Land resource space optimization configuration method and system

Abstract

The invention relates to the technical field of land resource management, in particular to a land resource space optimization configuration method and system, and the method comprises the following steps: dividing grid cells based on a land research region, setting the initial land utilization state of each cell, comparing the land suitability of adjacent cells, updating the land utilization type, and determining the land utilization state of each cell; and recursively calculating the change in each time step, and iteratively executing the transfer specification to obtain a land utilization change state sequence. According to the invention, through recursive calculation and land utilization state updating, land utilization dynamic simulation, data continuity and regional adaptability enhancement, vacancy value filling and neural network adjustment, data and environmental factor feedback adjustment, prediction precision and trend judgment capability are improved, and economic, social and ecological benefits are quantified. The land use proportion and spatial layout are optimized, the land resource allocation efficiency is improved, policy adjustment and scene simulation are combined, differentiated decision support is provided, and social fairness and efficient resource utilization are promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of land resource management, and in particular to a method and system for optimizing the spatial configuration of land resources. Background Art

[0002] The technical field of land resource management refers to the goal of maximizing economic, social and environmental benefits through reasonable planning, allocation and utilization of land resources. This field involves many aspects such as land planning, development, utilization and protection, with the focus on optimizing the land use structure and coordinating the relationship between land use and ecological protection. Land resource management also includes monitoring, evaluation and policy formulation of land use, and the use of modern information technology, remote sensing technology, big data analysis and other means to scientifically manage land resources and provide decision-making support. The goal of this field is to achieve sustainable utilization of land resources, reduce resource waste, protect the ecological environment, and promote balanced social and economic development.

[0003] Among them, the spatial optimization allocation method of land resources is a technical method in the field of land resource management, which is mainly used to improve the efficiency of land resource use. This method analyzes the current situation and demand of land resources, rationally plans the spatial layout of land, optimizes the land utilization structure, and ensures the efficient allocation of land resources. Its main purpose is to improve the benefits of land use, reduce invalid or inefficient land use, and promote the sustainable use of land resources, while taking into account environmental protection and social equity. In practical applications, the spatial optimization allocation method of land resources can be widely used in many fields such as urban planning, agricultural development, and regional economic layout, which helps to achieve a balance between economic growth and ecological protection.

[0004] In the dynamic simulation of land use, existing technologies rely on traditional planning methods, ignore the mutual influence and dynamic changes of neighborhood units, and find it difficult to fully capture the spatiotemporal changes of land use status, resulting in insufficient prediction accuracy. In land use planning, there is a lack of comprehensive quantification of economic, social and ecological benefits. Resource allocation is inefficient, and it is difficult to effectively resolve land conflicts, resulting in waste of land resources and ecological damage in some areas. In the decision-making process, existing technologies simply rely on static models, ignore the impact of policy scenarios on land use, and are unable to flexibly respond to dynamic environmental changes. The lack of a multi-party interest coordination mechanism can easily lead to intensified conflicts among stakeholders in planning, making it difficult to achieve social equity and rational use of resources, limiting the breadth and adaptability of existing technologies in practical applications, and hindering the sustainable management of land resources. Summary of the invention

[0005] In order to solve the problems that the existing technology relies on traditional planning methods in dynamic simulation of land use, ignores the mutual influence and dynamic changes of neighborhood units, and is difficult to fully capture the spatiotemporal changes of land use status, resulting in insufficient prediction accuracy, lack of comprehensive quantification of economic, social and ecological benefits in land use planning, and inefficient resource allocation. It is difficult to effectively solve land conflicts, resulting in waste of land resources and ecological damage in some areas. In the decision-making process, the existing technology simply relies on static models, ignores the impact of policy scenarios on land use, cannot flexibly respond to dynamic environmental changes, and lacks a multi-party interest coordination mechanism, which easily leads to intensified conflicts among stakeholders in planning, making it difficult to achieve social equity and rational use of resources, limiting the breadth and adaptability of existing technologies in practical applications, and hindering the sustainable management of land resources. The embodiment of the present invention provides a method and system for optimizing the spatial allocation of land resources. The technical solution is as follows:

[0006] On the one hand, a method for optimizing spatial allocation of land resources is provided, the method comprising:

[0007] S1: Based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land use type is updated by comparing the land suitability of adjacent cells, the change in each time step is recursively calculated, and the transfer regulations are iteratively executed to obtain the land use change state sequence;

[0008] S2: Based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled and then input into the artificial neural network, and the network parameters are adjusted in combination with the land use policy and ecological protection restriction conditions to obtain the prediction results of future land use change trends;

[0009] S3: Based on the predicted results of future land use change trends, quantify the economic, social and ecological benefits of land, calculate the land use conflict points by weight, optimize the land use ratio and spatial layout, and generate a land use planning scheme;

[0010] S4: According to the land use planning scheme, set the land use policy, combine the needs of ecological protection and economic development, simulate the differentiated policy scenarios, optimize the government decision-making, and obtain the government decision-making planning scheme;

[0011] S5: Based on the government decision-making and planning scheme, analyze the benefits of enterprises and residents’ needs, combine land use costs with environmental quality, analyze the impact of multiple interests, and generate a land resource spatial layout plan by coordinating and optimizing the strategies and choices of each entity.

[0012] As a further scheme of the present invention, the land use change state sequence includes regional coverage type, change frequency, and impact assessment; the future land use change trend prediction results include development trend prediction, influencing variable analysis, and policy response evaluation; the land use planning scheme includes use allocation scheme, layout adjustment strategy, and benefit evaluation criteria; the government decision-making planning scheme includes policy adjustment measures, development goal setting, and draft implementation regulations; the land resource spatial layout plan includes regional division details, interest balance mechanism, and environmental reference factors.

[0013] As a further solution of the present invention, based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land use type is updated by comparing the land suitability of adjacent cells, the change in each time step is recursively calculated, and the transfer regulations are iteratively executed to obtain the land use change state sequence. Specifically, the steps are:

[0014] S101: Based on the land study area, regular grid unit division is performed, grid boundaries and areas are determined, land use status is specified, agricultural land, construction land and unused land types are recorded, and the initial state data set of grid units is obtained;

[0015] S102: Based on the grid unit initial state data set, a neighborhood search operation is performed to determine the cell neighborhood range, count the land use types of the neighborhood units, sort the types according to suitability rules, record the suitability priorities between units, and obtain a land use suitability priority data set;

[0016] S103: Based on the land use suitability priority data set, recursive operations are performed to adjust the land use status of the grid unit, status updates are performed according to the priority list and transfer rules, unit status information is integrated, and a land use change status sequence is generated.

