process steps for constructing crop climate suitability constraints in the optimization method of this application;

[0064] Figure 3 This is a schematic diagram illustrating the process steps for constructing resource and security constraints in the optimization method of this application;

[0065] Figure 4 A schematic diagram illustrating the process steps involved in constructing resource and security constraints in the optimization method of this application;

[0066] Figure 5 This is a schematic diagram illustrating the process steps for constructing spatial and flood risk constraints in the optimization method of this application;

[0067] Figure 6 This is a schematic diagram of the process steps in the optimization method of this application to form an optimized crop planting layout scheme based on optimization parameters;

[0068] Figure 7 This is a schematic diagram illustrating the process steps for multi-dimensional verification of the planting layout optimization scheme in the optimization method of this application;

[0069] Figure 8 This is a schematic diagram of the process steps for generating optimization parameters in the optimization method of this application;

[0070] Figure 9 This is a schematic diagram of the process steps for obtaining future climate scenario data in the optimized method of this application. Detailed Implementation

[0071] The embodiments of the technical solution of the present invention will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solution of the present invention and are therefore intended to limit the scope of protection of the present invention.

[0072] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application should have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0073] like Figure 1As shown, this application provides a method for optimizing crop planting layout, the optimization method including:

[0074] Step S10: Acquire flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters. Crop-related parameters include parameters on crop flood tolerance, water requirement, yield, ecological impact coefficient, and suitable growth parameters. Flood simulation data can systematically present the spatiotemporal evolution characteristics of floods within the watershed and clearly define the degree of flood threat in different areas. Farmland inundation data accurately reflects the scope, frequency, and intensity of farmland inundation, providing a basis for risk-targeted optimization. Future climate scenario data includes long-term climate evolution trends and short-term extreme climate event characteristics, used to predict the potential impact of climate fluctuations on crop growth in advance. Crop-related parameters comprehensively include key attributes of crop adaptation to the environment and growth output. Flood tolerance parameters determine the crop's ability to resist flood stress, water requirement parameters clarify the water resource requirements for crop growth, yield parameters are related to the economic benefit goals of agricultural production, ecological impact coefficients reflect the degree of crop planting's impact on the regional ecological environment, and suitable growth parameters define the minimum environmental conditions for normal crop growth.

[0075] Step S20 identifies key indicators for optimizing crop planting layout. These indicators include crop planting area and spatial allocation of crop types. Crop planting area directly relates to the resource allocation pattern of different crops within a region; a reasonable area allocation can achieve efficient use of land and water resources while balancing multiple benefits. Spatial allocation of crop types determines the suitable crop varieties for different regions. By scientifically matching crop characteristics with regional environmental conditions, the rationality and resilience of the planting layout are improved from the source. These two indicators are interconnected, clarifying both the quantitative allocation standards and defining the range of variety selection, reducing the blind spots in the optimization process, and ensuring that subsequent work always revolves around core needs.

[0076] Step S30 involves constructing constraints on crop planting layout. These constraints include those related to crop climate suitability, resource and security, and spatial and flood risk. The construction of these constraints forms a scientific framework for optimizing planting layout, defining reasonable boundaries for the plan and achieving a synergistic balance among multiple needs. Crop climate suitability constraints ensure precise adaptation of crop growth to future climate conditions, improving crop growth stability and yield reliability. Resource and security constraints focus on sustainable water resource utilization and food security, reducing excessive water consumption, strengthening the food security barrier, and controlling the negative impact of crop planting on the ecological environment. Spatial and flood risk constraints strengthen the spatial rationality and flood resilience of the layout, standardize the spatial distribution of crop planting, improve agricultural production management efficiency, and reduce flood disaster losses. These three constraints comprehensively cover key dimensions such as climate suitability, resource utilization, security assurance, and risk prevention, constructing a three-dimensional protection system to ensure that the optimized plan meets agricultural production needs while possessing risk resistance capabilities.

[0077] Step S40 involves importing flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters into the constraints. Based on key indicators and a pre-set multi-objective intelligent optimization algorithm, optimization parameters are generated, and a crop planting layout optimization plan is formed according to these parameters. The deep integration of data and constraints, along with the empowerment of intelligent algorithms, achieves efficient transformation from basic information to optimized plans. Importing these four types of core data systems into triple constraints provides precise data support for the execution of constraints, reducing the disconnect between theoretical optimization and reality. The multi-objective intelligent optimization algorithm efficiently balances multiple objectives and constraints, solving for the optimal crop planting area and type allocation plan through scientific computation, overcoming the limitations and experiential deficiencies of manual decision-making. The generation of optimization parameters and the formation of the plan construct a complete closed-loop logic. The resulting planting layout plan not only fully adapts to the climatic characteristics and flood risk patterns of flood-prone areas but also achieves a synergistic win-win situation of multiple benefits and risk prevention, effectively improving the stability of agricultural production.

[0078] Multi-objective intelligent optimization algorithms are a class of intelligent computing methods that find cooperative optimal solutions among multiple conflicting optimization objectives by simulating natural phenomena or biological behaviors. The core is to break through the limitations of single-objective optimization and achieve multi-objective cooperative optimization while satisfying multiple constraints. Specific algorithms include Non-Dominated Sorting Genetic Algorithm (NSGA-Ⅲ) and Multi-Objective Gray Wolf Optimization Algorithm (MOGWO).

[0079] In this embodiment, by integrating multi-dimensional core data on flood simulation, farmland inundation, future climate scenarios, and crops, comprehensive and precise foundational support is provided for optimizing planting layout, reducing the one-sidedness of experience-based decision-making. By clarifying two key indicators—crop planting area and spatial allocation of crop types—the core optimization direction is focused, ensuring the relevance of the solution. By constructing a triple constraint system of crop climate suitability, resources and security, and space and flood risk, the system not only achieves crop growth and environmental adaptation under future climate scenarios but also takes into account the multiple needs of water resource utilization, food security, ecological protection, and flood risk prevention, reducing the limitations of single-factor optimization. Through multi-objective intelligent optimization algorithms, optimization parameters are generated and layout schemes are formed, enabling the schemes to adapt to the climate fluctuation characteristics of flood-prone areas and directly quantify and couple flood-causing factors through spatial and flood risk constraints, reducing the impact of disasters from the source. The resulting optimization schemes are scientific, adaptable, and operable, effectively meeting the climate adaptability and risk prevention needs of agricultural production in flood-prone areas.

