Land utilization optimization method and system based on big data

Abstract

The invention relates to the technical field of land management, in particular to a land utilization optimization method and system based on big data, which are used for acquiring soil, climate, infrastructure and terrain data, classifying according to soil particles, drainage and nutrients, analyzing road and water conservancy distribution, evaluating accessibility and supply capability and generating a land utilization feature classification result. According to the method, the soil quality, the climate conditions, the infrastructure distribution and the terrain and landform information are comprehensively analyzed, so that the land classification precision is improved, and the comprehensiveness of data integration is ensured. According to soil characteristics and long-term environmental changes, land use matching is optimized, and the scientificity of resource allocation is improved. In combination with terrain change characteristics, drainage conditions are optimized, the water accumulation risk is reduced, and the land applicability is enhanced. The spatial distribution is adjusted, the use intensity is optimized, use conflicts are reduced, and the rationality of the land spatial structure is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of land management, and particularly to a method and system for optimizing land use based on big data. Background Art

[0002] The technical field of land management includes the rational utilization, planning, and management of land resources, including aspects such as land classification, utilization pattern optimization, ecological environment assessment, and policy formulation. The core lies in using informatization, digitization, and intelligent means to improve land use efficiency, reduce resource waste, and promote sustainable development. Land management involves multiple links, including land survey, mapping, land use control, land use planning, and land reclamation. In recent years, with the development of technologies such as big data, remote sensing monitoring, and geographic information systems, land management technology has gradually evolved towards intelligence and refinement, relying on big data analysis and spatial information technology to achieve precise monitoring, reasonable allocation, and scientific management of land resources.

[0003] Among them, the method for optimizing land use based on big data refers to using big data technology to analyze the allocation of land resources and improving land use efficiency through optimization strategies. It covers technical matters such as data collection, data analysis, construction of land use models, and formulation of optimization plans. First, land use data is collected through various means such as satellite remote sensing, UAV aerial photography, and sensors, including soil type, terrain features, crop types, and historical use conditions. Secondly, the geographic information system is used to integrate and spatially analyze the data, identify land use patterns, and establish a database in combination with land classification standards. Then, based on machine learning and statistical modeling methods, the land use demand, environmental carrying capacity, and policy constraints are analyzed to form optimization strategies. Finally, combined with geographic spatial analysis methods, specific land optimization use plans are provided, such as the delineation of cultivated land protection areas, adjustment of urban expansion plans, and identification of ecological restoration areas, so as to make the land resources more scientifically allocated on the basis of meeting policy regulations.

[0004] The existing technologies have problems such as insufficient data integration, low classification accuracy, imperfect terrain analysis, and uneven spatial distribution in land use optimization. The data collection method is single, affecting the accuracy of land use classification. The land use matching relies on static analysis and lacks long-term environmental adaptability. The terrain analysis does not fully consider factors such as elevation, slope, and water system, which is likely to cause problems such as poor drainage or waterlogging, reducing the safety of land use. The land use distribution has not been optimized, with serious use conflicts in high-density areas and resource waste in low-density areas, limiting the overall use efficiency. The boundary connection and function matching lack systematic optimization, affecting the coordinated use of regional land resources. Summary of the Invention

[0005] To solve the technical problems existing in the prior art, an embodiment of the present invention provides a method and system for optimizing land use based on big data. The technical solutions are as follows:

[0006] A method for optimizing land use based on big data, comprising the following steps:

[0007] S1: Obtain soil, climate, infrastructure, and terrain data, classify them according to soil particles, drainage, and nutrients, analyze the distribution of roads and water conservancy, evaluate accessibility and supply capacity, and generate a classification result of plot utilization characteristics;

[0008] S2: Based on the soil categories in the classification result of plot utilization characteristics, extract areas matching agriculture, construction, and ecological protection, analyze the climate adaptability of the matching areas, and adjust the boundary areas to generate a classification matching distribution result of plots;

[0009] S3: Based on the terrain characteristics in the classification matching distribution result of plots, judge the influence of elevation, slope, and water system on land use, adjust steep or low-lying slope areas, and count terrain adaptation information to generate a terrain adaptation distribution result of plots;

[0010] S4: Based on the terrain adaptation distribution result of plots, analyze the spatial density distribution of agricultural, construction, and ecological plots, adjust plots with scattered uses, compare the relevance of uses of adjacent plots, and generate an optimized distribution result of plot utilization types;

[0011] S5: Based on the optimized distribution result of plot utilization types, evaluate the land use structure, analyze the spatial coordination of plots, detect the connection of plot boundaries, optimize the matching degree between plots, and generate an adjustment result of land use areas.

[0012] As a further solution of the present invention, the classification result of plot utilization characteristics includes soil type, precipitation characteristics, evaporation characteristics, infrastructure accessibility, and land use attribute; the classification matching distribution result of plots includes matching areas for agricultural land, construction land, ecological protection land, and infrastructure adaptability; the terrain adaptation distribution result of plots includes elevation distribution, slope characteristics, water system influence, drainage capacity, and waterlogging risk areas; the optimized distribution result of plot utilization types includes spatial distribution of land use, intensity of use, use conflict areas, and optimized use configuration plan; the adjustment result of land use areas includes optimization of land use structure, adjustment of spatial coordination, optimization of boundary connection, correction of function matching, and adjustment of layout rationality.

[0013] As a further solution of the present invention, the steps for obtaining the classification result of plot utilization characteristics are:

[0014] S101: Obtain the data of the soil particle composition, drainage capacity, and nutrient content of the plot. Based on the sand proportion, clay proportion, and silt proportion in the soil particle composition, perform particle size level division. Call the drainage capacity and nutrient content data for comparison, calculate the average values of the drainage capacity and nutrient content under different particle size structures respectively, and divide different soil type categories according to the average value threshold to obtain the soil attribute category value;

[0015] S102: Call the soil attribute category value, jointly obtain the precipitation data and evaporation data of the plot, count the annual data change frequency according to the daily scale and monthly scale respectively, calculate the daily average change rate, monthly fluctuation range, and extreme difference value of precipitation and evaporation, and use the formula:

[0016]

[0017] where, P i represents the precipitation on the i-th day, E i represents the evaporation on the i-th day, n is the number of days participating in the statistics, P j , E j represent the precipitation and evaporation in the j-th month, m is the number of months participating in the statistics, μ represents the average value on the monthly scale , min k (P k +E k ) represents the sum of the minimum precipitation and evaporation on a certain day in the whole year;

[0018] Perform operations to obtain the water dynamic trend value, and combine it with the plot soil type for judgment, establish the water response difference comparison result, and obtain the water suitability trend value;

[0019] S103: Call the water suitability trend value, jointly obtain the road distribution information and water conservancy facility layout data within the plot range, calculate the road accessibility value and the supply service degree coefficient according to the facility density, road accessibility, and their coincidence ratio with the main soil area, respectively establish the supply accessibility capacity level identifier, integrate the level identifier and the water suitability trend value for zoning and classification judgment, and obtain the plot utilization characteristic classification result.

[0020] As a further solution of the present invention, the steps for obtaining the plot classification matching distribution result are:

[0021] S201: Based on the plot utilization characteristic classification result, identify the soil attribute category value of each plot, call the soil distribution layer and plot coding information matched by each type of plot, aggregate and extract the corresponding soil type data according to the plot number, and screen the soil category according to the existing relationship between soil type and functional suitability, match the functional areas suitable for agriculture, construction, and ecological protection, and generate the land functional suitability zoning value;

[0022] S202: Call the land function suitability zoning value, combine it with the annual temperature, precipitation, and humidity meteorological data sequences corresponding to the plot location, extract the annual average temperature, annual average precipitation, and the deviation value of the extreme temperature within the year, judge the climate stability of each plot under long-term conditions, and use the formula:

[0023]

[0024] where S c represents the climate adaptability index value of the plot, T y represents the annual average temperature corresponding to the plot, P y represents the annual average precipitation of the plot, σ y represents the variance of the extreme temperature within the year of the plot, D yk represents the monthly average temperature deviation value in the kth year, H yk represents the monthly humidity deviation value in the kth year, and y represents the total sample quantity of the selected number of years;

[0025] Obtain the climate adaptability index value through calculation, and conduct a combined comparison with the soil type to obtain the matching characteristics of the plot under the multi-year average climate background, and establish the climate stability adaptability value;

[0026] S203: Call the climate stability adaptability value, combine and extract the road, water conservancy, and power facility layout layers corresponding to each plot, calculate the road accessibility, water resource guarantee degree, and power connection rate according to the supporting requirement conditions under each land use type, conduct a functional adaptability comparison with the stability value obtained in the previous sub-step respectively, and then adjust the classification of the edge plot attributes by analyzing the consistency degree between the plot boundary and the surrounding use boundaries to generate the plot classification matching distribution result.