[0017] As a further solution of the present invention, based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled and then input into the artificial neural network, and the network parameters are adjusted in combination with the land use policy and ecological protection restriction conditions to obtain the prediction results of the future land use change trend. Specifically, the steps are as follows:

[0018] S201: Based on the land use change state sequence, capture original land use data, gradually extract spatial unit land use information, match missing values ​​and interpolate to fill in vacant values, correct abnormal data, and generate a regional land use data set;

[0019] S202: Based on the regional land use dataset, extract the land use change trend of the spatial unit, screen the policy and red line area, set the classification constraint rules and correct the data, adjust the abnormal state, and generate a regional land use dynamic dataset;

[0020] S203: Based on the regional land use dynamic data set and in combination with the original change trend, key environmental factors are called, the change parameter states and weights are recursively adjusted, the future land use change prediction values ​​are calculated, the change sequence is recorded, and the future land use change trend prediction results are obtained.

[0021] As a further solution of the present invention, the predicted value of future land use change is calculated according to the formula:

[0022]

[0023] Among them, LU pred represents the predicted value of future land use change, W c Represents the weight coefficient of environmental factors, C env represents the key environmental factor index, W t Represents the weight coefficient of the change trend, T ch Represents the original change trend value, W l represents the land use distribution adjustment weight coefficient, L adj Represents the adjusted land distribution area value, L total Represents the total land area value, W s Represents the model smoothing weight coefficient.

[0024] As a further solution of the present invention, according to the prediction results of the future land use change trend, the economic, social and ecological benefits of the land are quantified, and the land use conflict points are weightedly calculated to optimize the land use ratio and spatial layout, and the steps of generating a land use planning scheme are specifically as follows:

[0025] S301: Based on the future land use change trend prediction result, extract the core indicators of land benefits, analyze the benefit values ​​corresponding to the land use types, count and classify the benefit values, normalize and adjust them, and generate the land benefit quantification results;

[0026] S302: Based on the land benefit quantification results, compare the benefit value differences of differentiated land types, screen the core location and range of the conflict area, calculate the priority ranking, and generate a land use conflict priority data set;

[0027] S303: Based on the land use conflict priority data set, extract the land use ratio and spatial distribution constraints, gradually optimize the land use area allocation, adjust the spatial layout of the conflict area, and generate a land use planning scheme.

[0028] As a further solution of the present invention, according to the land use planning scheme, land use policies are set, and the differentiated policy scenarios are simulated to optimize government decision-making and obtain the government decision-making planning scheme in combination with ecological protection and economic development needs:

[0029] S401: Based on the land use planning scheme, extract spatial distribution data, statistically analyze benefit indicators through regional classification, adjust the tax rate range and subsidy standards to quantify benefit changes, summarize regional policy impact values, and generate a land use policy parameter data set;

[0030] S402: Based on the land use policy parameter data set, combined with ecological protection requirements and economic development constraints, extract land use restriction conditions, iteratively process policy combinations and superimpose benefit data, simulate land distribution changes, and generate differentiated policy scenario simulation data sets;

[0031] S403: Based on the differentiated policy scenario simulation data set, extract policy scenario land benefit data, calculate land benefit prediction errors, compare benefit ranking policy parameters, adjust land use ratio and spatial distribution, optimize subsidy and tax rate policy constraints, and generate government decision-making planning solutions.

[0032] As a further solution of the present invention, the land benefit prediction error is calculated according to the formula:

[0033]

[0034] Among them, y i represents the land benefit value of the ith policy scenario measured in real time, P i represents the adjustment ratio of policy parameters in the i-th policy scenario, L i represents the i-th land use adjustment ratio, T i represents the intensity of the adjustment of the i-th tax rate policy, S i represents the adjustment intensity of the ith subsidy policy, α 1 is the weight coefficient for adjusting the policy parameters, α 2 is the weight coefficient for land use adjustment ratio, β 1 is the adjustment coefficient for the intensity of tax rate policy adjustment, β 2 It is the adjustment coefficient for the intensity of subsidy policy adjustment.

[0035] As a further solution of the present invention, based on the government decision-making and planning scheme, analyzing the benefits of enterprises and residents' needs, combining land use costs and environmental quality, analyzing the impact of multiple interests, and by coordinating and optimizing the strategies and choices of each subject, the steps of generating a land resource spatial layout plan are specifically as follows:

[0036] S501: Based on the government decision-making and planning scheme, extract enterprise benefit and resident demand indicators, analyze and calculate enterprise benefit change values, screen influencing factors in combination with resident demand, quantify the weight of land use on indicators, and generate enterprise benefit and resident demand impact data sets;

[0037] S502: Based on the enterprise benefit and resident demand impact data set, extract the core interest parameters of multiple parties, assign weights to coordinate the priority of the interest parameters of multiple parties, adjust the land use ratio and distribution relationship, and generate a multi-party interest coordination parameter data set;

[0038] S503: Based on the multi-party interest coordination parameter data set, optimize the interest weights of multiple parties and the priority of land use, adjust the spatial layout of land use, optimize the land distribution boundaries and proportions, integrate the adjustment results to iteratively update the plan, and generate a land resource spatial layout plan.

[0039] On the other hand, an electric vehicle state monitoring system is provided, the electric vehicle state monitoring system is used to execute the above electric vehicle state monitoring method, the system comprises:

[0040] The grid unit division module performs grid division based on the land study area, sets the initial land use status of each grid unit, evaluates the land suitability of adjacent grids, updates the land type if the conditions are met, recursively updates the grid status, and obtains the land use unit change sequence;

[0041] The land use change analysis module extracts and corrects the original data based on the land use unit change sequence, fills in missing values, and adjusts the data in combination with land use policies and ecological conditions to obtain land use change feedback results;

[0042] The land use trend prediction module inputs data into the prediction model based on the land use change feedback results, adjusts parameters, performs multi-step prediction, and generates future land use trend prediction results;

[0043] The land use planning optimization module evaluates the economic, social and ecological benefits of the land, calculates the conflict points, optimizes the use ratio and spatial layout, and generates a land use planning optimization plan based on the future land use trend prediction results;

[0044] The government decision simulation module sets land use policy parameters based on the land use planning optimization plan, simulates differentiated policy scenarios, analyzes policy implementation results, and generates a government decision planning plan;

[0045] The multi-party interest coordination module analyzes the conflicting points of interests of multiple parties based on the government decision-making and planning scheme, adjusts strategies and land allocation, and obtains a land resource spatial layout plan by referring to resource allocation and ecological impact.