[0080] like Figure 2 As shown, the steps for constructing crop climate suitability constraints include:

[0081] Step S311 involves obtaining the suitable temperature range, soil compatibility parameters, and precipitation requirement thresholds for the crop. Soil compatibility parameters include the pH range and organic matter content threshold. Obtaining these key environmental compatibility parameters lays the foundation for constructing climate suitability constraints, ensuring that the constraints meet the essential needs of crop growth. The suitable temperature range clarifies the temperature boundary for normal crop growth and development, ensuring the stable progress of crop physiological processes. The pH range in the soil compatibility parameters determines the soil pH environment suitability for crop root growth, while the organic matter content threshold is related to soil fertility and nutrient supply capacity, affecting crop growth. The precipitation requirement threshold defines the total amount and distribution rhythm of precipitation required at each stage of crop growth, providing a basis for water supply adaptation. The accurate acquisition of these parameters achieves comprehensive coverage of the crop growth environment requirements, making subsequent constraint construction more targeted and scientific, ensuring from the source that climate suitability constraints align with crop growth needs.

[0082] Step S312 involves acquiring temperature change data, soil property data, and precipitation distribution data under future climate scenarios. Temperature change data reveals the temperature fluctuation trends and magnitudes in the target area at different future periods, reflecting the impact of global warming on the temperature environment for crop growth. Soil property data reflects the future physical and chemical properties of the soil, ensuring the timeliness and accuracy of soil suitability assessment. Precipitation distribution data clearly demonstrates the spatiotemporal distribution characteristics of future precipitation, including total precipitation, seasonal distribution, and patterns of extreme precipitation events. Acquiring this data overcomes the limitations of assessments based on historical data, allowing climate suitability analysis to fully consider future climate evolution trends and making subsequent suitability index calculations more aligned with practical application scenarios.

[0083] Step S313: Based on the crop's suitable temperature range, soil suitability parameters, and precipitation requirement threshold, and combined with temperature change data, soil characteristic data, and precipitation distribution data under future climate scenarios, the climate suitability index of the crop in the target area is calculated according to a preset quantitative formula. Through the organic integration and quantitative calculation of multi-dimensional parameters, a scientific assessment of crop climate suitability is achieved. Using the crop's own environmental requirement parameters as a benchmark, combined with actual environmental data under future climate scenarios, ensures that the assessment results are both consistent with crop growth patterns and adaptable to future environmental changes. The preset quantitative formula, through reasonable weight allocation, comprehensively considers the impact of the three key factors—temperature, soil, and precipitation—on crop suitability, transforming scattered parameters into an intuitive and comparable suitability index, reducing the one-sidedness of single-factor assessments. The formula calculation process achieves precise matching analysis between crop requirements and environmental conditions, making climate suitability constraints more scientific and operable. The quantitative formula is: S I =T c ×0.4+S c ×0.3+R c ×0.3, where S I T represents the climate suitability index. c S represents the temperature adaptability coefficient. c R represents the soil compatibility coefficient. c This represents the precipitation fit coefficient.

[0084] Step S314 sets a climate suitability index greater than a preset suitability threshold as a crop climate suitability constraint. The preset suitability threshold is set based on the suitability level corresponding to the recent average annual crop yield in the target area. By setting a suitability threshold, areas with climate conditions suitable for crop growth are screened, ensuring the feasibility of the planting layout at the climate level. The preset suitability threshold, based on the suitability level corresponding to the recent average crop yield in the target area, achieves a close integration of the constraint with the actual local agricultural production, ensuring both climate suitability for crop growth and the need for yield stability. This constraint directly excludes inappropriate planting choices in climate-unsuitable areas, guiding crop planting towards climate-suitable areas from a macro perspective, providing a strong guarantee for improving overall planting efficiency and risk resistance.

[0085] like Figure 3 As shown, the steps for constructing resource and security constraints include:

[0086] Step S321 establishes a constraint that the water consumption for crop cultivation must be less than or equal to the available agricultural water resources in the region. The available agricultural water resources are calculated based on the county-level administrative unit, combined with the exploitable surface water and groundwater, minus the reserved water use by the ecological environment and other sectors. This constraint ensures a proper match between crop cultivation and water supply, guaranteeing the sustainable use of water resources in agricultural production. Calculating the available agricultural water resources by county-level administrative unit aligns with practical administrative management and resource allocation scenarios, accurately reflecting the differences in water resource endowments across different regions. By comprehensively considering the natural recharge of surface water and the upper limit of groundwater exploitation, and prioritizing ecological base flow and non-agricultural water needs, the supply capacity of regional agricultural water resources is defined, reducing estimation biases caused by considering a single water source or neglecting competition among multiple sectors. Limiting the water consumption for crop cultivation to within the available agricultural water resources effectively prevents excessive water extraction or waste, ensuring the water needs for crop growth while maintaining the ecological balance of regional water resources, providing water resource support for the stable development of agricultural production in flood-prone areas.

[0087] Step S322 establishes a constraint that the proportion of grain crop planting area is greater than or equal to a preset safety proportion. The preset safety proportion is set at 60% for major grain-producing areas and 40% for non-major grain-producing areas. This constraint establishes a solid bottom line for regional food security, ensuring that agricultural production layout is consistent with the national food security strategy. The preset safety proportion is set differently based on the functional positioning of regions. Major grain-producing areas, as the core areas of grain production, have a higher safety proportion set to guarantee the national grain supply; non-major grain-producing areas, taking into account both grain self-sufficiency and diversified agricultural development, have a reasonable safety proportion standard set to achieve synergy between food security and economic development. By mandating that the proportion of grain crop planting area is not lower than the preset standard, the basic scale of grain planting is guaranteed, and the excessive expansion of cash crops that squeeze grain planting space is reduced, thus stabilizing grain output from the layout level.

[0088] Step S323 establishes a constraint that the ecological impact index of crop planting is less than or equal to a preset ecological threshold. The preset ecological threshold is set at 0.5 for food crops and 0.4 for cash crops. This constraint promotes an eco-friendly approach to crop planting and facilitates the coordinated development of agricultural production and ecological protection. The preset ecological thresholds are differentiated for different crop types. Food crops, as basic crops ensuring people's livelihoods, have relatively lenient ecological thresholds to balance food production and ecological impact; cash crops have stricter ecological thresholds to strengthen the management of their ecological risks. By limiting the ecological impact index of crop planting within the preset thresholds, the negative impacts of crop planting on ecological elements such as soil, vegetation, and biodiversity are effectively controlled, reducing ecological degradation caused by agricultural production. This constraint not only ensures the economic benefits of agricultural production but also safeguards the bottom line of the regional ecological environment, facilitating the construction of an ecologically livable and sustainable agricultural development pattern in flood-prone areas.