[0027] As a further solution of the present invention, the steps for obtaining the plot terrain adaptability distribution result are as follows:

[0028] S301: Based on the plot classification matching distribution result, screen the elevation, slope, and water system distribution data of each plot in the area, extract the elevation grid value and calculate the average elevation difference within each plot, obtain the slope grid and generate the maximum slope value, overlay the water system distribution layer, extract the minimum distance value from the water body, judge the adaptability level of each plot under the current use, and mark the areas that do not meet the conditions to generate the terrain constraint identification value;

[0029] S302: Call the terrain constraint identification value, analyze the elevation position of the local lowest point and the terrain closed range within the plot, identify the catchment area unit, obtain the average slope, total drainage direction convergence degree, water body confluence cumulative amount, soil permeability coefficient, and surface cover type within this range, and use the formula:

[0030]

[0031] Among them, R d represents the difference value of drainage smoothness, Q w represents the cumulative water flow value of the water catchment area, F p represents the average slope value within the water catchment area, S s represents the soil permeability coefficient, represents the sum of drainage impedance indexes under z different surface cover types, P c is the water permeability level of the c-th type of surface, L c is the thickness and density parameter of the c-th type of surface, K v is the set drainage efficiency reference value;

[0032] Calculate to obtain the difference value of drainage smoothness, compare it with the set drainage efficiency reference value, and combine with the existing uses for use adjustment to obtain the drainage adaptability grade value of the plot;

[0033] S303: Call the drainage adaptability grade value of the plot, summarize the plots for construction and agriculture, count the distribution characteristics of the terrain and drainage index grades corresponding to each use type, establish an adaptability grade coding matrix according to the plot number, and perform statistical analysis based on the constraint grade distribution value of each type of plot under the current use, and redefine the original use label as a compatible use or an ecological use to generate the terrain adaptability distribution result of the plot.

[0034] As a further solution of the present invention, the steps for obtaining the optimized distribution result of the plot use type are:

[0035] S401: Based on the terrain adaptability distribution result of the plot, extract the vector boundaries and use attribute information of the agricultural, construction, and ecological use plots, calculate the boundary area, shape compactness, and use distribution continuity of each use category within the overall area range, obtain the minimum spacing value between continuously distributed plots, and count the number of plots in each cell to generate the use aggregation density value;

[0036] S402: Call the use aggregation density value, mark the area where the cell density value is greater than the upper threshold as a high-density block, perform cross-statistics on the use types therein, identify the use conflicts of the plots with different uses in the same cell, and use the formula:

[0037]

[0038] Among them, C u represents the use conflict interference value, U ag 、U ck respectively represent the use identification codes of the use types a and c of the plots in the area, Dag , D ck represents the relative spacing between plots of this use type, S ab , S cd represents the spatial floor area of the corresponding plot, B e represents the use boundary intersection index of the e-th boundary unit. g, h, k, t, and w respectively represent the number of plots of use type a, the number of their areas, the number of plots of use type c, the number of their areas, and the total number of intersection boundary units;

[0039] Calculate the use conflict interference value through operations, adjust the use unity of the areas where the conflict value is greater than the set conflict threshold, and obtain the use conflict distribution level value;

[0040] S403: Call the use conflict distribution level value, extract the use attributes of its adjacent patches and analyze the use consistency ratio, perform use fusion matching on the use of this plot, preferentially select the type that is consistent with the use of the largest adjacent area around, re-code the use and then merge it into the same use layer according to the number, establish an updated use space layer, and generate the optimized distribution result of the plot use type.

[0041] As a further solution of the present invention, the steps for obtaining the land use area adjustment result are:

[0042] S501: Based on the optimized distribution result of the plot use type, obtain the boundary shape, area value and adjacency relationship of each type of use type, calculate the ratio of the plot area to the average area of the use area, and extract the number of adjacent plots and the number of adjacent use types of the plot, identify the degree of deviation in use configuration, and establish the use distribution dispersion value;

[0043] S502: According to the use distribution dispersion value, extract the areas where the uses are relatively dense in the spatial layout, identify the continuous use concentration blocks, calculate the degree of concentration of the same use in space, extract the two types of intersection areas as the structural adjustment area units, and obtain the layout structure imbalance section;

[0044] S503: Call the plot unit area, use aggregation level, use dispersion coefficient, spatial offset distance and adjacency coordination level in the layout structure imbalance section, construct a priority evaluation model for reconfiguring the plot use structure, and use the formula:

[0045]

[0046] Among them, A gs,k represents the area of the k-th plot area, L ua,k represents the use aggregation level of this plot, D dc,k represents the use distribution dispersion coefficient, O cv represents the spatial offset value of the current plot, Represents the offset average value of all plots, H lc,k Represents the adjacent use coordination level, Q represents the number of plots participating in use reconstruction in the structurally unbalanced section, and k is the index number;

[0047] Perform operations to obtain the priority value of use structure reconfiguration. Sort according to the priority value and adjust the contact relationship between the uses in the high-priority area and the boundary. Execute use reconstruction and boundary replacement to generate the land use area adjustment result.

[0048] A land use optimization system based on big data, the system includes:

[0049] The data collection and classification module obtains soil quality data, climate condition data, infrastructure distribution data and topographic and geomorphic information, classifies based on soil particle composition, drainage capacity, nutrient content, screens precipitation and evaporation characteristics, identifies seasonal change trends, analyzes the distribution of roads and water conservancy facilities, judges accessibility and supply capacity, integrates various data, classifies land use attributes, and generates the classification result of plot use characteristics;

[0050] The land use matching module, based on the classification result of the plot use characteristics, identifies soil categories, extracts areas suitable for agriculture, construction, and ecological protection, analyzes climate adaptability, judges the stability of different plots under long-term environmental conditions, evaluates the suitability of roads, water conservancy, and power facilities for different land uses, matches land use types, adjusts the boundary area, and generates the classification matching distribution result of plots;

[0051] The terrain adaptation analysis module, based on the classification matching distribution result of the plots, screens the terrain change characteristics, judges the impact of elevation, slope, and water system distribution on land use, adjusts the use classification for areas where the slope value exceeds the land development standard, calculates the drainage smoothness index for catchment areas, conducts waterlogging risk assessment for low-lying plots, adjusts the use of plots where the waterlogging risk index exceeds the set risk threshold, counts the terrain adaptation information, and generates the terrain adaptation distribution result of plots;

[0052] The spatial optimization and adjustment module, based on the terrain adaptation distribution result of the plots, analyzes the spatial distribution characteristics of agricultural, construction, and ecological use plots, screens the plot density, identifies high-density areas, judges whether there are use conflicts, readjusts the plots with scattered use distribution, and retrieves the use relationship of adjacent plots to optimize the plot use configuration and generate the optimized distribution result of plot use types;

[0053] The land use structure evaluation module, based on the optimized distribution result of the plot use types, evaluates the overall land use structure, analyzes the spatial coordination of each type of plot, screens the boundary connection situation, adjusts the areas with unreasonable use division, optimizes the functional matching between plots, corrects the over-dispersed or concentrated layout, and generates the land use area adjustment result.

[0054] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0055] In the present invention, by comprehensively analyzing soil quality, climate conditions, infrastructure distribution, and topographic and geomorphic information, the accuracy of land classification is improved, ensuring the comprehensiveness of data integration. According to soil characteristics and long-term environmental changes, the matching of land use is optimized, improving the scientific nature of resource allocation. Combining the characteristics of terrain changes, the drainage conditions are optimized, reducing the risk of waterlogging and enhancing the land suitability. The spatial distribution is adjusted, the density of land use is optimized, reducing land use conflicts, and improving the rationality of the land spatial structure. Overall, the connection of land boundaries, the matching of functions, and the rationality of layout are optimized, improving the coordinated allocation ability of land resources. By comprehensively applying multi-source data fusion, spatial modeling, and dynamic optimization strategies, the land use pattern becomes more refined, improving land use efficiency and sustainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0057] Figure 1 is the flowchart of the method of the present invention;

[0058] Figure 2 is the flowchart for obtaining the classification result of the land use characteristics of the plots of the present invention;

[0059] Figure 3 is the flowchart for obtaining the classification matching distribution result of the plots of the present invention;

[0060] Figure 4 is the flowchart for obtaining the terrain adaptation distribution result of the plots of the present invention;

[0061] Figure 5 is the flowchart for obtaining the optimized distribution result of the land use types of the plots of the present invention;

[0062] Figure 6 is the flowchart for obtaining the land use area adjustment result of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] The following will describe the technical solutions in the present invention with reference to the drawings.