[0046] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0047] By recursively calculating land use changes and updating the status, it is helpful to accurately simulate land use dynamics and improve the data time series continuity and regional adaptability analysis capabilities. On the basis of capturing the state sequence of land use changes, combined with vacancy value filling and neural network modeling, through dynamic adjustment of data and environmental factor feedback, the prediction accuracy and trend judgment ability under environmental constraints are enhanced, providing a scientific basis for long-term land use planning. Through quantitative analysis of economic, social and ecological benefits, the proportion of land use and spatial layout are optimized, the land conflict points and utilization directions are clarified, and the efficiency of land resource allocation and conflict coordination capabilities are improved. Combined with government policy adjustments and scenario simulations, policy variables such as tax rates and subsidies are comprehensively optimized to provide differentiated decision-making support, improve the scientific nature and feasibility of decision-making, and solve the problems of uneven land distribution and declining environmental quality through strategic coordination of stakeholders and optimization of spatial layout, promote social equity and efficient use of resources, and enhance the systematicness and operability of land use planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the workflow of the present invention.

[0049] Figure 2 This is a detailed flow chart of S1 of the present invention.

[0050] Figure 3 This is a detailed flow chart of S2 of the present invention.

[0051] Figure 4 This is a detailed flow chart of S3 of the present invention.

[0052] Figure 5 This is a detailed flow chart of S4 of the present invention.

[0053] Figure 6 This is a detailed flow chart of S5 of the present invention.

[0054] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] See also Figure 1 The embodiment of the present invention provides a method for optimizing the spatial configuration of land resources. The processing flow of the method may include the following steps:

[0061] S1: Based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land suitability of adjacent cells is compared according to the land use type of the neighboring cells, the land use type is updated, the change in each time step is recursively calculated, the transfer regulations are iteratively executed, and the land use change state sequence is obtained;

[0062] S2: Based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled, and then input into the artificial neural network. The network parameters are adjusted in combination with the land use policy and the ecological protection red line restriction conditions. According to the feedback of the original data and environmental factors, the prediction results of future land use change trends are obtained;

[0063] S3: Based on the prediction results of future land use change trends, the economic, social and ecological benefits of land are quantified, and the land use conflict points are calculated by weighted calculation to optimize the land use ratio and spatial layout, and generate a land use planning scheme;

[0064] S4: According to the land use planning scheme, with the government as the decision-making body, set land use policies, including tax rates and subsidy policies, combine ecological protection and economic development needs, formulate decision constraints, simulate differentiated policy scenarios and provide feedback, optimize government decisions, and obtain government decision-making planning schemes;

[0065] S5: Based on the government decision-making and planning scheme, analyze the benefits of enterprises and residents' needs, combine land use costs and environmental quality, analyze the mutual influence of multiple interests, and generate a land resource spatial layout plan by coordinating and optimizing the strategies and choices of each subject.

[0066] The land use change state sequence includes regional coverage type, change frequency, and impact assessment. The future land use change trend forecast results include development trend forecast, influencing variable analysis, and policy response evaluation. The land use planning scheme includes use allocation scheme, layout adjustment strategy, and benefit evaluation standard. The government decision-making planning scheme includes policy adjustment measures, development goal setting, and draft implementation regulations. The land resource spatial layout plan includes regional division details, interest balance mechanism, and environmental reference factors.

[0067] Specifically, if Figure 2 As shown in the figure, based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land use type is updated by comparing the land suitability of adjacent cells, the changes in each time step are recursively calculated, and the transfer regulations are iteratively executed to obtain the land use change state sequence. The specific steps are:

[0068] S101: Based on the land study area, regular grid unit division is performed, grid boundaries and areas are determined, land use status is specified, agricultural land, construction land and unused land types are recorded, and the initial state data set of grid units is obtained;

[0069] Determine the grid boundary and area, divide the study area into several regularized grid cells by equal area division, record the spatial coordinates and area information of each cell, and record them uniformly in metric units to ensure the uniformity of cell size. Combined with the existing land use classification data, mark the land use status of each grid cell as agricultural land, construction land or unused land type. The classification is based on the results of the land resource status survey. At the same time, it is necessary to record the subdivision information of land use types, such as agricultural land is subdivided into cultivated land, forest land, grassland, etc., and construction land is subdivided into residential land, industrial land, public facility land, etc. By calling remote sensing images and geographic information system tools, extract the surface coverage information of each grid cell and cross-check it, calibrate the land use status label, ensure data accuracy, and form an initial state containing attributes such as grid cell number, spatial coordinates, area, and land use type. During the recording process, it is necessary to verify whether the cell boundary is completely consistent with the regional boundary. For the boundary cell, its area needs to be calculated according to the actual coverage ratio and its land use status needs to be corrected, and finally the grid cell initial state data set is obtained.

[0070] S102: Based on the grid unit initial state data set, a neighborhood search operation is performed to determine the cell neighborhood range, count the land use types of the neighborhood units, sort the types according to the suitability rules, record the suitability priorities between units, and obtain the land use suitability priority data set;

[0071] First, the neighborhood range is determined. According to the spatial coordinates of the cell, the range of the surrounding neighborhood grid cells of each unit is calculated. The specific range can be determined by the Euclidean distance threshold. For example, the neighborhood is determined by the side length of a grid cell as the radius. The land use types of the neighborhood units are counted, and the proportion and quantity of agricultural land, construction land and unused land in the neighborhood are recorded to provide a basis for suitability analysis. According to the land use suitability rules, such as agricultural development giving priority to areas adjacent to water sources, construction land giving priority to expanding to the edge of existing construction areas, and unused land giving priority to retaining ecologically sensitive areas, the land use types of each unit in the neighborhood are ranked in terms of suitability. The weighted scoring method is used to arrange the land use types of the neighborhood units from high to low according to suitability priority, and the suitability priority and ranking results are recorded for each unit to obtain a land use suitability priority dataset containing attributes such as unit number, neighborhood range, land use type ranking, and suitability priority.