[0089] like Figure 4 As shown, the steps for constructing resource and security constraints also include:

[0090] Step S324 determines the parameter thresholds corresponding to resource utilization, food security, and ecological protection. These thresholds include a preset safety ratio and a preset ecological threshold. The clarification of these thresholds establishes clear bottom lines for resource utilization, food security, and ecological protection, ensuring that the constraints are structured systematically. The preset safety ratio and preset ecological threshold correspond to the requirements for food supply security and ecological protection, respectively. By combining the available agricultural water resources in the region with the water requirements of various crops, the maximum arable area is precisely calculated according to crop type. This considers both the carrying capacity of regional water resources and the differences in water requirements among different crops, reducing planting risks caused by imbalances in water resource allocation. This achieves a precise match between resource constraints and crop characteristics.

[0091] Step S325 involves combining the available agricultural water resources in the region with the water requirements of each crop to calculate the maximum arable area for each crop type. The available agricultural water resources in the region are calculated by comprehensively considering the natural recharge capacity of surface water and the sustainable exploitation scale of groundwater, deducting water reserves for ecological environment and other sectors, reflecting the actual carrying capacity of agricultural water resources in the region. The water requirements parameters for each crop reflect the differences in water demand throughout the entire growth cycle, ensuring calculation by crop type. By allocating and calculating the available agricultural water resources in the region according to the crop water requirements parameters, the maximum arable area for each crop is determined, reducing water shortages caused by over-cultivation of a single crop while ensuring reasonable development space for various crops under water resource constraints. This makes water resource utilization more planned and efficient, preventing water waste or over-exploitation at the source, and providing a solid guarantee for the sustainable use of water resources in agricultural production in flood-prone areas.

[0092] Step S326 involves calculating the total regional grain output based on crop planting area ratios and yield parameters, and then using a preset safety ratio to determine the lower limit for grain crop planting area. Through quantitative calculation and reverse calculation logic, a bottom line for the planting scale of grain security is established, ensuring stable regional grain supply. Accurately calculating the total regional grain output based on crop planting area ratios and yield parameters makes grain production targets more operational. Using a preset safety ratio to determine the lower limit for grain crop planting area directly locks in the basic scale of grain planting, reducing the excessive expansion of cash crops that could squeeze grain planting space. Transforming grain security targets into clear planting area constraints allows the optimized plan to consider diverse needs while adhering to the bottom line of grain security, providing support for livelihood security and social stability in flood-prone areas.

[0093] Step S327 involves calculating the regional ecological impact index by summing the products of crop planting area and ecological impact coefficient, thus forming ecological impact constraints. Through scientific quantification and constraint construction, an eco-friendly orientation for crop planting is achieved, promoting the coordinated development of agricultural production and ecological protection. The regional ecological impact index, calculated by multiplying crop planting area and ecological impact coefficient, reflects the comprehensive impact of various crop planting methods on the ecological environment. Based on this, ecological impact constraints are formed, clearly defining the upper limit of regional ecological impact and effectively controlling ecological problems such as soil degradation and biodiversity loss that may be caused by crop planting. This transforms ecological protection from an abstract goal into quantifiable and actionable constraints, ensuring that agricultural production, while pursuing economic benefits, does not exceed the ecological carrying capacity limit.

[0094] Step S328 compares the actual planting area of ​​each crop with the maximum arable area, the planting area of ​​grain crops with the lower limit, and the ecological impact index with the preset ecological threshold to form resource and security constraints. Through multi-dimensional comparison and verification, a comprehensive and systematic resource and security constraint system is formed to ensure that the optimization plan takes into account multiple needs. Comparing the actual planting area of ​​each crop with the maximum arable area ensures the rationality and sustainability of water resource utilization; comparing the planting area of ​​grain crops with the lower limit safeguards the bottom line of food security; and comparing the ecological impact index with the preset ecological threshold strictly controls ecological and environmental risks. These three comparisons complement each other and provide layer-by-layer checks, constructing a three-dimensional constraint network, reducing imbalances caused by single-dimensional optimization, and ensuring that the resulting planting layout plan is scientific, reasonable, and feasible.

[0095] like Figure 5 As shown, the steps for constructing spatial and flood risk constraints include:

[0096] Step S331 establishes a constraint that the spatial clustering degree of crop planting at a preset grid scale is greater than or equal to a preset clustering degree threshold. This constraint strengthens the spatial rationality and management efficiency of crop planting layout, providing support for the large-scale operation of agricultural production. The preset grid scale conforms to the regional topography and actual planting management, ensuring that spatial division is both accurate and practical. Spatial clustering degree reflects the concentrated distribution characteristics of crop planting. By setting a constraint that is not lower than the preset threshold, it promotes the appropriate spatial concentration of similar crops, reducing problems such as increased management costs and inefficient resource utilization caused by dispersed planting layout. Centralized planting not only facilitates the unified implementation of agricultural operations such as field irrigation, fertilization, and pest and disease control, improving production management efficiency, but also optimizes the regional agricultural ecological pattern, enhances the adaptability of crop groups to environmental changes, and lays a spatial foundation for the large-scale and efficient development of agricultural production in flood-prone areas.

[0097] Preset grids are square grid units of fixed size and regular arrangement set in advance. They serve as the basic spatial carrier for spatial analysis and layout optimization. For example, 100m×100m or 1km×1km. Preset grids can transform continuous geographic space into quantifiable and computable discrete units, making it convenient to integrate data such as climate, soil, and flood risk.

[0098] Step S332 establishes a constraint that the flood risk coefficient of the crop planting area is less than or equal to a preset risk threshold. This constraint directly focuses on the needs of flood risk prevention and control, reducing disaster losses from the layout level. The flood risk coefficient comprehensively quantifies the degree of flood threat faced by the crop planting area. Its calculation integrates key disaster-causing factors such as flood depth and inundation duration with the crop's own flood tolerance characteristics, accurately reflecting the flood risk level of crops planted in different areas. By setting a preset risk threshold, the upper limit of crop planting risk is clearly defined, reducing the blind placement of flood-intolerant crops in high-flood-risk areas. Flood risk prevention and control is brought forward to the planting layout planning stage. By proactively avoiding high-risk areas or adapting to flood-tolerant crops, the damage of flood disasters to crop growth is reduced from the source, ensuring the stability of agricultural production.

[0099] In one embodiment of this application, the flood risk coefficient is calculated based on a correlation formula between flood depth, inundation duration, and crop flood tolerance sensitivity. Flood depth directly reflects the degree of flood stress on crops; the greater the depth, the higher the risk of damage to crop growth. Inundation duration determines the cumulative effect of stress; the longer the duration, the more significant the probability and degree of crop damage. Crop flood tolerance sensitivity reflects the inherent ability of different crops to cope with flood stress and is a core crop attribute for risk assessment. The organic combination of these three factors through the correlation formula breaks through the limitations of single-factor assessment, allowing the flood risk coefficient to comprehensively and objectively reflect the actual flood risk level of planting specific crops in a specific area.

