Method and device for identifying water conservation and ecological restoration area

Abstract

The invention discloses a water conservation and ecological restoration area identification method and device. The method comprises the following steps: firstly, obtaining the water conservation amount and water conservation influence factors of a target area; screening and detecting the water conservation amount and the water conservation influence factors to obtain an optimal water conservation value, a dominant factor and a background factor; clustering, classifying and superposing the background factors, and performing partition processing on the background factors and the dominant factors to obtain a plurality of effective ecological partition units; the optimal water source conservation value is combined to count and quantify the water source conservation amount of each effective ecological partition unit, and a water source conservation potential value and a potential surplus amount are obtained; and finally, according to the water conservation potential value and the potential surplus, dividing a restoration priority level, and identifying a restoration area. According to the method, the defects that a traditional method is low in recognition accuracy and weak in priority pertinence are overcome, the zoning and evaluation scientificity is improved, and the water conservation and ecological restoration efficiency is effectively improved.

Description

Technical Field

[0001] This application relates to the field of ecological environment restoration technology, and in particular to a method and apparatus for identifying water conservation and ecological restoration zones. Background Technology

[0002] With the increasing prominence of problems such as the degradation of water conservation functions and the decline in ecosystem service capacity, accurately identifying key water conservation areas and key ecological restoration areas has become a core requirement for ensuring regional ecological security and enhancing ecosystem stability. However, current methods for identifying water conservation and ecological restoration areas, while attempting to combine analysis with factors influencing water conservation, generally have significant limitations: on the one hand, they fail to systematically screen and explore various influencing factors such as topography, soil, and climate, resulting in low efficiency in factor utilization and inaccurate identification of key influencing factors; on the other hand, the clustering and classification logic in the zoning process is crude, failing to scientifically quantify the restoration potential and surplus gap of each zone, ultimately leading to weak targeting in the ecological restoration priority classification, misallocation of restoration resources, and restoration effects falling short of expectations.

[0003] Therefore, how to achieve effective ecological zoning and scientific potential assessment, and thus accurately identify water conservation and ecological restoration zones, is a key issue that urgently needs to be addressed. Summary of the Invention

[0004] In view of this, the method and apparatus for identifying water conservation and ecological restoration zones provided in this application can improve the scientific nature of zoning and assessment, and effectively improve the efficiency of water conservation and ecological restoration. The method and apparatus for identifying water conservation and ecological restoration zones provided in this application are implemented as follows: This application provides a method for identifying water conservation and ecological restoration zones, including: The water conservation capacity and water conservation influencing factors of the target area are obtained. The water conservation influencing factors include at least one of topography, soil, climate, vegetation and human activities. The water conservation capacity and the factors influencing water conservation are screened and detected to obtain the optimal water conservation value, dominant factor and background factor. The background factors are clustered and classified overlayed to obtain processed background factors. The processed background factors and the dominant factors are then partitioned to obtain multiple effective ecological partition units. The optimal water conservation value and the water conservation amount corresponding to each effective ecological zone unit are statistically and quantitatively processed to obtain the water conservation potential value and potential surplus of each effective ecological zone unit. Based on the water conservation potential value and the potential surplus, the priority level of ecological restoration is divided, and the water conservation and ecological restoration areas are identified based on the ecological restoration priority level to obtain the identification results.

[0005] In some embodiments, the process of screening and detecting the water conservation capacity and the factors influencing water conservation to obtain the optimal water conservation value, dominant factor, and background factor includes: The water conservation capacity of the target area is subjected to time series screening to obtain the optimal water conservation value, which is used to characterize the optimal ecological environment state of the target area during the observation period. The factors affecting water conservation were screened and processed to obtain basic topographical factors, soil hydrological factors, climate conditions factors, vegetation ecological factors, and human intervention factors. The topographical elements, soil and hydrological elements, climate conditions, vegetation ecology elements, and human intervention elements are removed and integrated to obtain an initial factor pool. The optimal water conservation value and each factor in the initial factor pool are detected and processed to obtain the dominant factor and background factor.

[0006] In some embodiments, the clustering and classification overlay processing of the background factors to obtain processed background factors, and the partitioning of the processed background factors and the dominant factors to obtain multiple effective ecological partition units, including: The optimal discretization scheme is obtained, and the background factors and the optimal discretization scheme are preprocessed and clustered to obtain ecological background units. The dominant factors and the ecological background units are partitioned to obtain a theoretical joint partition; The theoretical joint partition and the dominant factor are subjected to invalid factor combination elimination processing to obtain multiple valid ecological partition units.