[0064] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or designs. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0065] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0066] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0067] To make the technical problems to be solved, technical solutions and advantages of the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0068] Please refer to Figure 1 , the present invention provides a technical solution: a method for optimizing land use based on big data, including the following steps:

[0069] S1: Obtain the soil quality data, climate condition data, infrastructure distribution data, and topographical and geomorphic information of the plot, classify according to soil particle composition, drainage capacity, and nutrient content, screen precipitation and evaporation characteristics, identify seasonal change trends, analyze the distribution of roads and water conservancy facilities, judge accessibility and supply capacity, integrate various data, classify land use attributes, and generate the classification result of plot use characteristics;

[0070] S2: Based on the classification result of plot use characteristics, identify soil types, extract areas suitable for agriculture, construction, and ecological protection, analyze climate adaptability, judge the stability of different plots under long-term environmental conditions, evaluate the adaptability of roads, water conservancy, and power facilities to different land uses, match land use types, adjust boundary areas, and generate the classification matching distribution result of plots;

[0071] S3: Based on the distribution results of plot classification matching, screen the characteristics of terrain changes, judge the impacts of elevation, slope, and water system distribution on land use, adjust the utilization types of steep or low-lying slope areas, identify catchment areas, judge the drainage smoothness, adjust the land use of plots with waterlogging risks exceeding the risk threshold, count the terrain adaptation information, and generate the terrain adaptation distribution results of plots;

[0072] S4: Based on the terrain adaptation distribution results of plots, analyze the spatial distribution characteristics of agricultural, construction, and ecological use plots, screen the plot density, identify high-density areas, judge whether there are use conflicts, readjust the plots with scattered use distributions, and retrieve the use relationships of adjacent plots to optimize the plot use configuration and generate the optimized distribution results of plot utilization types;

[0073] S5: Based on the optimized distribution results of plot utilization types, evaluate the overall land use structure, analyze the spatial coordination of each type of plot, screen the boundary connection conditions, adjust the areas with unreasonable use divisions, optimize the functional matching between plots, correct the overly scattered or concentrated layouts, and generate the land use area adjustment results.

[0074] The plot utilization feature classification results include soil type, precipitation characteristics, evaporation characteristics, infrastructure accessibility, and land use attributes; the plot classification matching distribution results include agricultural land matching areas, construction land matching areas, ecological protection land matching areas, and infrastructure adaptability; the terrain adaptation distribution results of plots include elevation distribution, slope characteristics, water system impacts, drainage capacity, and waterlogging risk areas; the optimized distribution results of plot utilization types include land use spatial distribution, use density, use conflict areas, and optimized use configuration plans; the land use area adjustment results include land use structure optimization, spatial coordination adjustment, boundary connection optimization, functional matching correction, and layout rationality adjustment.

[0075] Please refer to Figure 2 , and the steps for obtaining the plot utilization feature classification results are as follows:

[0076] S101: Obtain the data of soil particle composition, drainage capacity, and nutrient content of plots, conduct particle size level division based on the sand particle ratio, clay particle ratio, and silt particle ratio in the soil particle composition, call the drainage capacity and nutrient content data for comparison, calculate the mean values of drainage capacity and nutrient content under different particle size structures respectively, and divide different soil type categories according to the mean value thresholds to obtain the soil attribute category values;

[0077] Obtain the data of soil particle composition, drainage capacity and nutrient content of the plot. First, based on the remote sensing patches or plot zoning numbers, match the coordinates of the sampling points with the plot numbers, extract the soil particle composition data of each sampling point item by item, and calculate the three-phase ratio, that is, the percentage content of sand, silt and clay, to form a soil three-phase composition vector. For example, if the composition of a plot sample A is 60% sand, 25% silt and 15% clay, it is classified as sandy loam type. For the collection of drainage capacity parameters, obtain the infiltration rate data through a ground infiltration instrument, with the unit of mm / h. Suppose the infiltration rate at point A is 15 mm / h. Combine the nutrient content detection to obtain the nitrogen, phosphorus and potassium contents and convert them to a unified unit of mg / kg. For example, the nitrogen content is 120 mg / kg, phosphorus is 45 mg / kg, and potassium is 88 mg / kg. Synthesize the nutrient scoring factor according to the ratio. After normalization processing, the scoring factor enters the next classification judgment. Map the above three types of parameters to the standard interval thresholds respectively. For example, an infiltration rate less than 8 mm / h is classified as "poor" drainage capacity, 8 - 20 as "medium", and greater than 20 as "good". The above point A is 15 mm / h, corresponding to the "medium" grade; for the nutrient content, use K-means clustering to divide it into 3 types of intervals, and point A is classified into the medium nutrient grade; based on the above results, classify and attribute the soil types of the sample points, form a soil type distribution map in space, and then integrate the attributes of each classification area to finally form the soil attribute category value.

[0078] S102: Call the soil attribute category value, jointly obtain the precipitation data and evaporation data of the plot, statistically count the annual data change frequencies according to the daily scale and monthly scale respectively, calculate the daily average change rate, monthly fluctuation range and range value of precipitation and evaporation, and use the formula:

[0079]

[0080] where, P i represents the precipitation on the i-th day, E i represents the evaporation on the i-th day, n is the number of days participating in the statistics, P j , E j represent the precipitation and evaporation in the j-th month, m is the number of months participating in the statistics, μ represents the average value on the monthly scale, min k (P k +E k ) represents the sum of the minimum precipitation and evaporation on a certain day in the whole year;

[0081] Operate to obtain the water dynamic trend value, and combine it with the plot soil type for combined judgment, establish the water response difference comparison result, and obtain the water suitability trend value;

[0082] Call the soil property category values and jointly obtain the precipitation and evaporation data of the plot. First, divide the area into different analysis units according to the soil classification results. For a sandy loam area, set the continuous observation period to 10 days, and extract the corresponding daily precipitation data P in this area. i And evaporation data E i , and assume the actual monitoring data for 10 days are as follows:

[0083] Precipitation P i (Unit: mm): 4.2, 3.5, 6.1, 5.0, 2.8, 3.9, 5.6, 4.7, 3.2, 4.0;

[0084] Evaporation E i (Unit: mm): 2.5, 3.1, 5.0, 3.8, 2.4, 2.9, 4.3, 4.1, 2.7, 3.6;

[0085] Calculate the daily water volume difference P i -E i :

[0086] 4.2 - 2.5 = 1.7;

[0087] 3.5 - 3.1 = 0.4;

[0088] 6.1 - 5.0 = 1.1;

[0089] 5.0 - 3.8 = 1.2;

[0090] 2.8 - 2.4 = 0.4;

[0091] 3.9 - 2.9 = 1.0;

[0092] 5.6 - 4.3 = 1.3;

[0093] 4.7 - 4.1 = 0.6;

[0094] 3.2 - 2.7 = 0.5;

[0095] 4.0 - 3.6 = 0.4;

[0096] Obtain the moisture difference sequence:

[0097] 1.7, 0.4, 1.1, 1.2, 0.4, 1.0, 1.3, 0.6, 0.5, 0.4;

[0098] Calculate the average value:

[0099]

[0100] Extract the total annual precipitation and evaporation in this area for 12 months, which are respectively:

[0101] Precipitation P j (Unit: mm): 105.0, 120.3, 98.7, 115.6, 123.0, 132.5, 128.4, 117.6, 108.3, 99.2, 112.0, 125.7;

[0102] Evaporation E j (Unit: mm): 96.0, 110.5, 93.1, 105.8, 117.5, 124.3, 120.6, 109.8, 101.2, 94.6, 106.7, 119.4;

[0103] Calculate the monthly ratio R j =P j / E j :

[0104] 105.0 / 96.0 = 1.0938;

[0105] 120.3 / 110.5 = 1.0888;

[0106] 98.7 / 93.1 = 1.0602;

[0107] 115.6 / 105.8 = 1.0927;

[0108] 123.0 / 117.5 = 1.0468;

[0109] 132.5 / 124.3 = 1.0659;

[0110] 128.4 / 120.6 = 1.0647;

[0111] 117.6 / 109.8 = 1.0709;