[0100] The correlation formula is a mathematical expression that integrates three core factors—flood depth, inundation duration, and crop flood tolerance sensitivity—through quantitative weighting or functional relationships, and is used to accurately calculate flood risk coefficients.

[0101] The correlation formula is customized according to the actual scenario. For example, the flood risk coefficient = flood depth weighting coefficient × flood depth + inundation duration weighting coefficient × inundation duration + crop flood tolerance sensitivity correction coefficient. This transforms scattered disaster-causing and disaster-resistance factors into a unified risk quantification indicator, making flood risk assessment calculable and comparable. FR = α × H + β × T + γ × S, where FR represents the flood risk coefficient, ranging from 0 to 1, with a higher value indicating a higher flood risk to crops in the area; H represents the standardized flood depth value, which standardizes the ratio of the actual flood depth in the target area to the crop's critical flood tolerance depth from 0 to 1, directly reflecting the stress intensity of flooding on crops; T represents the standardized inundation duration value, which standardizes the ratio of the actual inundation duration to the crop's critical flood tolerance time from 0 to 1, reflecting the cumulative effect of flood stress; and S represents the corrected crop flood tolerance sensitivity, ranging from 0 to 1, indicating the crop's flood tolerance. The stronger the value, the smaller the value. It is calculated by the formula S=S0×(1-λ×D+μ×P), where S0 represents the basic value assigned to the crop type, D represents the soil drainage performance level coefficient, P represents the drainage efficiency coefficient of the water conservancy facility, λ and μ are correction coefficients with a value of 0.5; α, β and γ are weighting coefficients, which are dynamically set according to the flood disaster characteristics of the target area. α has a value of 0.4-0.5, flood depth is the core disaster-causing factor, β has a value of 0.3-0.4, inundation duration is the secondary disaster-causing factor, γ has a value of 0.1-0.2, and crop flood tolerance sensitivity is the disaster resistance adjustment factor, and α+β+γ=1 is satisfied.

[0102] Crop flood tolerance sensitivity is dynamically assigned based on crop type and adjusted by considering soil drainage performance and irrigation facility drainage efficiency. This dynamic assignment and scientific adjustment ensure that the sensitivity aligns with the complex conditions of actual planting scenarios. Different crops exhibit significant differences in physiological structure and growth characteristics, resulting in varying flood tolerance. Dynamic assignment based on crop type ensures that the sensitivity parameter reflects the inherent attributes of the crop. Soil drainage performance directly affects the rate of water receding from the field; better drainage performance reduces the actual impact of floods on crops. Irrigation facility drainage efficiency determines the effectiveness of water removal under artificial intervention; drainage facilities can effectively mitigate flooding. By combining these two factors to adjust the initial assignment, the crop flood tolerance sensitivity parameter better reflects the actual disaster resistance conditions of the region, reducing the discrepancy between theoretical values ​​and real-world scenarios.

[0103] Spatial clustering is calculated based on the spatial location relationships of grid cells, providing a quantitative standard for the rationality of crop planting spatial layout. As the basic unit of spatial analysis, the spatial location relationships of grid cells directly reflect the concentrated distribution characteristics of crop planting. By calculating the degree of association between adjacent grid cells of the same crop, spatial clustering is quantified, clearly presenting the dispersed or concentrated state of crop planting. This calculation method meets the spatial optimization needs at the grid scale, giving the spatial clustering index clear physical meaning and operability, and providing accurate data support for constructing spatial clustering constraints and guiding concentrated, large-scale crop planting.

[0104] like Figure 6 As shown, after the steps of forming an optimized crop planting layout scheme based on the optimization parameters, the following steps are included:

[0105] Step S50 involves multi-dimensional verification of the planting layout optimization plan to determine if it meets all constraints. Verification indicators include a yield achievement rate of ≥90%, a flood loss reduction rate of ≥25%, and a water resource utilization rate of ≥80%. This multi-dimensional verification strengthens the quality control of the planting layout optimization plan, ensuring it meets the needs of agricultural production in flood-prone areas. The yield achievement rate is directly related to the economic benefits of agricultural production and food supply capacity; a standard of at least 90% ensures the optimized plan can stably achieve the expected yield target. The requirement of a flood loss reduction rate of at least 25% focuses on the core of flood risk prevention and control, ensuring the plan effectively reduces disaster losses and enhances the resilience of agricultural production against disasters. The standard of a water resource utilization rate of at least 80% strengthens the orientation towards efficient water resource utilization, reduces resource waste, and aligns with the concept of sustainable development. Through comprehensive verification of key indicators, the plan's performance in yield guarantee, risk prevention and control, and resource utilization is fully evaluated to ensure it meets all constraints.

[0106] Step S51: If the conditions are not met, correct the optimization parameters. If parameter adjustments are ineffective, re-optimize the constraint threshold parameters. When the solution fails to meet the constraints, prioritize correcting the optimization parameters by fine-tuning core parameters such as crop planting area and spatial allocation of crop types to quickly adapt to the constraint requirements. If parameter correction still fails to achieve the expected results, re-optimize the constraint threshold parameters and adjust the constraint boundaries to reduce solution failures caused by unreasonable threshold settings. This step-by-step correction logic ensures both the flexibility and efficiency of the optimization process, as well as the scientific nature and adaptability of the constraints.

[0107] Step S52: If the conditions are met, the optimized planting layout scheme is determined to be a practical application scheme. When a scheme passes multi-dimensional verification and meets all constraints, it can be determined as a practical application scheme, meaning that the scheme has achieved the expected goals in terms of yield guarantee, flood risk prevention and control, water resource utilization, and ecological protection. The determination of the practical application scheme ends the iterative cycle of the optimization process and provides directly implementable planting layout guidance for flood-prone areas, ensuring the stability and efficiency of agricultural production while improving the climate adaptability and risk resistance of regional agriculture.

[0108] like Figure 7 As shown, the steps for multi-dimensional verification of the planting layout optimization scheme also include:

[0109] Step S510 defines an extreme climate scenario. This extreme climate scenario is based on the Coupled Model Intercomparison (CMIP) high-emission scenario. Under the high-emission scenario, the temperature rise exceeds a preset temperature, and the precipitation fluctuation exceeds a preset first percentage. The CMIP high-emission scenario aligns with the extreme development trend of global warming and reflects the most severe future climate evolution direction. The temperature rise exceeding the preset temperature and the precipitation fluctuation exceeding the preset first percentage quantify the degree of temperature and precipitation anomalies under extreme climate conditions, clarifying the extreme temperature stress and precipitation imbalance risks faced by crop growth. This allows subsequent validation to focus on the most unfavorable climate conditions, ensuring that the optimized scheme remains adaptable under extreme temperature and precipitation fluctuations, thus improving the scheme's climate resilience from the source. The first percentage is a preset quantitative threshold used to define the intensity of precipitation fluctuations under extreme climate scenarios. It is not a fixed value but needs to be set based on historical precipitation data of the target area and actual agricultural production needs, such as 15% or 20%. For example, when the deviation of the future total precipitation or seasonal distribution from the historical average exceeds the first percentage, it is determined to be an extreme precipitation fluctuation scenario.