[0007] In some embodiments, obtaining the optimal discretization scheme involves preprocessing the background factors and the optimal discretization scheme, as well as performing clustering processing to obtain ecological background units, including: Obtain the optimal discretization scheme generated by the optimal parameter geodetector; The background factor and the optimal discretization scheme are matched and preprocessed to obtain the preprocessed background factor. The preprocessed background factors are clustered using a clustering algorithm to obtain ecological background units. The clustering algorithm aims to minimize intra-class variance and maximize inter-class differences.

[0008] In some embodiments, the step of detecting and processing the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor and background factor includes: Factor detection processing is performed on the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor. The dominant factor is the factor whose explanatory power for the optimal water conservation value exceeds a preset explanatory power threshold. Interactive detection processing is performed on each factor in the initial factor pool to obtain the background factor, which is a factor whose nonlinear enhancement frequency is higher than a preset frequency threshold.

[0009] In some embodiments, the partitioning of the dominant factor and the ecological background unit to obtain a theoretical joint partition includes: The dominant factor and the optimal discretization scheme are matched and preprocessed to obtain the preprocessed dominant factor. The preprocessed dominant factors and the ecological background units are partitioned to obtain a theoretical joint partition.

[0010] In some embodiments, the effective ecological zoning units include priority restoration zones, key improvement zones, moderate optimization zones, and status quo maintenance zones.

[0011] This application provides an identification device for water conservation and ecological restoration zones, comprising: The acquisition module is used to acquire the water conservation capacity of the target area and the factors affecting water conservation, wherein the factors affecting water conservation include at least one of topography, soil, climate, vegetation and human activities; The processing module is used to screen and detect the water conservation capacity and the factors affecting water conservation, so as to obtain the optimal water conservation value, dominant factor and background factor. The processing module is also used to perform clustering and classification superposition processing on the background factors to obtain processed background factors, and to perform partitioning processing on the processed background factors and the dominant factors to obtain multiple effective ecological partition units. The processing module is also used to perform statistical quantification on the optimal water conservation value and the water conservation amount corresponding to each effective ecological zone unit to obtain the water conservation potential value and potential surplus of each effective ecological zone unit. The identification module is also used to classify the priority level of ecological restoration according to the water source conservation potential value and the potential surplus, and to identify the water source conservation and ecological restoration areas based on the ecological restoration priority level to obtain the identification result.

[0012] The computer device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.

[0013] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method described in this application embodiment.

[0014] This application provides a method and apparatus for identifying water conservation and ecological restoration zones. The method first acquires the water conservation volume and influencing factors of the target area; then, it screens and detects the water conservation volume and influencing factors to obtain the optimal water conservation value, dominant factors, and background factors; after clustering and classifying and superimposing the background factors, it partitions the background factors and dominant factors to obtain multiple effective ecological partition units; finally, it statistically quantifies the water conservation volume of each effective ecological partition unit based on the optimal water conservation value to obtain the water conservation potential value and potential surplus; and finally, it classifies restoration priority levels based on the water conservation potential value and potential surplus to identify restoration zones. This approach overcomes the shortcomings of traditional methods, such as low accuracy and weak priority targeting, improves the scientific rigor of partitioning and assessment, effectively enhances the efficiency of water conservation and ecological restoration, and solves the technical problems mentioned in the background art. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram illustrating the implementation process of a method for identifying water conservation and ecological restoration zones provided in this application embodiment; Figure 2 A schematic diagram illustrating the implementation process for obtaining the optimal water conservation value, dominant factor, and background factor, provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an identification device for water conservation and ecological restoration zones provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] The following description of some technologies involved in the embodiments of this application is provided to aid understanding and should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, some descriptions of well-known functions and structures are omitted in the following description.

[0019] Figure 1 This is a schematic diagram illustrating the implementation process of a method for identifying water conservation and ecological restoration zones provided in this application, including steps 101 to 105. Wherein, Figure 1 This is merely one execution order shown in the embodiments of this application and does not represent the only execution order for a method of identifying water conservation and ecological restoration zones. Where the final result can be achieved, Figure 1 The steps shown can be performed in parallel or in reverse order.