[0112] 108.3 / 101.2 = 1.0701;

[0113] 99.2 / 94.6 = 1.0486;

[0114] 112.0 / 106.7 = 1.0497;

[0115] 125.7 / 119.4 = 1.0528;

[0116] Calculate the mean μ:

[0117]

[0118] Calculate the approximate value of the squared deviation between each ratio and the mean: (1.0938 - 1.0637) 2 = 0.00091;

[0119] (1.0888 - 1.0637) 2 = 0.00063;

[0120] (1.0602 - 1.0637) 2 = 0.00001;

[0121] (1.0927 - 1.0637) 2 = 0.00084;

[0122] (1.0468 - 1.0637) 2 = 0.00029;

[0123] (1.0659 - 1.0637) 2 = 0.00000;

[0124] (1.0647 - 1.0637) 2 = 0.00000;

[0125] (1.0709 - 1.0637) 2 = 0.00005;

[0126] (1.0701 - 1.0637) 2 = 0.00004;

[0127] (1.0486 - 1.0637) 2 = 0.00023;

[0128] (1.0497 - 1.0637) 2 = 0.00020;

[0129] (1.0528 - 1.0637) 2 = 0.00012;

[0130] The sum of squared deviations is:

[0131]

[0132] Taking the square root gives:

[0133]

[0134] Then find the minimum value of the sum of precipitation and evaporation throughout the year. Assume the 236th day is the minimum value, with precipitation of 0.2 mm and evaporation of 0.3 mm. Then:

[0135] min(P k + E k ) = 0.2 + 0.3 = 0.5 mm;

[0136] Substitute into the formula:

[0137] T v = |0.86 + 0.0657 - 0.5| = |0.4257| = 0.4257;

[0138] The obtained moisture dynamic trend value is 0.4257. According to the regional hydrological analysis, the suitable range for sandy loam is set at 0.6, 1.8. Since the current result is lower than the lower limit of the range, it is determined to be "low". Therefore, the moisture suitability trend value for this unit is "low".

[0139] The results show that the moisture dynamic trend value of 0.4257 indicates that there is an obvious gap between precipitation and evaporation in this plot under the current climatic conditions. The moisture balance state is weak, the annual fluctuation level is low, and there is an extremely minimum water volume day, making it difficult to meet the needs of conventional crops.

[0140] S103: Invoke the moisture suitability trend value, jointly obtain the road distribution information and water conservancy facility layout data within the plot range, calculate the road accessibility value and the supply service degree coefficient according to the facility density, road accessibility and their coincidence ratio with the main soil area, respectively establish the supply accessibility capacity level identifier, integrate the level identifier and the moisture suitability trend value for zoning and classification judgment, and obtain the plot utilization characteristic classification result;

[0141] Call the moisture suitability trend value, jointly obtain the road distribution and water conservancy facility layout data within the plot, perform vector extraction and spatial rasterization processing on the road layer, and count the coverage rate of the road length per square kilometer, that is, the road density. For example, if the total road length within 1 square kilometer in area X is 2.8 km, then the road density is 2.8 km / km2. At the same time, extract the connection length between the main road and the plot, calculate the total length of the plot access path and convert it into an access index. Assuming the distance to the main road is 1.2 km, the access index can be set as 1 / 1.2 = 0.83. Then, code and label the water conservancy facilities, and count the number of water source points per unit area. Assuming a plot has 3 water wells and 2 sprinkler irrigation devices, with a total of 5 facilities and an area of 1.5 km2, the facility density is 5 / 1.5 = 3.33 items / km2. Divide the grades according to the road density and facility density respectively. Assume that the road density lower than 1 km / km2 is low grade, 1 - 3 is medium grade, and above 3 is high grade. The threshold for dividing the access index is: <0.5 is low, 0.5 - 1 is medium, >1 is high; the water conservancy facility density is divided into: <2 is low, 2 - 4 is medium, >4 is high. Associate the above grade labels with the moisture suitability trend value for composite judgment. For example, the moisture suitability trend value in plot X is 1.91, corresponding to the medium grade. If the road grade is medium and the water conservancy facility grade is medium, then generate a composite label of "medium-medium-medium". Match this label with the established land use type database, and the corresponding type is "dry farming agricultural area". Finally, output the plot utilization characteristic classification result of this area.

[0142] Please refer to Figure 3 , the steps to obtain the plot classification matching distribution result are as follows:

[0143] S201: Based on the plot utilization characteristic classification result, identify the soil attribute category values of each plot, call the soil distribution layer and plot coding information matched by each type of plot, aggregate and extract the corresponding soil type data according to the plot number, and screen the soil categories according to the existing relationship between soil type and functional suitability, match the functional areas suitable for agriculture, construction, and ecological protection, and generate the land functional suitability zoning value;

[0144] Based on the classification results of plot utilization characteristics, identify the soil attribute category values corresponding to each plot. First, spatially overlay the obtained plot utilization characteristics classification results with the regional soil attribute distribution layer, and call the soil attribute information corresponding to each plot code one by one. Match the soil type according to the plot number index. For example, if the plot A is numbered X001, the matched soil attribute is loamy clay, and the corresponding soil particle composition ratio is 32% for sand, 45% for silt, and 23% for clay. After extracting this data, aggregate and summarize each plot, divide all plots into several groups according to the soil attribute labels. Subsequently, call the corresponding functional suitability matching relationships of various soils in existing research or standards. For example, loamy clay is suitable for rice cultivation and ecological conservation, sandy loam is suitable for dry farming and some construction areas, and heavy clay areas are preferentially classified for ecological protection purposes. Screen the functional uses of each group of soil attributes and set the attribute function matching matrix. The matrix content is as follows: If the soil attribute corresponding to a certain plot is X and its functional suitability value is 1, then classify this plot into the functional use candidate area. For example, if the functional suitability matrix corresponding to sandy loam plot B is Agriculture = 1, Construction = 1, Ecological Protection = 0, it can be classified into the areas suitable for agriculture and construction. Finally, assign functional suitability labels according to the plot numbers and generate the results; this process ultimately obtains the land functional suitability zoning value.

[0145] S202: Call the land functional suitability zoning value, combine it with the annual temperature, precipitation, and humidity meteorological data series corresponding to the plot location, extract the annual average temperature, annual average precipitation, and the deviation value of the extreme temperature within the year, and judge the climate stability of each plot under long-term conditions. Use the formula:

[0146]

[0147] where, S c represents the climate adaptability index value of the plot, T y represents the annual average temperature corresponding to the plot, P y represents the annual average precipitation of the plot, σ y represents the variance of the extreme temperature within the year of the plot, D yk represents the monthly average temperature deviation value in the kth year, H yk represents the monthly humidity deviation value in the kth year, and y represents the total number of years of the selected sample;

[0148] Calculate the climate adaptability index value through operations, and make a joint comparison with the soil type to obtain the matching characteristics of the plot under the multi-year average climate background, and establish the climate stability adaptability value;

[0149] Call the appropriate zoning values of land functions, jointly obtain the annual average temperature, annual average precipitation and annual extreme temperature data series of each plot year by year within a 10-year cycle, extract the monitoring data of climate observation stations within the grid range where each type of plot is located, and set the annual average temperature series of the area where plot C is located within 10 years as:

[0150] T y ={13.2, 13.4, 13.6, 13.3, 13.7, 13.5, 13.4, 13.6, 13.8, 13.5} (unit: °C), and the annual average precipitation series is:

[0151] P y ={850, 870, 860, 855, 880, 870, 865, 875, 890, 860} (unit: mm),

[0152] Then the annual average temperature of the corresponding plot is T y = 13.5, and the annual average precipitation is P y = 867.5. Then extract the annual extreme temperature records, set as: {41.2, 40.5, 42.1, 40.7, 41.0, 41.6, 40.9, 41.3, 42.0, 41.1}, and calculate its variance to get:

[0153]

[0154] Take the square root to get:

[0155] Then extract the annual average temperature deviation value D yk and the humidity deviation value H yk , for example:

[0156] D yk ={0.2, -0.1, 0.3, -0.2, 0.2, 0.1, -0.1, 0.3, 0.4, 0.0};

[0157] H yk ={5, 3, 6, 2, 4, 5, 3, 6, 7, 4};

[0158] After performing the multiplication operation, we get:

[0159]

[0160]

[0161] Then find the average:

[0162]

[0163] Substitute the above data into the formula:

[0164]

[0165] This is the climate adaptability index value of the plot. The larger the value, the more stable the average climate configuration of the plot under stable climate conditions, and the lower the impact of extreme fluctuations and humidity offsets within the year. After comparison with the preset range, if the climate adaptability index value is between 1500 and 2000, it is classified as the "suitable" level. Therefore, the value here can be marked as the suitable level, and then matched and integrated with the soil suitability zoning value to output the climate stability adaptability value of the plot.