[0110] Step S520 defines an extreme flood scenario as a high-recurrence-rate flood, where the flood depth exceeds a preset second percentage. It clarifies the key quantitative indicators for extreme flood scenarios, defining boundaries for verifying the flood risk resistance capability of the proposed solution. High-recurrence-rate floods represent flood events with extremely low probability of occurrence but extremely high destructive intensity, representing a critical extreme situation that agricultural production in flood-prone areas needs to focus on preventing. A flood depth exceeding the preset second percentage quantifies the inundation intensity of extreme floods, directly correlated with the risk level of crop damage. This makes the verification of extreme flood scenarios more targeted, ensuring that the optimized solution can maintain the bottom line of planting safety even under the threat of high-intensity floods. The second percentage is a preset quantitative threshold used to define the flood depth intensity under extreme flood scenarios. It is set in conjunction with historical flood depth data of the target area and the critical value for farmland flood tolerance, such as 30% or 40%. When the ratio of the high-recurrence-rate flood depth to the historical baseline flood depth exceeds the second percentage, it is determined to be an extreme flood intensity.

[0111] Step S530 verifies whether the optimized planting layout scheme can still meet the constraints under the superimposed conditions of extreme climate and extreme flood scenarios. Through rigorous verification under these extreme scenarios, the overall risk resistance capability of the optimized scheme is comprehensively tested. The superimposed extreme climate and extreme flood scenarios simulate the most unfavorable combined disaster environment, exceeding the verification intensity of unconventional scenarios. Verifying whether the scheme can still meet the constraints essentially tests whether the scheme can still guarantee multiple objectives of climate adaptability, resource sustainability, food security, and ecological friendliness under dual extreme pressures. This superimposed verification breaks through the limitations of single extreme scenario verification, ensuring that the scheme has comprehensive risk resistance capabilities, reducing production losses caused by insufficient response to a single extreme event, and making the final scheme more adaptable to the complex disaster risk pattern of flood-prone areas.

[0112] Step S540: If the conditions are not met under extreme scenarios, return to adjust the crop planting area and crop type spatial allocation. When the solution fails to meet the constraints under superimposed extreme scenarios, adjustments are made focusing on the two core optimization directions: crop planting area and crop type spatial allocation. By adjusting the area, resource allocation is optimized to prioritize planting space for crops resistant to extreme environments. By adjusting the crop type spatial allocation, the proportion of flood-resistant and extreme climate-resistant crops is increased. This targeted adjustment allows the solution to quickly adapt to the needs of extreme scenarios, reducing the inefficiency caused by generalized adjustments and ensuring that the optimization direction always revolves around improving adaptability to extreme environments.

[0113] Step S550: Regenerate the optimized scheme and verify it again. Regenerating the optimized scheme involves systematically integrating the adjusted parameters and solving the algorithm to form a new layout scheme adapted to extreme scenarios; the verification again is a secondary test of the extreme environment adaptability of the new scheme to ensure that the adjustment effect achieves the expected results.

[0114] like Figure 8 As shown, the steps for generating optimization parameters based on key indicators and a preset multi-objective intelligent optimization algorithm include:

[0115] Step S410 involves defining the optimization objectives, which include improving economic efficiency, ensuring food security, controlling ecological impact, and mitigating flood risks. Improving economic efficiency focuses on the output benefits of agricultural production, ensuring the economic feasibility and sustainability of planting activities. Ensuring food security upholds the basic needs of the people and ensures a stable regional food supply. Controlling ecological impact emphasizes the harmonious coexistence of agricultural production and the ecological environment, reducing ecological damage. Mitigating flood risks directly addresses the core pain points of flood-prone areas, reducing the impact of disasters on agricultural production. These four objectives cover economic, social, ecological, and risk prevention dimensions, breaking the limitations of single-objective optimization and ensuring that the optimization plan not only conforms to the laws of agricultural production but also accurately adapts to the specific needs of flood-prone areas.

[0116] Step S420 involves assigning differentiated weights to each optimization objective. This weight allocation is dynamically adjusted based on the policy orientation of the target region and the priority of agricultural production. The policy orientation of the target region determines the macro-direction of agricultural development, while the priority of agricultural production reflects the differences in the region's core needs. The weight allocation is dynamically adjusted based on both, ensuring that the optimization focus is more realistic. For example, major grain-producing areas can increase the weight of food security, ecologically sensitive areas can increase the weight of ecological impact control, and high-risk flood areas can increase the weight of flood risk avoidance. This dynamic adjustment mechanism reduces the rigidity of solutions caused by fixed weights, ensuring that the optimization process always revolves around the core needs of the region, making the final solution more targeted and practical.

[0117] Step S430 incorporates crop planting area and spatial allocation of crop types as decision variables for the algorithm, embedding constraints related to crop climate suitability, resource and security, and spatial and flood risk. Crop planting area and spatial allocation of crop types are used as core decision variables to lock in key dimensions for optimization, ensuring the optimization direction does not deviate from the requirements. Simultaneously, the three types of constraints—crop climate suitability, resource and security, and spatial and flood risk—are embedded into the algorithm to define scientific boundaries for the decision variables, reducing the likelihood of the optimization process exceeding the bottom lines of climate adaptability, resource sustainability, spatial rationality, and risk controllability.

[0118] Step S440 involves iterative algorithm calculations to obtain the crop planting area parameters and crop type spatial allocation parameters that satisfy all constraints and achieve synergistic optimization of the objectives, forming an optimization parameter set. The iterative algorithm solves for the optimal solution under multiple objectives and constraints, resulting in a scientifically reliable optimization parameter set. Through multiple rounds of iterative calculations, the optimization effects of different combinations of decision variables can be comprehensively explored, gradually approaching the ideal state that satisfies all constraints and achieves synergistic optimization of the four optimization objectives. The obtained crop planting area parameters and crop type spatial allocation parameters ensure a balance between economic benefits, food security, ecological protection, and flood risk avoidance, while strictly adhering to various constraints. The formation of the optimization parameter set provides a precise quantitative basis for the subsequent construction of specific planting layout schemes, ensuring that the schemes can take into account multiple values, adapt to regional needs, and effectively meet the climate adaptability and risk prevention requirements of agricultural production in flood-prone areas.