[0020] Step 101: Obtain the water conservation capacity of the target area and the factors affecting water conservation.

[0021] In this embodiment of the application, the water conservation capacity of the target area is obtained using the water balance method, and the formula is as follows: (1). In formula (1), Where P is the water conservation capacity, ET is the rainfall, ET is the actual evapotranspiration, and Q is the surface runoff.

[0022] Five elements were selected: topography, soil, climate, vegetation, and human activities. Topography included elevation and slope; soil included porosity and organic carbon content; climate included annual rainfall and average annual temperature; vegetation included annual maximum NDVI (Normalized Difference Vegetation Index) and vegetation cover; and human activities included land use type and population density. All elements were standardized to a 1km×1km resolution and a time scale consistent with the conservation capacity.

[0023] Step 102 involves screening and detecting the water conservation capacity and its influencing factors to obtain the optimal water conservation value, dominant factors, and background factors.

[0024] In this embodiment of the application, the annual average water conservation capacity is calculated by statistically analyzing the regional average value grid by grid over time. The value with the largest value that has been verified by ecological and climatic conditions is selected as the optimal water conservation value.

[0025] Factors influencing water conservation were first categorized into five types based on their ecological function correlation: topographical foundation, soil and hydrology, etc. Factors with a data missing rate >20% and an absolute value of the correlation coefficient for water conservation <0.1 were then removed, forming an initial factor pool. An optimal parameter geographic detector was used, with the optimal water conservation value as the dependent variable and the factors in the factor pool as independent variables. Factor detection was used to screen factors with an explanatory power (q-value) ≥30% and a significance test (p) <0.01 as dominant factors. Interaction detection was used to screen factors with the highest frequency of nonlinear enhancing interactions, which were then used as background factors.

[0026] Step 103: Cluster and classify the background factors to obtain the processed background factors. Then, partition the processed background factors and the dominant factors to obtain multiple effective ecological partition units.

[0027] In this embodiment, the background factors are first processed by obtaining the optimal discretization scheme that maximizes the q value based on the optimal parameter geographic detector, and then the k-means clustering algorithm is used to form ecological background units.

[0028] After preprocessing the dominant factors using the same optimal discretization scheme, they are layered with ecological background units according to the explanatory power of the dominant factors from high to low, forming a theoretical joint partition. Two types of invalid combinations are eliminated: combinations without actual spatial distribution and combinations that violate ecological laws (such as high-altitude areas corresponding to low rainfall). Finally, effective ecological partition units with spatial continuity and clear ecological significance are obtained.

[0029] Step 104: Statistically quantify the optimal water conservation value and the water conservation amount corresponding to each effective ecological zone unit to obtain the water conservation potential value and potential surplus of each effective ecological zone unit.

[0030] In this embodiment, statistical indicators such as the average, 75th percentile, and 90th percentile of water conservation capacity are calculated for each effective ecological zone unit. Based on the optimal water conservation value, the 90th percentile, which is resistant to abnormal fluctuations and close to the optimal level, is selected as the water conservation potential value. The potential surplus is obtained by subtracting the average current water conservation capacity of the unit from the potential value.

[0031] Step 105: Based on the water conservation potential value and potential surplus, ecological restoration priority levels are divided, and water conservation and ecological restoration areas are identified based on the ecological restoration priority levels to obtain the identification results.

[0032] In this embodiment, ecological restoration priority levels are defined based on percentiles of potential surplus. These include: Priority Restoration Area (potential surplus ≥ 80th percentile), Key Improvement Area (50th percentile ≤ potential surplus < 80th percentile), Moderate Optimization Area (20th percentile ≤ potential surplus < 50th percentile), and Status quo Maintenance Area (potential surplus < 20th percentile). These levels are then overlaid with regional administrative boundaries to output a spatial distribution map and attribute table of water conservation and ecological restoration areas.

[0033] This application's embodiments construct a standardized technical framework covering the entire process—from data acquisition, screening and detection, clustering and partitioning, potential assessment, to remediation identification—solving the problems of fragmented processes and loose connections between stages in traditional identification methods, ensuring the reproducibility and stability of the technology. It introduces the optimal water conservation value as a core reference, unifying factor detection targets and potential assessment standards, avoiding the problems of inaccurate positioning of dominant factors and ambiguous quantification of remediation potential caused by the lack of a unified reference in traditional methods. Through the clustering and superposition of background factors and dominant factors, and the classification of potential surplus, it achieves the linkage between ecologically uniform partitioning and precise remediation priority, solving the problems of unclear ecological significance and misallocation of remediation resources in traditional methods.