[0072] S103: Based on the land use suitability priority data set, recursive operations are performed to adjust the land use status of the grid unit, status updates are performed according to the priority list and transfer rules, unit status information is integrated, and a land use change status sequence is generated;

[0073] Recursive operations are performed to adjust the land use status of grid cells. In each recursive process, the cells with the highest priority are selected in turn according to the suitability priority list, and the land use status needs to be updated according to the land use transfer rules. For example, the conversion of agricultural land to construction land must meet the planning indicator constraints. The land use status update operation is performed on the cells that meet the transfer conditions, and the updated status information is stored in the status sequence. For cells whose status has not changed, their current status is retained. During the recursive process, the status information of all grid cells needs to be integrated in real time, the area change of each land use type is counted, and the neighborhood impact is recalculated to update the suitability priority dataset. Through recursive iteration, until the land use status of all grid cells no longer changes, a land use change status sequence is generated, and the sequence is stored as a time series dataset to ensure that the status information can be traced and analyzed.

[0074] Specifically, if Figure 3As shown in the figure, based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled and then input into the artificial neural network, and the network parameters are adjusted in combination with the land use policy and ecological protection restrictions to obtain the future land use change trend prediction results. The specific steps are as follows:

[0075] S201: Based on the land use change state sequence, capture the original land use data, gradually extract the land use information of spatial units, match the missing values ​​and interpolate to fill the vacant values, correct the abnormal data, and generate the regional land use dataset;

[0076] The land use information of spatial units is gradually extracted. The time series data of each grid unit is read by partition extraction, and the land use type and area ratio of the unit are recorded. For units with missing values, the missing values ​​are filled by linear interpolation based on the land use change trend of adjacent time points. For example, if the land use area of ​​a unit is 200 hectares and 240 hectares at the previous and subsequent time points, the missing point will be calculated as 220 hectares by interpolation and assigned the corresponding land use type. For abnormal data, the neighborhood mean method is used for correction. The land use ratio of neighboring units at the same time point is counted, and abnormal values ​​that obviously deviate from the mean are eliminated. For example, if a unit is recorded as 500 hectares, but the neighborhood mean is only 100 hectares, it will be corrected to the neighborhood mean and its land use type will be remarked. After completing the data correction, the land use information of all units is integrated into a regional land use dataset, including unit number, time series, land use type and corrected area ratio, to ensure the integrity and continuity of the data.

[0077] S202: Based on the regional land use dataset, extract the land use change trend of spatial units, screen policies and red line areas, set classification constraint rules and correct data, adjust abnormal status, and generate a regional land use dynamic dataset;

[0078] Perform difference calculation on the time series data of each unit to calculate the rate and direction of land use change. For example, for a unit, if its agricultural land area decreases from 300 hectares to 200 hectares, and the construction land increases from 100 hectares to 200 hectares, then record its land use change rate as -100 hectares and +100 hectares respectively. Screen the policy protection area and red line area, set immutable constraints on the units within their scope to ensure that their land use type will not change. For general areas, make corrections through classification constraint rules, such as the expansion of construction land must follow planning control, and the development of unused land must meet the requirements of ecological protection red lines. For abnormal states in the data, such as sudden changes in the unit land use type, readjust its change state by analyzing the trends before and after to ensure the logical consistency of the data, and finally generate a regional land use dynamic data set, including unit number, land use type change trend, rate, classification constraint state and correction results, to ensure that the dynamic characteristics of land use changes in the region can be reflected.

[0079] S203: Based on the regional land use dynamic data set, combined with the original change trend, calling the key environmental factors, recursively adjusting the change parameter state and weight, calculating the future land use change prediction value, recording the change sequence, and obtaining the future land use change trend prediction result;

[0080] Calculate the predicted value of future land use change according to the formula:

[0081]

[0082] Among them, LU pred represents the predicted value of future land use change, W c Represents the weight coefficient of environmental factors, C env represents the key environmental factor index, W t Represents the weight coefficient of the change trend, T ch Represents the original change trend value, W l represents the land use distribution adjustment weight coefficient, L adj Represents the adjusted land distribution area value, L total Represents the total land area value, W s Represents the model smoothing weight coefficient;

[0083] The formula is used to calculate the predicted value of future land use change trend. The results are used to analyze the potential trend of dynamic changes in land use in a specific area and provide a decision-making basis for planning and management.

[0084] W c =0.35, indicating the weight coefficient of environmental factors, which is determined by the average value of environmental factors in land use related literature research. The weight coefficient fluctuates with the number and impact of key environmental factors;

[0085] C env =70, indicating the key environmental factor index, which is calculated by the standardized average values ​​of environmental parameters including water resources, climate change and ecological index in regional environmental monitoring data. This value reflects the comprehensive impact of regional environment on land use change;

[0086] W t =0.5, indicating the weight coefficient of the change trend, which is calculated based on the impact of the land use change trend in the past decade and is adjusted according to the time span and volatility of the change trend;

[0087] T ch =9, indicating the change trend value of past land use, which is calculated through historical land use dynamic data and the method is the average annual change rate;

[0088] W l =0.4, indicating the weight coefficient of land use distribution adjustment, which is determined based on the importance of land distribution optimization adjustment in expert analysis and increases with the increase of adjustment range;

[0089] L adj =1800, indicating the adjusted land distribution area value, which is calculated by adjusting the optimization plan, and the unit is square kilometers;

[0090] L total =2500, indicating the total land area value, which is directly obtained from the actual surveying and mapping data, in square kilometers;

[0091] W s =0.2, indicating the model smoothing weight coefficient, which is obtained by calculating the continuity impact of the model prediction, and the value is adjusted according to the smoothing degree requirement;

[0092] Substitute the parameters into the formula for calculation:

[0093] The calculation process is as follows:

[0094] W c ·C env =0.35·70=24.5;

[0095]

[0096]

[0097] Calculate the absolute value of the numerator: |24.5+1.5-0.288|=|25.712|=25.712;

[0098] Add smoothing factor: 1+W s =1+0.2=1.2;

[0099] Calculate the fraction:

[0100] The result 21.4267 shows that the predicted value of future land use change trend is 21.4267. The higher the value, the greater the change of regional land use will be. This result can be used to further analyze the feasibility of land use optimization schemes and adjust the key directions and priorities in regional environmental planning.