[0119] like Figure 9 As shown, the steps for obtaining future climate scenario data include:

[0120] Step S110 involves screening multiple climate prediction models, each containing simulation data corresponding to different emission pathways. Multiple sets of climate prediction models, each including simulation data for different emission pathways, are selected. These different emission pathways correspond to different global greenhouse gas emission trends, and their simulation data can reflect environmental change characteristics under different climate evolution directions, reducing the limitations of predictions caused by data from a single emission pathway. By integrating multi-model data, it ensures that subsequent climate scenario analysis can cover multiple possibilities from low to high emissions, making future climate scenario data more comprehensive and representative.

[0121] Step S120 uses the comprehensive correlation coefficient, standard deviation, and root mean square error to compare the fit between each climate prediction model and the observed climate data of the target area. The comprehensive correlation coefficient measures the linear correlation between the model's simulated data and the observed data; a higher value indicates that the simulated trend is more consistent with reality. The standard deviation reflects the degree of data dispersion, and by comparing them, the model's ability to reproduce the characteristics of climate fluctuations can be judged. The root mean square error quantifies the overall deviation between the simulated values ​​and the observed values, directly reflecting the model's simulation accuracy. By using these three indicators, the differences in simulation performance among the models are identified, reducing the one-sidedness of evaluation based on a single indicator.

[0122] Step S130: Candidate models that meet preset criteria for fit are screened, their comprehensive scores are calculated, and the optimal model is selected. This two-round screening process locks in the optimal climate prediction model, ensuring the reliability of subsequent climate data. First, candidate models meeting the preset criteria are screened, eliminating models with insufficient simulation accuracy and narrowing the selection range. Then, the candidate models are re-ranked by calculating a comprehensive score, which incorporates the weighting of multiple evaluation indicators to reflect the model's overall simulation capability. The model with the highest comprehensive score is selected as the optimal model, ensuring both simulation accuracy and stability / adaptability.

[0123] Step S140 involves correcting the climate sequence output by the optimal model. This correction method involves establishing a distribution mapping relationship between historical observation sequences and the model sequence, and optimizing the data using a climate change trend adjustment factor. Scientific correction of the climate sequence output by the optimal model improves the fit between the data and the actual climate characteristics of the target region. Establishing a distribution mapping relationship between historical observation sequences and the model sequence effectively corrects systematic biases in the model, making the distribution characteristics of the simulated data more consistent with observed data. Optimization using a climate change trend adjustment factor can correct biases while fully preserving the future climate evolution trend reflected by the model, reducing the loss of key climate signals during the correction process. The climate sequence, after dual optimization, possesses both accurate observational matching and the ability to accurately predict future climate change trends.

[0124] Step S150: Extract extreme climate event data from the corrected sequence to form future climate scenario data for constructing constraints. Extreme climate event data is directly related to the climate risks faced by crop cultivation. Extracting this data allows future climate scenario data to focus on extreme situations that significantly impact agricultural production. Using this type of data to construct constraints ensures that crop planting layout optimization fully considers the potential impact of extreme climate events, improves the climate adaptability and risk resistance of the plan, and makes the optimization results better meet the actual needs of flood-prone areas in responding to extreme climate events.

[0125] In one aspect, the steps for establishing crop climate suitability constraints also include:

[0126] Step S31: Obtain meteorological environmental variables, topographic environmental variables, soil environmental variables, and crop distribution environmental variables. Meteorological environmental variables cover various factors that reflect the annual variation characteristics, extreme characteristics, and seasonal differences of temperature and precipitation. These factors directly affect the temperature conditions and water supply for crop growth. Topographic environmental variables include altitude, slope, and aspect, which are used to characterize the heat distribution, sloping cultivation conditions, and light differences within the region. Different topographic conditions will indirectly affect the microenvironment for crop growth. Soil environmental variables involve parameters related to the physicochemical properties of the topsoil, such as soil acidity / alkalinity, nutrient content, and water retention capacity. These parameters determine the soil's ability to support crop growth. Crop distribution environmental variables are the actual distribution location information of crops within the target area, which can intuitively reflect the adaptation relationship between crops and existing environmental conditions.

[0127] Step S32 involves removing redundant variables from meteorological, topographical, soil, and crop distribution environmental variables to output a set of effective variables. Redundant variables refer to variables that are highly correlated and reflect overlapping environmental information. Retaining too many redundant variables increases the computational burden on the model and may interfere with the model's identification of core environmental factors. Specific correlation testing methods are used to determine the degree of association between variables, eliminating those with excessive correlation or redundant information. The final set of effective variables comprehensively and accurately reflects the key environmental factors affecting crop growth with the fewest possible variables.

[0128] Step S33 involves dividing the effective variable set into a training set and a test set, starting the suitability evaluation model, and performing cross-validation on the model to test its accuracy. If the accuracy is insufficient, variables are re-selected. Dividing the model into training and test sets separates training and validation. The training set allows the model to learn the statistical relationships and patterns between variables, while the test set tests the model's predictive ability for unknown data. The suitability evaluation model is a tool for simulating the adaptation relationship between crops and the environment based on the effective variable set. Cross-validation is a rigorous method for testing model accuracy. By repeatedly dividing the training and test sets and repeatedly training and validating the model, the stability and predictive accuracy of the model can be comprehensively evaluated. If the test results show that the model accuracy does not meet the preset standard, it indicates that the current effective variable set may have problems such as missing key factors or redundant variables interfering. In this case, it is necessary to return to the variable selection stage and re-optimize the variable combination until an effective variable set that can support the model to achieve acceptable accuracy is obtained.

[0129] Step S34: If the accuracy meets the standard, the natural breakpoint method is used to classify the output results of the suitability evaluation model into four levels: unsuitable, low-suitable, moderately suitable, and highly suitable. Generating these four levels transforms the abstract output data into intuitive and practical information. A suitable evaluation model meeting the accuracy standard means it can reliably reflect the adaptation relationship between crops and the environment. Its output results are usually continuous values, representing the suitability of crops in different regions. The natural breakpoint method is a classification method that can identify the natural clustering characteristics of data. Based on the distribution pattern of the data itself, it divides the suitability value into four distinct levels while maximizing the differences between different levels and minimizing the differences within the same level. An unsuitable level represents that the environmental conditions in the area cannot meet the crop's growth needs at all; a low-suitable level represents poor environmental conditions that can only barely support crop growth; a moderately suitable level represents good environmental conditions that can meet the basic needs of crop growth; and a highly suitable level represents excellent environmental conditions that are most conducive to crop growth. Through this classification, the suitable spatial pattern for crop growth within the target area can be clearly presented.