[0166] The results show that the climate adaptability index value of 1782.63 indicates that the plot has a high level of temperature and humidity stability, small extreme temperature fluctuations, and weak humidity variability in the past 10 years, and is suitable for agriculture and ecological uses that are sensitive to climate conditions. As a calculated quantitative indicator, it is directly used to derive the climate stability adaptability level of the plot and serves as the core input value in subsequent land use matching processes.

[0167] S203: Call the climate stability adaptability value, jointly extract the layout layers of roads, water conservancy, and power facilities corresponding to each plot, calculate the road accessibility, water resource guarantee degree, and power connection rate according to the supporting requirement conditions under each land use type, respectively compare the functional adaptability with the stability value obtained in the previous sub-step, and then adjust the classification of the edge plot attributes by analyzing the consistency degree between the plot boundary and the surrounding use boundaries to generate the plot classification matching distribution result;

[0168] Call the climate stability adaptability value, jointly with the data of the road, water conservancy, and power facility layers matched by each plot, extract the coverage rate or connection degree information of each type of facility within a single plot, and calculate the adaptability indicators of each type of facility respectively. Among them, the road accessibility is calculated by the ratio of the total road length to the plot area. If the area of plot D is 1.5 square kilometers and the total road length is 4.2 kilometers, the road accessibility is 2.8 km / km 2 , the water resource guarantee degree is measured by the number of water source points per square kilometer. If there are 3 water source points, the density is 2.0 points / km 2 , the power connection rate is statistically calculated by the proportion of whether the access points of the power backbone network are accessed and the number of access points. Assuming that 3 out of 5 access points are accessed, the connection rate is 60%. Set the corresponding threshold ranges for the above 3 types of facility indicators according to the land use requirements. For example, for agricultural use, the requirements are accessibility ≥ 2.0 km / km 2 and water resource guarantee degree ≥ 1.5 points / km 2, the power connection rate ≥ 50%. If the corresponding indicators of plot D are all met, the plot can be classified as an agricultural adaptation type. Subsequently, the matching degree between the plot boundary and the uses of surrounding plots is judged. If the land use type of the adjacent area is a mixed construction and ecological area, and the boundary coincidence rate is 55%, which is lower than the set boundary consistency threshold of 65%, then adjust the boundary attributes of part of the plot to the mixed use label, update its classification label, and obtain the plot classification matching distribution result.

[0169] Please refer to Figure 4 , and the steps for obtaining the terrain adaptation distribution result of the plot are as follows:

[0170] S301: Based on the plot classification matching distribution result, screen the elevation, slope and water system distribution data of each plot in the area, extract the elevation grid value and calculate the average elevation difference within each plot, obtain the slope grid and generate the maximum slope value, overlay the water system distribution layer, extract the minimum distance value from the water body, judge the adaptation level of each plot under the current use, and mark the areas that do not meet the conditions to generate the terrain constraint identification value;

[0171] Based on the plot classification matching distribution result, extract the elevation, slope and water system layer data of each plot. First, perform a clipping operation with the plot boundary range, project the DEM elevation data to the same resolution grid, extract the maximum elevation, minimum elevation and average elevation within each plot, and calculate the elevation difference through the difference between the maximum value and the minimum value. For example, the highest point of plot A is 132 meters and the lowest point is 112 meters, then the elevation difference is 20 meters, corresponding to the elevation change range of this plot exceeding the elevation tolerance threshold of 15 meters for agricultural land. Subsequently, aggregate the plot grid slope values to obtain the maximum slope value and average value. If the maximum slope value is 11.3°, which has exceeded the upper limit of the set slope adaptation range of 7°, it is initially judged as unsuitable for agricultural construction use. Then extract the shortest distance from each plot to the nearest water body from the water system vector data. For example, the shortest distance between plot A and the river is 63 meters, and perform joint normalization processing with elevation and slope. After unifying the values to the 0-1 interval using the standard deviation normalization method and setting a threshold, if the normalized elevation is greater than 0.8, the slope is greater than 0.75, and the water body distance is less than 0.2, it is marked as a terrain sensitive area. Finally, identify the boundary area that needs to adjust the use and assign it a terrain constraint level mark to obtain the terrain constraint identification value.

[0172] S302: Invoke the terrain constraint identification value, analyze the elevation position of the local lowest point and the terrain closed range within the plot, identify the catchment area unit, obtain the average slope, total drainage direction convergence, water body confluence accumulation, soil permeability coefficient and surface cover type within this range, and use the formula:

[0173]

[0174] Among them, R d represents the difference value of drainage smoothness, Q w represents the cumulative water flow value of the water catchment area, F p represents the average slope value within the water catchment area, S s represents the soil permeability coefficient, represents the sum of drainage impedance indicators under z different surface cover types, P c is the moisture permeability level of the c-th type of surface, L c is the thickness density parameter of the c-th type of surface, K v is the set drainage efficiency benchmark value;

[0175] Calculate to obtain the difference value of drainage smoothness, compare it with the set drainage efficiency benchmark value, and adjust the use in combination with the existing use to obtain the drainage adaptability level value of the plot;

[0176] Call the terrain constraint identification value, identify the water catchment area and drainage capacity characteristics of each plot. For the plots marked with a relatively high terrain constraint level, sequentially extract their lowest elevation positions, extract the terrain closed area within three orders of magnitude through the position of the low-lying point in the elevation grid, regard this area as a single water catchment unit, and extract the average slope, total number of convergence directions, cumulative runoff value, soil permeability coefficient and surface type of this unit. Taking plot B as an example, the observation results are as follows: the average slope is 6.4 degrees, the total number of convergence directions is 8, the cumulative flow is 210 cubic meters, the soil permeability coefficient is 9.8, and the surface type consists of three types, namely bare land, cultivated land and concrete grassland, and their corresponding moisture permeability levels are 0.3, 0.6, 0.8 respectively, and the thickness density parameters are 1.4, 1.1, 1.3 respectively. Substitute each parameter into the formula:

[0177]

[0178] Substitute the values into:

[0179]

[0180] According to the result R d = 24.76, which is significantly higher than the set waterlogging risk control threshold of 0.25. Therefore, plot B is identified as an area with good drainage conditions and there is no need to change its use, and its current use is retained. This value is the difference value of drainage smoothness, which is used to measure the drainage capacity of the water catchment area under the existing slope, water flow and surface permeability conditions. The higher this value, the stronger the drainage capacity, and the less likely the water catchment is to gather and generate the risk of surface runoff. This value will be compared with the set drainage benchmark value. If it is lower than the threshold, it will be marked as "waterlogging risk", and if it is higher, it will be marked as "suitable". Currently, it is in a higher state.

[0181] The results show that Plot B has excellent drainage capacity in terms of structural drainage conditions and there is no possibility of water retention. Therefore, the current use can be maintained in land use, and its drainage adaptation level is marked as "suitable". By jointly structuring slope, water flow, surface impedance and soil permeability characteristics, the drainage potential of the plot can be quantitatively responded to, and the structural identification of terrain adaptability can be achieved without introducing complex simulation tools.

[0182] S303: Retrieve the drainage adaptation level values of the plots, summarize the plots for construction and agricultural uses, count the distribution characteristics of terrain and drainage index levels corresponding to each use type, establish an adaptation level coding matrix according to the plot numbers, and conduct statistical analysis based on the constraint level distribution values of each type of plot under the current use. Reset the original use labels to compatible uses or ecological uses, generate the terrain adaptation distribution results of the plots;

[0183] Retrieve the drainage adaptation level values of the plots, aggregate the samples of plots with agricultural and construction uses, form a two-dimensional matrix of the terrain constraint levels and drainage adaptation levels of the plots corresponding to each use, and conduct a summary statistics of all the plots in the matrix with the use as the first dimension and the level combination as the second dimension. Suppose there are 500 plots in the agricultural use plots, among which 180 plots meet the terrain constraint level ≤ 1 and the drainage adaptation level = suitable, 230 plots have the terrain constraint level = 2 but the drainage level = suitable, and 90 plots have the terrain constraint level = 3 and the drainage level = unsuitable. Then the adaptation ratios of the three categories are 36%, 46%, and 18% respectively. Among them, 18% is higher than the set adaptation critical value of 15%. Therefore, the system marks the uses of these 90 plots as re-adjustment units, re-match the compatible use labels, such as ecological restoration, under-forest utilization, etc. After updating the plot use codes, merge them with the surrounding use boundaries in the order of the numbers to determine whether they form a transition boundary or an isolated point area. If the adjacent use difference rate is less than 35%, they can be merged and attributed to the adjacent main use. Finally, establish an updated use classification structure table and output the terrain adaptation distribution results of the plots.