[0034] In the above Figure 1 Based on the above, this application also provides a schematic diagram of the implementation process for obtaining the optimal water conservation value, dominant factor, and background factor, as shown below. Figure 2 As shown, steps 201 to 204 are included: Step 201: Perform time series screening on the water conservation capacity of the target area to obtain the optimal water conservation value.

[0035] In this embodiment of the application, based on the time series data of water conservation, the annual values ​​of water conservation raster data are statistically analyzed pixel by pixel using ArcGIS raster calculator, and then the annual average water conservation of the target area is calculated using the zoning statistical tool to generate a year-to-annual average conservation correspondence table.

[0036] Sort the values ​​by average annual conservation volume in descending order and select the maximum value as the candidate optimal value.

[0037] We extracted vegetation cover (≥65%, the highest during the observation period) and human disturbance indicators (construction land ratio ≤8.3%, the lowest during the observation period) for candidate years to ensure that the ecosystem is in optimal condition.

[0038] Based on the multi-year spatial distribution averages of precipitation, surface runoff, and actual evapotranspiration, the annual precipitation (≥1350mm, 14.3% higher than the average during the observation period) and annual actual evapotranspiration (≤980mm, 3.4% lower than the average during the observation period) of the candidate years are conducive to water conservation.

[0039] Based on the above verification, the candidate values ​​can represent the optimal ecological environment state of the target area during the observation period and are determined as the optimal water conservation values.

[0040] Step 202 involves screening and processing the factors affecting water conservation to obtain basic topographical factors, soil hydrological factors, climate conditions, vegetation ecological factors, and human intervention factors.

[0041] In this application embodiment, elements that are not directly related to water conservation functions or have very weak connections are removed, while the core elements of topography, soil, climate, vegetation and human activities are retained.

[0042] Basic topographical elements include elevation and slope, reflecting the impact of topography on runoff paths and infiltration.

[0043] Soil hydrological factors, including soil porosity and soil organic carbon content, directly determine the soil's water retention and infiltration capacity.

[0044] Climate conditions include annual rainfall and average annual temperature, which provide hydrological inputs and energy background for water conservation.

[0045] Vegetation ecological elements include annual maximum NDVI and vegetation cover, which regulate water interception and transpiration processes. Among them, according to the formula... (2) The vegetation cover was calculated, where NDVI value for areas without vegetation cover The NDVI value for areas with pure vegetation cover. , Set the confidence level range for NDVI values ​​from 5% to 95%.

[0046] Human intervention factors include land use type and population density, reflecting the intensity of human activities' disturbance to the ecosystem.

[0047] Step 203 involves eliminating and integrating basic topographic elements, soil and hydrological elements, climate conditions, vegetation and ecological elements, and human intervention elements to obtain the initial factor pool.

[0048] In this embodiment, data quality verification and format integration are performed on topographic basic elements, soil hydrological elements, climate condition elements, vegetation ecological elements, and human intervention elements to construct an initial factor pool.

[0049] Calculate the missing rate of each element's raster data, remove elements with a missing rate >20%, and fill elements with a missing rate ≤20% using the neighborhood mean method.

[0050] Calculate the Pearson correlation coefficient between each factor and water conservation capacity, remove factors with an absolute correlation coefficient < 0.1, and retain factors with an absolute correlation coefficient ≥ 0.1.

[0051] The retained elements were uniformly converted into ASCII raster format, with a spatial resolution of 1km×1km and a time scale of annual data of the optimal ecological environment state, forming an initial factor pool, and each factor was numbered (such as F1-altitude, F2-slope, F3-soil porosity, etc.).

[0052] Step 204: Detect and process the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor and background factor.

[0053] In this embodiment, an optimal parameter geographic detector is used, with the optimal water conservation value as the core reference, to detect the initial factor pool.

[0054] The initial factor pool and the optimal water conservation value raster data were used to generate 1000 uniformly distributed sample points using ArcGIS's Create Random Points tool. Then, the Extract Multi-Value to Point tool was used to assign the factor and optimal water conservation value attributes to the sample points, generating a CSV format sample dataset.