[0101] Specifically, if Figure 4 As shown in the figure, according to the prediction results of future land use change trends, the economic, social and ecological benefits of land are quantified, and the land use conflict points are calculated by weight, and the land use ratio and spatial layout are optimized. The specific steps to generate a land use planning scheme are as follows:

[0102] S301: Based on the prediction results of future land use change trends, extract the core indicators of land benefits, analyze the benefit values ​​corresponding to land use types, statistically and categorize the benefit values ​​and normalize and adjust them to generate the quantitative results of land benefits;

[0103] Specific indicators for benefit measurement are set, including economic benefits, ecological benefits and social benefits. Different weight values ​​are assigned to each type of benefit indicator in combination with the actual characteristics of each land use type. For economic benefits, the output value contribution of land per unit area is recorded. For example, the average annual income of agricultural land is recorded through agricultural output, and the contribution of construction land is calculated based on the market value of development and utilization. For ecological benefits, the ecological contribution values ​​of unused land and agricultural land are extracted through indicators such as carbon sequestration capacity and water conservation capacity. For social benefits, the social influence of facilities such as schools and hospitals on construction land is evaluated in combination with the public service facility supply capacity of land. After classifying and processing the above data, the benefit values ​​are normalized and adjusted, and each type of benefit value is dimensionlessly processed according to the same dimension to ensure comparability between different benefit indicators. The adjusted benefit values ​​are kept in the range of 0 to 1. The normalized benefit values ​​after the above classification are combined to generate land benefit quantification results, including land use type, core benefit indicators, normalized benefit values, etc., to lay a data foundation for subsequent analysis.

[0104] S302: Based on the land benefit quantification results, compare the benefit value differences of differentiated land types, screen the core location and range of the conflict area, calculate the priority ranking, and generate a land use conflict priority data set;

[0105] According to the performance of each land use type in each core indicator, the comparative relationship of differentiated benefit values ​​is calculated. For example, agricultural land has higher ecological benefits than construction land, but lower economic benefits than construction land. Based on this comparative relationship, the relative performance of the benefit values ​​of different land types is ranked, and the land types and regions with prominent differences are marked. Conflict areas are screened, and the core area range with significant conflicts is extracted by superimposing the land benefit quantification results and the future land use change prediction results. For example, the area with significant differences between economic benefits and ecological benefits is used as the conflict range. The land type benefit difference value of each conflict area is counted, and the priority ranking is calculated based on the potential contribution of land use. The basis of priority includes the size of the difference value, the area of ​​the region, and the degree of adaptation between the current land use and future planning. A land use conflict priority dataset is generated, including information such as the location of the conflict area, the difference in land type benefit values, and the priority ranking, which serves as the key basis for further optimizing the allocation of land use.

[0106] S303: Based on the land use conflict priority data set, extract the land use ratio and spatial distribution constraints, gradually optimize the land use area allocation, adjust the spatial layout of the conflict area, and generate a land use planning scheme;

[0107] Extract the land use ratio and spatial distribution constraints of the conflicting areas, clarify the current area ratio of different land types in each area, and set the optimization target value in combination with the planning objectives. For the conflicting areas with high priority, gradually optimize the land use area allocation. For example, by adjusting the area ratio of construction land and agricultural land, the economic benefits and ecological benefits in the region are balanced, while ensuring that the ecological function of the land is not damaged. Combined with spatial distribution constraints, such as red line protection areas and urban construction control lines, adjust the spatial layout of the conflicting areas, give priority to arranging construction land around existing development areas, avoid disorderly expansion of unused land, give priority to arranging agricultural land in water-rich areas or areas with high soil fertility, and give priority to ecological protection of unused land within the scope of the ecological red line. In the process of gradual optimization, the land benefit data needs to be dynamically updated to ensure that the benefit indicators of the land are continuously improved after each adjustment. Finally, the optimized land use area allocation data and spatial layout adjustment data are integrated to generate a land use planning scheme, including the optimized land use type distribution, area allocation and spatial layout, to guide the actual planning implementation.

[0108] Specifically, if Figure 5 As shown in the figure, according to the land use planning scheme, the land use policy is set, the needs of ecological protection and economic development are combined, the differentiated policy scenarios are simulated, the government decision is optimized, and the steps to obtain the government decision-making planning scheme are as follows:

[0109] S401: Based on the land use planning scheme, extract spatial distribution data, statistically analyze benefit indicators through regional classification, adjust the tax rate range and subsidy standards to quantify benefit changes, summarize the regional policy impact values, and generate a land use policy parameter data set;

[0110] The land use types in the planning scheme are divided into regions, and the distribution ratios and area data of different land types in each region are recorded. At the same time, core benefit indicators are extracted, including economic benefits, ecological benefits and social benefits. For different regions, the land tax rate range and subsidy standards are adjusted in combination with benefit indicators. For example, for areas with low economic benefits but high ecological benefits, lower tax rates are set and ecological protection subsidies are increased. For areas with high economic benefits but low ecological contributions, tax rates are moderately increased to promote efficient use of resources. Based on regional classification statistics, benefit changes are quantified. For example, the quantitative data on agricultural land with increased subsidies, increased output per unit area, and significant improvement in ecological benefits need to be clearly marked. According to the actual adjustment effects of regional policies, the policy impact values ​​are summarized, and the tax rate adjustments, subsidy changes and benefit improvements in different regions are integrated into a data set. Specific parameters such as land use types, benefit change values, and policy adjustment impacts are recorded. Finally, a land use policy parameter data set is generated to provide data support for subsequent scenario simulations.