[0184] Please refer to Figure 5 , the steps to obtain the optimized distribution results of plot use types are as follows:

[0185] S401: Based on the terrain adaptation distribution results of the plots, extract the vector boundaries and use attribute information of agricultural, construction, and ecological use plots, calculate the boundary area, shape compactness, and use distribution continuity of each use category within the overall area, obtain the minimum spacing value between continuously distributed plots, count the number of plots in each cell, and generate the use aggregation density value;

[0186] Plots of different use types are divided into three categories: agricultural, construction, and ecological. Extract the corresponding vector boundaries for each category and obtain their area, shape index, and spatial continuity parameters. First, process the plots under agricultural use, extract their circumscribed boundaries, and calculate the shape compactness index, which is measured by the ratio of the area to the minimum circumscribed rectangle. If the area of plot A is 9,500 square meters and the area of the minimum enclosing rectangle is 12,200 square meters, then the compactness is 9,500 / 12,200 ≈ 0.778, indicating that its shape is relatively complete. Subsequently, a grid unit of 200 meters × 200 meters is defined within the entire study area, and the number of plots contained in each grid cell is counted. After counting the aggregation of agricultural use grid cells, it is found that the number of plots in 12 grid cells exceeds 10. Set the spatial density threshold to 10 plots / cell and define the dense area. Repeat the above operations for construction use and ecological use respectively to obtain the aggregation indicators corresponding to each use and uniformly encode them into the attribute fields, and finally form a marked field for subsequent conflict identification and processing to obtain the use aggregation density value.

[0187] S402: Call the use aggregation density value, mark the area where the cell density value is greater than the upper threshold as a high-density block, and conduct cross-statistics on the use types therein. Identify the use contradictions for the plots with different use types in the same cell. Use the formula:

[0188]

[0189] Among them, C u represents the use conflict interference value, U ag , U ck respectively represent the use identification codes of use type a and use type c for the plots in the area, D ag , D ck represent the relative spacing between the plots of this use type, S ab , S cd represent the spatial floor areas of the corresponding plots, B e represents the use boundary intersection index of the e-th boundary unit. g, h, k, t, and w respectively represent the number of plots of use a, the number of their areas, the number of plots of use c, the number of their areas, and the total number of intersection boundary units;

[0190] Calculate the use conflict interference value through operations, and adjust the use unity for the areas where the conflict value is greater than the set conflict threshold to obtain the use conflict distribution level value;

[0191] Identify all grid cells with aggregation density values greater than the threshold, mark them as high-density use blocks, extract their use compositions cell by cell. If grid number X001 contains 6 agricultural plots, 4 ecological plots, and 2 construction plots, it indicates the existence of a mixed-use area. Conduct coding processing on the use composition, assign code 1 to agriculture, code 2 to ecology, and code 3 to construction respectively, and assign combined values to their spacing and area according to the plots. At the same time, count the areas within the grid where use boundaries intersect, and define the boundary intersection index as the ratio of the shared boundary length between adjacent plots of different uses to their average side length. Suppose the average side length of agricultural plots within grid X001 is 36 meters, and the total shared boundary with ecological plots is 112 meters, then its boundary intersection index is 112 / 36≈3.11;

[0192] Hypothesis: U ag = 1,1, corresponding to the use codes of two agricultural plots, D ag = 18,25, representing the spacing between them, S ab = 420,380, representing the area; U ck = 2,2, the use code of the ecological plot, D ck = 20,21, the spacing; S cd = 410,370, the area; B e = 3.11,2.85, are the intersection indices at two different boundary positions.

[0193] The calculation is as follows:

[0194] The first part:

[0195]

[0196] The difference is:

[0197] |0.05375 - 0.1051| = 0.05135;

[0198] The second part:

[0199]

[0200] The total value:

[0201] C u = 0.05135 + 2.98 = 3.03135;

[0202] The results show that the use conflict interference value of grid X001 is 3.03135, which has significantly exceeded the preset conflict threshold of 1.5. This value not only reflects the overlap of different use types in terms of distribution density and spatial location within the region, but also quantifies the structural mixing degree between use boundaries through the boundary intersection index. Therefore, it can be determined that there is serious interference in the spatial use of this region.

[0203] S403: Call the grade value of the conflict distribution of land uses, extract the land use attributes of its adjacent patches and analyze the consistency ratio of their uses, perform use integration matching on the land use of this plot, preferentially select the type that is consistent with the use of the largest adjacent area around, re-code the use and then merge it into the same type of use layer according to the number, establish an updated use space layer, and generate the optimized distribution result of the land use type;

[0204] Select the adjacent plots of each conflict patch and extract their use attributes, calculate the proportion of adjacent uses. For example, the adjacent plots of plot D are A, B, and C respectively, where A and C are agricultural, B is ecological, and the areas are A: 480㎡, B: 220㎡, C: 530㎡. Then the adjacent agricultural area is 1010㎡, the ecological area is 220㎡, and the proportion of agricultural use is 1010 / 1230≈82.1%. Set the fusion priority proportion to 50%. Since the agricultural use has exceeded this threshold, the use of plot D is adjusted to agricultural, and it is merged with the surrounding agricultural use codes. Update the land use field of the plot to a unified code. After reconstructing the use layer, re-code the grid number and clustering position, obtain the continuity index of the spatial structure of each type of use, and use it as the final input data of the spatial utilization structure to generate the optimized distribution result of the land use type.

[0205] Please refer to Figure 6 , and the steps to obtain the result of land use area adjustment are as follows:

[0206] S501: Based on the optimized distribution result of the land use type, obtain the boundary form, area value and adjacency relationship of each type of use, calculate the ratio of the plot area to the average area of the use area, and extract the number of adjacent plots and the number of adjacent use types of the plot, identify the deviation degree of the use configuration, and establish the dispersion value of the use distribution;

[0207] Extract the boundary forms, spatial locations, area data, and adjacency structures of agricultural, construction, and ecological land parcels within the research scope. Call the existing layer data to calculate the area values and the number of boundary adjacencies of each type of land parcel, and count the number of adjacent use types based on the boundary adjacency relationships of land parcels with different uses. For example, the area of land parcel D001 is 1.8 hectares, and it is adjacent to three land parcels with different uses, coded as agricultural (1), ecological (2), and construction (3) respectively. Then the number of adjacent use types is 3. Furthermore, calculate the adjacent use diversity index, and its calculation method is the number of adjacent use categories divided by the total number of adjacent land parcels. For example, if the total number of adjacent land parcels is 4, then the diversity index is 3 / 4 = 0.75. Set the determination benchmark for a relatively small area as 60% of the average area of the same type of use. For example, if the average area of agricultural use is 3.5 hectares, then 60% is 2.1 hectares. The area of D001 is less than this value, and the number of adjacent use types exceeds 2, and the diversity index is greater than 0.4, meeting all screening conditions. Therefore, it is marked as a land parcel with a deviation in use configuration. For other land parcels such as D002 with an area of 2.3 hectares, the number of adjacent uses is 2, and the diversity index is 0.5. Although the area is relatively small, the number of adjacent uses does not exceed the benchmark and is not screened. Traverse all land parcels in the entire region using this method to establish a set of land parcels with an area less than 2.1 hectares, the number of adjacent uses exceeding 2, and the use diversity index greater than 0.4, and obtain the value of the dispersion degree of use distribution.