[0130] Step S35: Based on the classification results, output the range of medium-to-high suitability areas, using them as climate suitability constraints for crop planting. These medium-to-high suitability areas concentrate the space within the target area where environmental conditions are most favorable for crop growth. Explicitly outputting this range and using it as a climate suitability constraint essentially defines a scientific spatial boundary for crop planting. This constraint can guide planting activities to concentrate in areas with strong environmental adaptability, avoiding blindly planting crops in unsuitable or low-suitability areas, thereby improving the stability of crop growth and the reliability of yield. It can also reduce the waste and loss of agricultural production resources caused by unsuitable environments, providing a clear climate suitability basis for optimizing crop planting layout.

[0131] In one aspect, the optimization parameters include optimized crop planting area data and flood simulation results;

[0132] The steps for formulating an optimized crop planting layout plan based on the optimized parameters also include:

[0133] Step S41: Receive the optimized crop planting area data and use it as the non-spatial quantity requirement input for the spatial layout model. The optimized crop planting area data is a quantitative result determined based on a multi-objective intelligent optimization algorithm, comprehensively considering multiple objectives such as economic benefits, food security, ecological protection, and flood risk, thus clarifying the planting scale boundaries for various crops. The non-spatial quantity requirement of the spatial layout model refers to the constraint requirements on the total amount of crops planted, without involving specific geographical location allocation. Inputting the above area data into the model can provide a clear total quantity benchmark for subsequent spatial allocation, ensuring that the spatial layout result is consistent with the optimized planting structure in terms of quantity, and avoiding the problem of total quantity imbalance.

[0134] Step S42 involves obtaining flood simulation results and crop climate suitability constraints as spatial allocation guidance factors. Flood simulation results are data on flood distribution characteristics in the target area obtained through professional simulation techniques. These results clearly reflect the degree of flood threat faced by different regions, providing a basis for avoiding high-risk areas. Crop climate suitability constraints are defined based on the matching analysis of crop growth climate requirements and target area climate conditions, clarifying the spatial boundaries of suitable growth for various crops at the climate level. Spatial allocation guidance factors are key to guiding the model's spatial allocation of crops. Combining these two factors as guidance ensures that the model prioritizes areas with suitable climate conditions for crop growth while actively avoiding areas with high flood risk during spatial allocation, laying the foundation for subsequent precise spatial layout.

[0135] Step S43: Output the initial suitability probability based on the spatial layout model. This step involves the model making a preliminary judgment on the spatial adaptability of crops. The initial suitability probability is the initial probability value calculated by the model using its built-in algorithm, combining environmental driving factors and crop growth characteristics, indicating whether a spatial unit is suitable for planting a certain type of crop. This value directly reflects the basic adaptability between the spatial unit and the crop, providing an initial reference for subsequent risk correction and comprehensive allocation. It is an important intermediate result for spatial layout optimization.

[0136] Step S44 involves calling up flood risk coefficient data, performing a risk correction calculation on the initial suitability probability, and outputting the corrected suitability probability. The flood risk coefficient is a quantitative indicator calculated by comprehensively considering factors such as flood depth, inundation duration, and crop flood tolerance sensitivity. It can accurately reflect the flood risk level faced by planting specific crops in different spatial units. The risk correction calculation correlates the initial suitability probability with the flood risk coefficient, reasonably reducing the crop suitability probability in high-flood-risk areas and keeping the suitability probability in low-risk areas relatively stable. Through this correction, the suitability probability can better reflect the actual risk situation, avoiding over-planting crops in high-risk areas and improving the disaster resilience of spatial layout.

[0137] Step S45: Input the conversion elasticity coefficient and calculate the comprehensive allocation probability by combining it with the corrected suitability probability. The conversion elasticity coefficient is a parameter reflecting the spatial stability of different crop types, quantified by analyzing the crop planting transfer patterns over multiple time periods. A higher value indicates that the crop type is less likely to undergo spatial conversion, reflecting the historical continuity and stability requirements of crop planting. The comprehensive allocation probability is the final spatial allocation basis obtained by combining the corrected suitability probability and the conversion elasticity coefficient through specific calculations. It not only considers the compatibility and risk status of crops with spatial units but also takes into account the stability of crop planting, providing comprehensive and scientific decision support for the model to make reasonable spatial allocations.

[0138] Step S46 involves real-time comparison of the spatially allocated area of ​​each crop with the target area. The overall allocation probability is dynamically adjusted through iterative adjustment variables until the allocated area matches the target area, at which point the optimized crop spatial layout result is output. Real-time comparison refers to continuously monitoring the gap between the allocated spatial area of ​​each crop and the preset target area during the spatial allocation process. The iterative adjustment variable is a parameter in the model used to dynamically adjust the allocation rules. When there is a gap between the allocated area and the target area, this variable is adjusted to change the overall allocation probability, thereby affecting the subsequent spatial allocation direction and causing the allocation process to continuously move closer to the target area. After multiple iterative adjustments, until the spatially allocated area of ​​each crop completely matches the target area, the output optimized crop spatial layout result satisfies both the total quantity constraint requirements and achieves a scientific spatial configuration.

[0139] Step S47 involves verifying the consistency between the spatial layout optimization results and the optimized crop planting area data. If the verification passes, a complete crop planting layout optimization plan is formed. If the verification fails, the process returns to revise the suitability probability. Consistency verification involves checking whether the actual allocated area of ​​each type of crop in the spatial layout optimization results is completely consistent with the previously determined crop planting area data, ensuring there are no total deviations or discrepancies between spatial allocation and total requirements. If the verification passes, it indicates that the spatial layout and planting structure optimization goals are fully aligned. At this point, the two are integrated to form a complete optimization plan that includes planting scale and spatial location. If the verification fails, it indicates a deviation in the spatial allocation process, requiring a return to the risk correction stage to readjust the suitability probability calculation logic until the spatial layout results are consistent with the total requirements, ensuring the reliability and executability of the final plan.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for optimizing crop planting layout, characterized in that, The optimization method includes: Acquire flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters, including crop flood tolerance parameters, water requirement parameters, yield parameters, ecological impact coefficients, and suitable growth parameters; Determine the key indicators for optimizing crop planting layout, including crop planting area and spatial allocation of crop types; The constraints for crop planting layout are constructed, including constraints on crop climate suitability, constraints on resources and security, and constraints on space and flood risk. The flood simulation data, farmland inundation data, future climate scenario data, and crop-related parameters are imported into the constraints. Based on the key indicators and a preset multi-objective intelligent optimization algorithm, optimization parameters are generated, and a crop planting layout optimization scheme is formed according to the optimization parameters.