[0111] S402: Based on the land use policy parameter dataset, combined with ecological protection requirements and economic development constraints, extract land use restrictions, iteratively process policy combinations and superimpose benefit data, simulate land distribution changes, and generate differentiated policy scenario simulation datasets;

[0112] Extract the use restrictions of each land type, such as agricultural land must meet the minimum grain output ratio, unused land must comply with the ecological red line protection requirements, and the expansion of construction land must be controlled within specific indicators. According to the policy parameters and restrictions, the policy combination is gradually iterated, such as adjusting the tax rate and subsidy ratio, superimposing the benefit data to calculate the land benefit performance after the combination, and recording the policy impact of each combination in the database. When simulating the change of land distribution, the spatial distribution data of the planning scheme is used as the initial input, and the land use ratio is reallocated based on the differentiated impact of the benefits after the policy adjustment. For example, by adjusting the subsidy intensity, the agricultural land area is expanded by 10%, while reducing the development pressure on the ecological area, and recalculating the benefit distribution value of each region, a differentiated policy scenario simulation data set is generated, including the land use type change, benefit performance, ecological and economic indicators under different policy combinations. Comparison results provide a scientific simulation basis for different policy scenarios.

[0113] S403: Based on the differentiated policy scenario simulation data set, extract policy scenario land benefit data, calculate land benefit prediction errors, compare benefit ranking policy parameters, adjust land use ratio and spatial distribution, optimize subsidy and tax rate policy constraints, and generate government decision-making planning schemes;

[0114] Calculate the land benefit prediction error according to the formula:

[0115]

[0116] Among them, y i represents the land benefit value of the ith policy scenario measured in real time, P i represents the adjustment ratio of policy parameters in the i-th policy scenario, L i represents the i-th land use adjustment ratio, T i represents the intensity of the adjustment of the i-th tax rate policy, S i represents the adjustment intensity of the ith subsidy policy, α 1 is the weight coefficient for adjusting the policy parameters, α 2 is the weight coefficient for land use adjustment ratio, β 1 is the adjustment coefficient for the intensity of tax rate policy adjustment, β 2 It is the adjustment coefficient for the intensity of subsidy policy adjustment;

[0117] Detailed explanation of the formula and calculation process:

[0118] This formula is used to calculate the prediction error E of land benefits after policy optimization, and the result is used to evaluate the prediction accuracy of the model;

[0119] n: sample size, set to 100, indicating the number of samples selected from the policy scenario simulation data set;

[0120] y i : The actual land benefit value of the ith sample, obtained through the land use benefit monitoring data of the policy implementation area. For example, the y value of the first sample 1 500,000 yuan / hectare;

[0121] P i : The policy parameter adjustment ratio of the ith sample, obtained through quantitative analysis of policy documents, for example, P of the first sample 1 is 0.2;

[0122] L i : The land use adjustment ratio of the i-th sample, obtained by comparing the current land use status and planning data. For example, L 1 is 0.3;

[0123] T i: The tax rate policy adjustment intensity of the ith sample, obtained through quantitative analysis of tax policy documents, for example, T of the first sample 1 is 0.1;

[0124] S i : The subsidy policy adjustment intensity of the ith sample, obtained through quantitative analysis of subsidy policy documents. For example, S 1 is 0.15;

[0125] α 1 : The weight coefficient of the policy parameter adjustment ratio is set to 0.4, reflecting the impact of policy changes on land benefits. This value is determined based on the regression analysis results of the impact of policy adjustments on land benefits in historical data and fluctuates with changes in the intensity of policy adjustments;

[0126] α 2 : The weight coefficient of the land use adjustment ratio is set to 0.3, which measures the sensitivity of land allocation benefits. This value is determined by analyzing the impact of different land uses on economic benefits and fluctuates with the change of the land use adjustment range;

[0127] β 1 : The adjustment coefficient of the intensity of tax rate policy adjustment is set at 0.2 to adjust the flexibility of economic levers. This value is determined according to the elasticity coefficient of the impact of tax rate adjustment on land use benefits and fluctuates with the change of tax rate adjustment range;

[0128] β 2 : The adjustment coefficient of the subsidy policy adjustment intensity is set to 0.1 to optimize the contribution of social benefits. This value is determined through empirical analysis of the impact of subsidy policies on land benefits and fluctuates with changes in subsidy intensity;

[0129] Substitute the parameters of the first sample into the formula for calculation:

[0130]

[0131] E≈7.06

[0132] The result E≈7.06 shows that the error between the predicted land benefit of the first sample and the actual value is about 70,600 yuan / hectare. This result is used to evaluate the prediction accuracy of the model on the first sample. The smaller the error, the more accurate the model prediction.

[0133] Specifically, if Figure 6 As shown in the figure, based on the government decision-making and planning scheme, the analysis of corporate benefits and residents' needs, combined with land use costs and environmental quality, the analysis of the impact of multiple interests, and the coordination and optimization of the strategies and choices of each subject, the steps to generate a land resource spatial layout plan are as follows:

[0134] S501: Based on the government decision-making and planning scheme, extract the enterprise benefit and resident demand indicators, analyze and calculate the enterprise benefit change value, screen the influencing factors in combination with the resident demand, quantify the weight of the land use on the indicators, and generate the enterprise benefit and resident demand impact data set;

[0135] The enterprise benefit indicators are refined into specific contents such as economic output per unit of land, enterprise return on investment, and changes in operating costs. The resident demand indicators include residential comfort, coverage of public service facilities, and number of employment opportunities. The enterprise benefit change value is analyzed and calculated. For example, by comparing the enterprise output value of land use distribution before and after adjustment, the changes in economic output per unit area of ​​land are recorded, and the increase or decrease is marked as the benefit change value. Combined with the needs of residents, the key factors affecting land use are screened, such as the distribution of public facilities, the impact of the proportion of green area on residential comfort, and the impact of new industrial land on employment opportunities. According to the factors, the weight of land use on each indicator is quantified. For example, the weight of green area on resident comfort is 0.3, and the weight of public service facilities on demand satisfaction is 0.4. The enterprise benefit change value and the weight of resident demand impact are integrated to generate a data set of enterprise benefit and resident demand impact, which contains the contribution value, weight distribution and change data of each land use type on each indicator, and provides basic data for multi-party interest coordination.