[0055] Using the factor detection module, the explanatory power of each factor for the optimal water conservation value is calculated according to formula (3). (3), where q is the explanatory power, and L is the number of rank and category of the variable factors. And N represents the number of samples in different graded regions and the entire region. and Let h be the variance of different graded regions and the whole region, and h be the h-th graded region of the influencing factor, where h = 1, 2, ..., L.

[0056] An interaction detection module is used to calculate the interaction q-value between each factor and the other 9 factors to determine the type of interaction (nonlinear enhancement, synergistic enhancement, etc.). The frequency of nonlinear enhancement is statistically analyzed (interaction q-value > maximum q-value of a single factor indicates nonlinear enhancement).

[0057] Based on the results of the factor detection heatmap, the factors with the highest nonlinear enhancement frequency in the top 30% were selected as background factors (e.g., altitude and annual rainfall, vegetation cover all produce nonlinear enhancement, frequency=3; soil porosity and altitude, land use produce nonlinear enhancement, frequency=3, all of which meet the standard).

[0058] Identify the dominant factors (such as annual rainfall and annual maximum NDVI) and background factors (such as altitude, soil porosity, and land use type).

[0059] This application's embodiments optimize the optimal water conservation value screening logic to avoid misjudging abnormally high conservation values ​​caused by accidental hydrological events as optimal values, ensuring that the optimal value truly represents the optimal ecological state of the region and provides a reliable reference for subsequent steps. An initial factor pool is constructed by eliminating invalid elements and integrating formats, removing redundant and low-quality data to prevent invalid data from interfering with subsequent detection, thus improving the efficiency and accuracy of factor detection. Simultaneously, the data preparation process before detection is clearly defined, reducing the technical obstacles caused by inconsistent formats of multi-source data.

[0060] In some embodiments, the background factors are clustered and classified overlayed to obtain processed background factors. The processed background factors and dominant factors are partitioned to obtain multiple effective ecological partition units, including: obtaining the optimal discretization scheme, preprocessing the background factors and the optimal discretization scheme and clustering them to obtain ecological background units.

[0061] Specifically, an optimal parameter geographic detector is used to generate a scheme based on the core principle of maximizing the explanatory power (q value) of background factors on the optimal water conservation value, with background factors and the optimal water conservation value as inputs.

[0062] For numerical background factors, we attempted to classify them using 3-6 types of natural breakpoint method, quantile method, equal interval method, geometric interval method and standard deviation method respectively; for categorical background factors (such as land use type), we merged the original categories according to ecological correlation (e.g., merging 8 categories into 5 categories: cultivated land, forest land, grassland, construction land and water area).

[0063] Calculate the q-value for each type of discretization scheme, and select the scheme with the largest q-value as the optimal discretization scheme. An example is shown below: Altitude: Classified into 3 categories (<500m, 500-1000m, >1000m), q value = 0.28 (higher than 0.25 for the 4-category classification).

[0064] Soil porosity: Classified into 3 categories (<40%, 40%-50%, >50%), q value = 0.21 (higher than 0.18 for the 5-category classification).

[0065] Land use type: 5 categories merged (cultivated land = 1, forest land = 2, grassland = 3, construction land = 4, water area = 5), q value = 0.25 (higher than the original 8 categories of 0.20).

[0066] The background factors are formatted according to the optimal discretization scheme, and the continuous values ​​of altitude and soil porosity are converted into classified values, such as assigning value 1 to altitude <500m, value 2 to 500-1000m, and value 3 to >1000m.

[0067] Convert the textual category of land use type (e.g., forest land) into the corresponding numerical code (e.g., forest land = 2).

[0068] Use ArcGIS raster algebra tools to ensure that all background factor rasters have completely consistent resolution, coordinate system, and spatial extent to avoid pixel misalignment.

[0069] The k-means clustering algorithm is used with the goal of minimizing within-class variance and maximizing between-class variance. The intra-class sum of squares for k=3-7 is calculated using the elbow rule, with a maximum number of iterations of 100. The preprocessed three background factor rasters are converted into a pixel-attribute matrix and input into the k-means algorithm. After 28 iterations, the convergence condition is met.

[0070] For the five types of ecological background units output, the standard deviation of background factors within each unit was calculated using ArcGIS zoning statistics tools. For example, within the high-altitude forest type unit (number 3), the standard deviation of altitude was 180m and the standard deviation of soil porosity was 3.2%, both <5%, meeting the requirement of uniformity of ecological attributes.