2. The optimization method according to claim 1, characterized in that, The steps for establishing crop climate suitability constraints include: The suitable temperature range, soil compatibility parameters, and precipitation requirement thresholds for crops are obtained. The soil compatibility parameters include the pH range and organic matter content threshold. To obtain data on temperature changes, soil properties, and precipitation distribution under future climate scenarios; Based on the crop's suitable temperature range, soil compatibility parameters, and precipitation requirement threshold, and combined with temperature change data, soil characteristic data, and precipitation distribution data under future climate scenarios, the crop's climate suitability index in the target area is calculated according to a preset quantitative formula, wherein the quantitative formula is: S I = T c ×0.4 + S c ×0.3+R c ×0.3, where S I T represents the climate suitability index. c S represents the temperature adaptability coefficient. c R represents the soil compatibility coefficient. c Represents the precipitation adaptability coefficient; The climate suitability index being greater than a preset suitability threshold is set as a crop climate suitability constraint. The preset suitability threshold is set based on the suitability level corresponding to the average annual yield of crops in the target area.

3. The optimization method according to claim 2, characterized in that, The steps for establishing resource and security constraints include: A constraint is established that the water consumption for crop cultivation is less than or equal to the available agricultural water resources in the region. The available agricultural water resources in the region are calculated based on the county-level administrative unit, combined with the exploitable surface water and groundwater, and after deducting the water reserved for ecological environment and other departments. A constraint is established that the proportion of grain crop planting area is greater than or equal to a preset safe proportion, wherein the preset safe proportion is set at 60% for major grain-producing areas and 40% for non-major grain-producing areas; A constraint is established that the ecological impact index of crop planting is less than or equal to a preset ecological threshold, wherein the preset ecological threshold is set to 0.5 for food crops and 0.4 for cash crops.

4. The optimization method according to claim 1, characterized in that, The steps for establishing resource and security constraints also include: Determine the parameter thresholds corresponding to resource utilization, food security, and ecological protection, wherein the parameter thresholds include a preset security ratio and a preset ecological threshold; By combining the available agricultural water resources in the region with the water requirements of each crop, the maximum cultivable area of ​​each crop is calculated separately according to crop type. Based on the crop planting area ratio and yield parameters, the total grain output of the region is calculated, and the lower limit of the grain crop planting area is determined by combining the preset safe proportion. The regional ecological impact index is calculated by summing the products of crop planting area and ecological impact coefficient, thus forming ecological impact constraints. By comparing the actual planting area of ​​each crop with the maximum arable area, the planting area of ​​grain crops with the lower limit, and the ecological impact index with the preset ecological threshold, resource and security constraints are formed.

5. The optimization method according to claim 1, characterized in that, The steps for constructing spatial and flood risk constraints include: Establish a constraint that the spatial clustering degree of crop planting at a preset grid scale is greater than or equal to a preset clustering degree threshold; Establish a constraint that the flood risk coefficient of the crop planting area is less than or equal to a preset risk threshold; The flood risk coefficient is calculated based on a correlation formula between flood depth, inundation duration, and crop flood tolerance sensitivity. The crop flood tolerance sensitivity is dynamically assigned based on crop type and is modified in combination with the drainage performance of arable land soil and the drainage efficiency of water conservancy facilities. The spatial clustering degree is calculated based on the spatial location association relationship of the grid cells.

6. The optimization method according to claim 1, characterized in that, After the step of forming an optimized crop planting layout scheme based on the optimized parameters, the following steps are included: The proposed planting layout optimization scheme was verified in multiple dimensions to determine whether it met all constraints. The verification indicators included a yield achievement rate of ≥90%, a flood loss reduction rate of ≥25%, and a water resource utilization rate of ≥80%. If the conditions are not met, adjust the optimization parameters. If adjusting the optimization parameters is ineffective, re-optimize the parameter thresholds of the constraints. If the conditions are met, then the planting layout optimization scheme is determined to be a practical application scheme.

7. The optimization method according to claim 1, characterized in that, The step of multi-dimensionally verifying the planting layout optimization scheme also includes: Define an extreme climate scenario, which is based on a coupled-mode comparison plan high-emission scenario, in which the temperature rise exceeds a preset temperature and the precipitation fluctuation exceeds a preset first percentage. An extreme flood scenario is defined as a high recurrence period flood, where the flood depth exceeds a preset second percentage. Verify whether the proposed planting layout optimization scheme can still meet the constraints under the superposition of extreme climate and extreme flood scenarios; If the conditions are not met under extreme circumstances, return to adjust the spatial allocation of crop planting area and crop type; Regenerate the optimized solution and verify it again.

8. The optimization method according to claim 1, characterized in that, The steps for generating optimization parameters based on the key indicators and the preset multi-objective intelligent optimization algorithm include: The optimization objectives are defined, including improving economic benefits, ensuring food security, controlling ecological impacts, and mitigating flood risks. Differentiated weights are assigned to each of the aforementioned optimization objectives, and the weight assignment is dynamically adjusted based on the policy orientation of the target region and the priority of agricultural production. The algorithm uses crop planting area and spatial allocation of crop types as decision variables, and embeds constraints related to crop climate suitability, resources and security, and spatial and flood risks. Through iterative calculations using the algorithm, the crop planting area parameters and crop type spatial allocation parameters that satisfy all constraints and are optimal in synergy with the optimization objective are obtained, forming a set of optimization parameters.

9. The optimization method according to claim 1, characterized in that, The steps to obtain data on future climate scenarios include: Multiple climate prediction models are selected, and the climate prediction models contain simulation data corresponding to different emission pathways; We used the comprehensive correlation coefficient, standard deviation, and root mean square error to compare the fit between various climate prediction models and measured climate data of the target area. Candidate patterns that meet the preset criteria are selected, and the comprehensive score of the candidate patterns is calculated to select the optimal pattern. The climate sequence output by the optimal model is corrected by establishing a distribution mapping relationship between historical observation sequences and model sequences, and optimizing the data by combining climate change trend adjustment factors. Extreme climate event data are extracted from the corrected sequence to form future climate scenario data for constructing constraints.

10. The optimization method according to claim 1, characterized in that, The optimization parameters include optimized crop planting area data and flood simulation results; The step of forming an optimized crop planting layout scheme based on the optimized parameters also includes: Receive the optimized crop planting area data and use the crop planting area data as the non-spatial quantity requirement input of the spatial layout model; The flood simulation results and crop climate suitability constraints are obtained and used as spatial allocation guiding factors. Output the initial suitability probability based on the spatial layout model; Call the flood risk coefficient data, perform a risk correction operation on the initial suitability probability, and output the corrected suitability probability; Input the conversion elasticity coefficient and calculate the overall allocation probability by combining it with the corrected suitability probability; The system compares the spatial allocation area of ​​each crop with the target area in real time, and dynamically adjusts the overall allocation probability by iteratively adjusting variables until the allocated area matches the target area, and outputs the crop spatial layout optimization results. The spatial layout optimization results are checked for consistency with the optimized crop planting area data. If the check passes, the results are integrated to form a complete crop planting layout optimization scheme. If the check fails, the suitability probability is returned for revision.

Images