[0136] S502: Based on the enterprise benefit and resident demand impact data set, extract the core interest parameters of multiple parties, assign weights to coordinate the priority of the interest parameters of multiple parties, adjust the proportion and distribution relationship of land use, and generate a data set of multi-party interest coordination parameters;

[0137] Extract the core interest parameters of multiple parties, including the economic benefit parameters of enterprises, the living demand parameters of residents, and the ecological protection and economic growth indicators of the government, assign weights to each parameter, coordinate the priorities of the interest parameters of multiple parties by comprehensively considering the importance and urgency of the needs of multiple parties, and adjust the proportion and distribution relationship of land use according to the priority weights. For example, some industrial land can be adjusted to mixed-use land to meet the needs of residents without affecting the growth of corporate benefits. Conduct a benefit evaluation on each adjustment plan, record the changes in economic benefits, residents' demand satisfaction and ecological indicators before and after the adjustment, and integrate the adjusted results into a multi-party interest coordination parameter data set, including land use adjustment plans, priority parameters and weight allocation, and adjusted benefit performance, to provide guidance for optimizing land distribution.

[0138] S503: Based on the multi-party interest coordination parameter data set, optimize the interest weights of multiple parties and the priority of land use, adjust the spatial layout of land use, optimize the land distribution boundaries and proportions, integrate the adjustment results to iteratively update the plan, and generate a land resource spatial layout plan;

[0139] The weight distribution and priority data are used as optimization inputs to readjust the spatial layout of land use. For areas with higher priority, such as areas with higher resident demand, green space and public facility land are allocated first. For areas with greater impact on corporate benefits, the spatial continuity and transportation convenience of industrial land are ensured. For areas with priority for ecological protection, the distribution of unused land and ecological land is further optimized to improve the overall ecological benefit. During the adjustment process, the spatial boundaries of land use are optimized to reduce land waste caused by irregular distribution. At the same time, the proportion of land use is adjusted to meet the needs of multiple parties. For example, the proportion of industrial land is controlled within 20%, and the proportion of residential land is ensured to be no less than 50%. The adjusted land use data and spatial layout information are integrated, and the plan is iterated and updated multiple times to ensure that the matching degree between land benefits and multiple needs is continuously improved after each adjustment. A land resource spatial layout plan is generated, including the optimized land use proportion, spatial distribution and boundary adjustment information, to provide an implementation basis for efficient use of land resources and balance of interests.

[0140] The grid unit division module performs grid division based on the land study area, sets the initial land use status of each grid unit, evaluates the land suitability of adjacent grids, updates the land type if the conditions are met, recursively updates the grid status, and obtains the land use unit change sequence;

[0141] The grid unit division module performs grid division based on the land study area, sets the initial land use status of each grid unit, evaluates the land suitability of adjacent grids, updates the land type if the conditions are met, recursively updates the grid status, and obtains the land use unit change sequence;

[0142] The land use change analysis module extracts and corrects the original data based on the land use unit change sequence, fills in the missing values, and adjusts the data in combination with land use policies and ecological conditions to obtain the land use change feedback results;

[0143] The land use trend prediction module inputs data into the prediction model based on the feedback results of land use changes, adjusts parameters, performs multi-step prediction, and generates future land use trend prediction results;

[0144] The land use planning optimization module evaluates the economic, social and ecological benefits of land, calculates conflict points, optimizes the use ratio and spatial layout, and generates land use planning optimization plans based on the prediction results of future land use trends;

[0145] The government decision-making simulation module sets land use policy parameters based on the land use planning optimization plan, simulates differentiated policy scenarios, analyzes policy implementation results, and generates government decision-making planning plans;

[0146] The multi-party interest coordination module is based on government decision-making and planning schemes, analyzes the conflicting points of interests among multiple parties, adjusts strategies and land allocation, and obtains a land resource spatial layout plan by referring to resource allocation and ecological impact.

[0147] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for optimizing spatial allocation of land resources, characterized in that: The following steps are involved: Based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land use type is updated by comparing the land suitability of adjacent cells, the change in each time step is recursively calculated, and the transfer regulations are iteratively executed to obtain the land use change state sequence; Based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled and then input into the artificial neural network, and the network parameters are adjusted in combination with the land use policy and ecological protection restriction conditions to obtain the prediction results of the future land use change trend; Based on the predicted results of future land use change trends, the economic, social and ecological benefits of land are quantified, and land use conflict points are calculated by weight, the land use ratio and spatial layout are optimized, and a land use planning scheme is generated; According to the land use planning scheme, set the land use policy, combine ecological protection and economic development needs, simulate differentiated policy scenarios, optimize government decision-making, and obtain the government decision-making planning scheme; Based on the government decision-making and planning scheme, analyze the benefits of enterprises and residents' needs, combine land use costs and environmental quality, analyze the impact of multiple interests, and generate a land resource spatial layout plan by coordinating and optimizing the strategies and choices of each entity.

2. The method for optimizing spatial allocation of land resources according to claim 1, characterized in that: The land use change state sequence includes regional coverage type, change frequency, and impact assessment; the future land use change trend prediction results include development trend prediction, influencing variable analysis, and policy response evaluation; the land use planning scheme includes use allocation scheme, layout adjustment strategy, and benefit evaluation criteria; the government decision-making planning scheme includes policy adjustment measures, development goal setting, and draft implementation regulations; the land resource spatial layout plan includes regional division details, interest balance mechanism, and environmental reference factors.

3. The method for optimizing spatial allocation of land resources according to claim 1, characterized in that: Based on the land study area, grid cells are divided, the initial land use state of each cell is set, the land use type is updated by comparing the land suitability of adjacent cells, the changes in each time step are recursively calculated, and the transfer regulations are iteratively executed to obtain the land use change state sequence. The specific steps are as follows: Based on the land study area, regular grid unit division is carried out, grid boundaries and areas are determined, land use status is specified, agricultural land, construction land and unused land types are recorded, and the initial state data set of grid units is obtained; Based on the grid unit initial state data set, a neighborhood search operation is performed to determine the cell neighborhood range, count the land use types of the neighborhood units, sort the types according to the suitability rules, record the suitability priorities between units, and obtain the land use suitability priority data set; Based on the land use suitability priority dataset, a recursive operation is performed to adjust the land use status of the grid unit, and the status update is performed according to the priority list and the transfer rule, and the unit status information is integrated to generate a land use change status sequence.