[0208] S502: According to the value of the dispersion degree of use distribution, extract the regions where uses are relatively concentrated in the spatial layout, identify continuous use concentration blocks, calculate the degree of concentration of the same type of use in space, extract the two types of intersection regions as the structural adjustment regional units, and obtain the unbalanced layout structure sections;

[0209] Construct a spatial distribution layer for the set of discrete use land parcels selected, count their spatial aggregation states, judge whether they form a contiguous or concentrated trend, extract the set of adjacent land parcels with the same use code, merge and construct continuous use blocks, and calculate their contiguous areas. For example, for three agricultural land parcels with consecutive numbers D003, D005, and D006, with areas of 2.0, 2.1, and 2.5 hectares respectively, the contiguous area is 6.6 hectares. The average contiguous area of agricultural use in the region is 3.8 hectares. Then set the 1.5 - fold determination benchmark as 5.7 hectares. Since 6.6 is greater than this value, it is identified as an over - concentrated use area. At the same time, judge whether it intersects with the region where the use dispersion value is greater than 0.6. For example, the use dispersion of D003 is 0.58 and does not meet the condition, while that of D005 is 0.63 and meets the condition. Then the intersection region is D005, which is marked as an unbalanced structure land parcel. Use this method for contiguous use calculation, area comparison, and intersection extraction to comprehensively obtain the regional units in the spatial layout that simultaneously have over - concentration and use dispersion, and establish the unbalanced layout structure sections.

[0210] S503: Call the plot unit area, use aggregation level, use dispersion coefficient, spatial offset distance, and adjacency coordination level in the unbalanced layout structure section to construct a priority evaluation model for the reconfiguration of the plot use structure, and use the formula:

[0211]

[0212] Among them, A gs,k represents the regional area of the k-th plot, L ua,k represents the use aggregation level of this plot, D dc,k represents the use distribution dispersion coefficient, O cv represents the spatial offset value of the current plot, represents the average offset of all plots, H lc,k represents the adjacency use coordination level, Q represents the number of plots participating in the use reconstruction in the unbalanced structure section, and k is the index number;

[0213] Perform operations to obtain the priority value for the reconfiguration of the use structure, adjust the contact relationship between the uses in the high-priority area according to the priority value ranking, perform use reconstruction and boundary replacement, and generate the land use area adjustment result;

[0214] Call the participation parameters of all plots in the unbalanced layout structure section, including plot area, use aggregation level, use dispersion coefficient, offset distance, and adjacency coordination level, etc., read the field values from the layer data respectively, construct a priority calculation system for the reconfiguration, and substitute them into the formula for calculation, where:

[0215] ∑A gs,k ·L ua,k

[0216] =1.8·3 + 2.3·2 + 2.0·3 + 1.6·1 + 2.1·2=5.4 + 4.6 + 6.0

[0217] +1.6 + 4.2=21.8;

[0218]

[0219] Substitute the above results into the formula:

[0220] U rj =9.40 + 0.05 + 1.698=11.148;

[0221] The results show that the priority value for the use reconfiguration of the unbalanced structure section corresponding to the number set is 11.148, which is significantly higher than the set priority adjustment reference value of 9.0, indicating that this type of plot is preferentially included in the scope of use adjustment. After performing use replacement and boundary reorganization operations, a land use area adjustment result is established.

[0222] A land use optimization system based on big data, the system includes:

[0223] The data collection and classification module obtains soil quality data, climate condition data, infrastructure distribution data and topographic and geomorphic information, classifies them based on soil particle composition, drainage capacity, nutrient content, screens precipitation and evaporation characteristics, identifies seasonal change trends, analyzes the distribution of roads and water conservancy facilities, judges accessibility and supply capacity, integrates various data, classifies land use attributes, and generates the classification results of plot use characteristics;

[0224] The land use matching module, based on the classification results of plot use characteristics, identifies soil types, extracts areas suitable for agriculture, construction, and ecological protection, analyzes climate adaptability, judges the stability of different plots under long-term environmental conditions, evaluates the suitability of roads, water conservancy, and power facilities for different land uses, matches land use types, adjusts boundary areas, and generates the classification matching distribution results of plots;

[0225] The topographic adaptation analysis module, based on the classification matching distribution results of plots, screens topographic change characteristics, judges the impact of elevation, slope, and water system distribution on land use, adjusts the use classification for areas where the slope value exceeds the land development standard, calculates the drainage smoothness index for catchment areas, evaluates the waterlogging risk for low-lying plots, adjusts the use of plots where the waterlogging risk index exceeds the set risk threshold, counts topographic adaptation information, and generates the topographic adaptation distribution results of plots;

[0226] The spatial optimization and adjustment module, based on the topographic adaptation distribution results of plots, analyzes the spatial distribution characteristics of agricultural, construction, and ecological use plots, screens the plot density, identifies high-density areas, judges whether there are use conflicts, readjusts the plots with scattered use distribution, retrieves the use relationships of adjacent plots, optimizes the plot use configuration, and generates the optimized distribution results of plot use types;

[0227] The land use structure evaluation module, based on the optimized distribution results of plot use types, evaluates the overall land use structure, analyzes the spatial coordination of each type of plot, screens the boundary connection situation, adjusts the areas with unreasonable use division, optimizes the functional matching between plots, corrects the overly scattered or concentrated layout, and generates the land use area adjustment results.

[0228] As mentioned above, only the specific implementation manners of the present invention are described, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A land use optimization method based on big data, characterized in that: The following steps are involved: S1: Obtain soil, climate, infrastructure, and topography data, classify according to soil particles, drainage, and nutrients, analyze road and water distribution, evaluate accessibility and supply capacity, and generate land use feature classification results; S2: Based on the soil category in the land use feature classification result, extract the matching areas of agriculture, construction, and ecological protection, analyze the climate adaptability of the matching areas, and adjust the boundary areas to generate the land classification matching distribution results; S3: Based on the terrain features in the land parcel classification matching distribution results, determine the impact of elevation, slope, and water system on land use, adjust steep slopes or low-lying areas, and collect terrain adaptation information to generate land parcel terrain adaptation distribution results; S4: Based on the terrain adaptation distribution results of the plots, analyze the spatial density distribution of agricultural, construction and ecological plots, adjust the scattered plots, compare the relevance of the uses of adjacent plots, and generate the optimized distribution results of the plot utilization types; S5: Based on the optimized distribution results of the land use types, the land use structure is evaluated, the spatial coordination of the land plots is analyzed, the connection of the land plot boundaries is detected, the matching degree between the land plots is optimized, and the land use area adjustment results are generated.

2. The land use optimization method based on big data according to claim 1, characterized in that: The classification results of the land use characteristics include soil type, precipitation characteristics, evaporation characteristics, infrastructure accessibility, and land use attributes; the distribution results of the land classification matching include agricultural land matching areas, construction land matching areas, ecological protection land matching areas, and infrastructure adaptability; the distribution results of the land terrain adaptation include elevation distribution, slope characteristics, water system impact, drainage capacity, and waterlogging risk areas; the optimization distribution results of the land use type include spatial distribution of land use, land use density, land use conflict areas, and land use configuration optimization plans; the land use area adjustment results include land use structure optimization, spatial coordination adjustment, boundary connection optimization, functional matching correction, and layout rationality adjustment.

3. The land use optimization method based on big data according to claim 1, characterized in that: The steps to obtain the land use feature classification results are as follows: S101: obtaining soil particle composition, drainage capacity, and nutrient content data of the plot, dividing the soil into particle size classes based on the sand particle ratio, clay particle ratio, and silt particle ratio in the soil particle composition, calling the drainage capacity and nutrient content data for comparison, calculating the mean of the drainage capacity and nutrient content under different particle size structures, dividing different soil types into categories according to the mean threshold, and obtaining the soil attribute category value; S102: calling the soil attribute category value, jointly obtaining the precipitation data and evaporation data of the plot, counting the frequency of data changes within the year according to the daily scale and the monthly scale, calculating the daily average change rate, monthly fluctuation range and range value of precipitation and evaporation, using the formula: Among them, P i represents the precipitation on the i-th day, E i represents the evaporation on the i-th day, n is the number of days involved in the statistics, P j 、E j represents the precipitation and evaporation of the jth month, m is the number of months involved in the statistics, and μ represents the monthly scale The average value, min k (P k +E k ) represents the sum of the minimum precipitation and evaporation on a certain day in the whole year; The water dynamic trend value is obtained by calculation, and combined with the soil type of the plot to establish a comparison result of water response difference and obtain the water suitability trend value; S103: Call the moisture suitability trend value, jointly obtain the road distribution information and water conservancy facility layout data within the plot, calculate the road accessibility value and the supply service degree coefficient according to the facility density, road accessibility and the overlap ratio with the main soil area, establish the supply accessibility capacity level identification respectively, integrate the level identification and the moisture suitability trend value to perform zoning and classification judgment, and obtain the classification result of the plot utilization characteristics.