4. The method for optimizing spatial allocation of land resources according to claim 1, characterized in that: Based on the land use change state sequence, the original land use data of the region is captured, the missing values ​​are filled and then input into the artificial neural network, and the network parameters are adjusted in combination with the land use policy and ecological protection restrictions to obtain the future land use change trend prediction results. The specific steps are as follows: Based on the land use change state sequence, original land use data is captured, land use information of spatial units is gradually extracted, missing values ​​are matched and interpolated to fill in the vacant values, abnormal data is corrected, and a regional land use data set is generated; Based on the regional land use dataset, extract the land use change trend of spatial units, screen policies and red line areas, set classification constraint rules and correct data, adjust abnormal status, and generate a regional land use dynamic dataset; Based on the regional land use dynamic data set, combined with the original change trend, calling the key environmental factors, recursively adjusting the change parameter status and weight, calculating the future land use change prediction value, recording the change sequence, and obtaining the future land use change trend prediction result.

5. The method for optimizing spatial allocation of land resources according to claim 4, characterized in that: Calculate the predicted value of future land use change according to the formula: Among them, LU pred represents the predicted value of future land use change, W c Represents the weight coefficient of environmental factors, C env represents the key environmental factor index, W t Represents the weight coefficient of the change trend, T ch Represents the original change trend value, W l represents the land use distribution adjustment weight coefficient, L adj Represents the adjusted land distribution area value, L total Represents the total land area value, W s Represents the model smoothing weight coefficient.

6. The method for optimizing spatial allocation of land resources according to claim 1, characterized in that: According to the predicted results of future land use change trends, the economic, social and ecological benefits of land are quantified, and the land use conflict points are calculated by weight, and the land use ratio and spatial layout are optimized. The specific steps for generating a land use planning scheme are as follows: Based on the predicted results of future land use change trends, core indicators of land benefits are extracted, the benefit values ​​corresponding to land use types are analyzed, the benefit values ​​are statistically processed and classified, and normalized and adjusted to generate quantitative results of land benefits; Based on the land benefit quantification results, the benefit value differences of differentiated land types are compared, the core location and scope of the conflict area are screened, and the priority ranking is calculated to generate a land use conflict priority data set; Based on the land use conflict priority dataset, the land use ratio and spatial distribution constraints are extracted, the land use area allocation is gradually optimized, the spatial layout of the conflict area is adjusted, and the land use planning scheme is generated.

7. The method for optimizing spatial allocation of land resources according to claim 1, characterized in that: According to the land use planning scheme, the land use policy is set, the needs of ecological protection and economic development are combined, the differentiated policy scenarios are simulated, the government decision is optimized, and the steps to obtain the government decision-making planning scheme are as follows: Based on the land use planning scheme, extract spatial distribution data, statistically analyze benefit indicators through regional classification, adjust the tax rate range and subsidy standards to quantify benefit changes, summarize regional policy impact values, and generate a land use policy parameter data set; Based on the land use policy parameter dataset, combined with ecological protection requirements and economic development constraints, land use restriction conditions are extracted, policy combinations are iteratively processed and benefit data are superimposed to simulate land distribution changes and generate differentiated policy scenario simulation datasets; Based on the differentiated policy scenario simulation data set, the policy scenario land benefit data is extracted, the land benefit prediction error is calculated, the benefit ranking policy parameters are compared, the land use ratio and spatial distribution are adjusted, the subsidy and tax rate policy constraints are optimized, and the government decision-making planning scheme is generated.

8. The method for optimizing spatial allocation of land resources according to claim 7, characterized in that: Calculate the land benefit prediction error according to the formula: Among them, y i represents the land benefit value of the ith policy scenario measured in real time, P i represents the adjustment ratio of policy parameters in the i-th policy scenario, L i represents the i-th land use adjustment ratio, T i represents the intensity of the adjustment of the i-th tax rate policy, S i represents the adjustment intensity of the i-th subsidy policy, α1 is the weight coefficient of the policy parameter adjustment ratio, α2 is the weight coefficient of the land use adjustment ratio, β1 is the adjustment coefficient of the tax rate policy adjustment intensity, and β2 is the adjustment coefficient of the subsidy policy adjustment intensity.

9. The land resource space optimization configuration system according to claim 1, characterized in that: Based on the government decision-making and planning scheme, the steps of analyzing the benefits of enterprises and residents' needs, combining land use costs and environmental quality, analyzing the impact of multiple interests, and coordinating and optimizing the strategies and choices of each subject to generate a land resource spatial layout plan are as follows: Based on the government decision-making and planning scheme, extract enterprise benefit and resident demand indicators, analyze and calculate enterprise benefit change values, screen influencing factors based on resident demand, quantify the weight of land use on indicators, and generate enterprise benefit and resident demand impact data sets; Based on the enterprise benefit and resident demand impact data set, extract the core interest parameters of multiple parties, assign weights to coordinate the priority of the interest parameters of multiple parties, adjust the proportion and distribution relationship of land use, and generate a data set of multi-party interest coordination parameters; Based on the multi-party interest coordination parameter data set, the interest weights of multiple parties and the priority of land use are optimized, the spatial layout of land use is adjusted, the land distribution boundaries and proportions are optimized, the adjustment results are integrated to iteratively update the plan, and a land resource spatial layout plan is generated.

10. A land resource space optimization configuration system, characterized in that: According to any one of claims 1 to 9, the land resource spatial optimization configuration method, the system comprises: The grid unit division module performs grid division based on the land study area, sets the initial land use status of each grid unit, evaluates the land suitability of adjacent grids, updates the land type if the conditions are met, recursively updates the grid status, and obtains the land use unit change sequence; The land use change analysis module extracts and corrects the original data based on the land use unit change sequence, fills in missing values, and adjusts the data in combination with land use policies and ecological conditions to obtain land use change feedback results; The land use trend prediction module inputs data into the prediction model based on the land use change feedback results, adjusts parameters, performs multi-step prediction, and generates future land use trend prediction results; The land use planning optimization module evaluates the economic, social and ecological benefits of the land, calculates the conflict points, optimizes the use ratio and spatial layout, and generates a land use planning optimization plan based on the future land use trend prediction results; The government decision simulation module sets land use policy parameters based on the land use planning optimization plan, simulates differentiated policy scenarios, analyzes policy implementation results, and generates a government decision planning plan; The multi-party interest coordination module analyzes the conflicting points of interests of multiple parties based on the government decision-making and planning scheme, adjusts strategies and land allocation, and obtains a land resource spatial layout plan by referring to resource allocation and ecological impact.

Images