4. The land use optimization method based on big data according to claim 1, characterized in that: The steps to obtain the distribution results of land parcel classification matching are as follows: S201: Based on the land use feature classification result, the soil attribute category value of each land parcel is identified, the soil distribution layer and land parcel coding information matched by each type of land parcel are called, the corresponding soil type data is extracted by aggregation according to the land parcel number, and the soil category is screened according to the existing relationship between soil type and functional suitability, the functional areas suitable for agriculture, construction, and ecological protection are matched, and the land function suitability zoning value is generated; S202: calling the land function suitability zoning value, combining the annual temperature, precipitation, and humidity meteorological data series corresponding to the location of the plot, extracting the annual average temperature, annual average precipitation, and annual extreme temperature deviation values, and judging the climate stability of each plot under long-term conditions, using the formula: Among them, S c Indicates the climate adaptability index value of the plot, T y represents the average annual temperature corresponding to the plot, P y represents the average annual precipitation of the plot, σ y represents the variance of extreme temperature in a plot within a year, D yk represents the monthly mean temperature deviation value of the kth year, H yk represents the monthly humidity deviation value of the kth year, and y represents the total number of samples of the selected years; The climate adaptability index value is calculated and compared with the soil type to obtain the matching characteristics of the plot under the multi-year average climate background and establish the climate stability adaptability value; S203: Call the climate stability adaptability value, jointly extract the road, water conservancy, and power facility layout layers corresponding to each plot, calculate the road accessibility, water resource security, and power connection rate according to the supporting demand conditions under each type of land use, and compare the functional adaptability with the stability value obtained in the previous sub-step, and then adjust the attribute classification of the edge plot by analyzing the consistency between the plot boundary and the surrounding use boundary, and generate the plot classification matching distribution result.

5. The land use optimization method based on big data according to claim 1, characterized in that: The steps to obtain the results of the terrain adaptation distribution of the plot are as follows: S301: Based on the land parcel classification matching distribution results, the elevation, slope and water system distribution data of each land parcel in the region are screened, the elevation grid value is extracted and the average elevation difference in each land parcel is calculated, the slope grid is obtained and the maximum slope value is generated, the water system distribution layer is superimposed, the minimum distance value to the water body is extracted, the adaptability level of each land parcel under the current use is determined, and the areas that do not meet the conditions are labeled to generate terrain constraint identification values; S302: Call the terrain constraint identification value, analyze the local lowest point elevation position and terrain closure range in the plot, identify the watershed unit, obtain the average slope, total convergence degree of drainage direction, cumulative water flow, soil permeability and surface cover type within the range, and use the formula: Among them, R d Indicates the difference in drainage patency, Q w Indicates the cumulative flow value of the water body in the catchment area, F p represents the average slope value in the catchment area, S s represents the soil permeability coefficient, represents the sum of drainage impedance indexes under different land cover types of class z, P c is the water permeability level of the c-type surface, L c is the thickness and density parameter of the c-type surface, K v is the set drainage efficiency benchmark value; The drainage patency difference value is obtained by calculation, and it is compared with the set drainage efficiency benchmark value. The use is adjusted in combination with the existing use to obtain the drainage adaptability grade value of the plot; S303: Call the drainage adaptability grade value of the plot, summarize the plots used for construction and agriculture, count the terrain and drainage index grade distribution characteristics corresponding to each use type, establish an adaptation grade coding matrix according to the plot number, perform statistical analysis based on the constraint grade distribution value of each type of plot in the matrix under the current use, redefine the original use label to compatible use or ecological use, and generate the plot terrain adaptation distribution result.

6. The land use optimization method based on big data according to claim 1, characterized in that: The steps to obtain the optimized distribution results of land use types are as follows: S401: Based on the terrain adaptation distribution results of the plots, extract the vector boundaries and use attribute information of the agricultural, construction, and ecological use plots, calculate the boundary area, shape compactness, and use distribution continuity of each use category within the overall area, obtain the minimum spacing value between continuously distributed plots, count the number of plots in each cell, and generate a use aggregation density value; S402: calling the usage aggregation density value, marking the area where the cell density value is greater than the upper threshold as a high-density block, and performing cross-statistics on the usage types therein, and identifying the usage conflicts of the plots with different uses in the same cell, using the formula: Among them, C u Indicates the usage conflict interference value, U ag , U ck The use identification codes of the land parcels of use type a and use type c in the region, respectively. ag , D ck Indicates the relative distance between plots of this use type, S ab , S cd Indicates the spatial area of ​​the corresponding plot, B e represents the interlaced index of the use boundary of the e-th boundary unit, g, h, k, t, and w represent the number of plots for use a, the number of their areas, the number of plots for use c, the number of their areas, and the total number of interlaced boundary units, respectively; The use conflict interference value is obtained by calculation, and the use uniformity is adjusted for the area where the conflict value is greater than the set conflict threshold, so as to obtain the use conflict distribution level value; S403: Call the use conflict distribution level value, extract the use attributes of its adjacent patches and analyze the use consistency ratio, perform use fusion matching on the plot, give priority to the type that is consistent with the use of the largest adjacent area in the surrounding area, re-encode the use and merge it into the same type use layer by number, establish and update the use space layer, and generate the optimized distribution result of the plot utilization type.

7. The land use optimization method based on big data according to claim 1, characterized in that: The steps to obtain the land use area adjustment results are: S501: Based on the optimized distribution result of the land use type, the boundary shape, area value and adjacency relationship of each type of use are obtained, the ratio of the land area to the average use area is calculated, and the number of adjacent land plots and the number of adjacent use types of the land parcel are extracted to identify the degree of use configuration deviation and establish the use distribution dispersion value; S502: extracting relatively densely used areas in the spatial layout according to the use distribution dispersion value, identifying continuous use concentrated blocks, calculating the degree of spatial concentration and continuity of similar uses, extracting two types of intersection areas as structural adjustment area units, and obtaining the layout structure imbalance section; S503: Calling the unit area of ​​the plots in the imbalanced layout structure section, the use aggregation level, the use dispersion coefficient, the spatial offset distance and the adjacent coordination level to build a plot use structure reconfiguration priority evaluation model, using the formula: Among them, A gs,k represents the area of ​​the kth plot, L ua,k Indicates the use aggregation level of the land parcel, D dc,k It represents the coefficient of dispersion of usage distribution, O cv Indicates the spatial offset value of the current plot. represents the average offset of all plots, H lc,k represents the coordination level of adjacent uses, Q represents the number of plots involved in the use reconstruction in the structural imbalance section, and k is the index number; The calculation obtains the priority value of the use structure reconfiguration, adjusts the contact relationship between the use and boundary of the high priority area according to the priority value, performs use reconstruction and boundary replacement, and generates the land use area adjustment result.

8. A land use optimization system based on big data, characterized in that: According to any one of claims 1 to 7, the land use optimization method based on big data is implemented, and the system comprises: The data collection and classification module obtains soil quality data, climate condition data, infrastructure distribution data and topography information, classifies soil based on particle composition, drainage capacity and nutrient content, screens precipitation and evaporation characteristics, identifies seasonal trends, analyzes the distribution of roads and water conservancy facilities, determines accessibility and supply capacity, integrates various data, classifies land use attributes, and generates land use feature classification results; The land use matching module identifies soil types based on the land use feature classification results, extracts areas suitable for agriculture, construction, and ecological protection, analyzes climate adaptability, determines the stability of different plots under long-term environmental conditions, evaluates the adaptability of roads, water conservancy, and power facilities to different land uses, matches land use types, adjusts boundary areas, and generates land classification matching distribution results; The terrain adaptation analysis module screens the terrain change characteristics based on the classification and matching distribution results of the plots, determines the impact of elevation, slope, and water system distribution on land use, adjusts the use classification for areas where the slope value exceeds the land development standard, calculates the drainage patency index for the catchment area, conducts waterlogging risk assessment for low-lying plots, adjusts the use of plots whose waterlogging risk index exceeds the set risk threshold, and statistically calculates terrain adaptation information to generate plot terrain adaptation distribution results; The spatial optimization and adjustment module analyzes the spatial distribution characteristics of agricultural, construction and ecological land plots based on the land plot terrain adaptation distribution results, screens the density of land plots, identifies high-density areas, determines whether there are conflicts in use, readjusts land plots with scattered use distribution, retrieves the use relationship of adjacent land plots, optimizes the use configuration of land plots, and generates optimized distribution results of land use types; The land use structure assessment module evaluates the overall land use structure based on the optimized distribution results of the land use types, analyzes the spatial coordination of each type of land, screens boundary connections, adjusts areas with unreasonable use divisions, optimizes functional matching between land plots, corrects overly dispersed or concentrated layouts, and generates land use area adjustment results.

Images