[0071] By combining the characteristics of the factors, such as low-altitude cultivated land type (No. 1), mid-altitude grassland type (No. 2), high-altitude forest type (No. 3), low-altitude construction land type (No. 4), and water area surrounding type (No. 5), the final ecological background unit is formed.

[0072] Furthermore, the dominant factors and ecological background units are partitioned to obtain a theoretical joint partition.

[0073] Specifically, a geographic detector with optimal parameters consistent with the background factors is used to complete discretization and format adaptation.

[0074] For the identified dominant factors (such as annual rainfall and annual maximum NDVI), the selection scheme is based on maximizing the q-value: Annual rainfall: Classified into 3 categories (<800mm, 800-1200mm, >1200mm), q value = 0.42 (higher than 0.39 for the 4-category classification).

[0075] Maximum annual NDVI: 3-class classification (<0.6, 0.6-0.8, >0.8), q value = 0.38 (higher than 0.35 for the 3-class natural breakpoint classification).

[0076] Classification value conversion: Convert the continuous values ​​of annual rainfall and NDVI into classification values ​​(e.g., annual rainfall <800mm=1, 800-1200mm=2, >1200mm=3), ensuring that the classification value format is consistent with the background cells.

[0077] Dominant factor combinations: Based on the priority of annual rainfall - annual maximum NDVI (a higher annual rainfall q value indicates a stronger dominant effect), 9 dominant factor combinations are generated (e.g., 1-1: <800mm+<0.6; 2-3: 800-1200mm+>0.8, etc.), and each combination is assigned a unique combination number (1-9).

[0078] In ArcGIS, use the raster calculator tool to generate theoretical partition numbers using the formula: ecological background unit number × 10 + dominant factor combination number. Example: High-altitude forest type (3) + annual rainfall > 1200 mm (3) + NDVI > 0.8 (3) → zone number = 3 × 10 + 9 = 39 (9 is the number of the 3-3 combination).

[0079] The average water conservation capacity of each theoretical zone was calculated using ArcGIS zoning statistics tools. Groups with an average conservation capacity difference of less than 5% and the same land use type were merged. For example, zone 39 (average conservation capacity 50.2 mm) and zone 38 (average conservation capacity 48.5 mm) had a difference of 3.4% (less than 5%) and were both forest land, so they were merged into one category.

[0080] Ultimately, 15 theoretical joint partitions were obtained, and each partition was labeled with background unit-dominant factor combination features (e.g., 3-3-3: high-altitude forest + high rainfall + high NDVI).

[0081] Furthermore, invalid factor combinations were eliminated from the theoretical joint partitioning to obtain multiple valid ecological partitioning units.

[0082] Specifically, combinations that have no actual spatial distribution within the target area are excluded. For example, high-altitude forest type (3) + annual rainfall <800mm (1).

[0083] Eliminate combinations that violate ecological principles. For example, low-altitude construction land type (4) + NDVI>0.8 (3) has low vegetation coverage in concentrated construction land areas and NDVI is generally <0.6. This combination does not conform to the actual ecological characteristics.

[0084] Based on the above criteria, three invalid combinations (such as 3-1, 4-3, and 5-2) were removed from the 15 theoretical joint partitions, leaving 12 candidate partitions.

[0085] The spatial continuity of the candidate partitions was checked using ArcGIS domain analysis tools. Fragmented partitions with a maximum connected area of ​​less than 100 km² were eliminated; in this example, all 12 candidate partitions met the requirement.

[0086] Twelve effective ecological zoning units were identified, and a table was created to correspond to zoning number, spatial range, ecological characteristics, and average conservation capacity.

[0087] This application's embodiments employ a three-step process: constructing ecological background units, generating theoretical partitions, and eliminating invalid combinations. First, a basic framework with uniform ecological attributes is formed through clustering. Then, dominant factors are superimposed to reflect core driving differences, solving the problem of traditional overlaying directly mixing multiple factors and resulting in confused ecological meaning in partitions. A new invalid factor combination elimination step is added, using a dual verification of spatial existence and ecological rationality to eliminate combinations without actual geographical distribution or that violate ecological laws (such as high altitude + low rainfall), avoiding the problem of traditional partitions containing invalid units and being unapplicable. The superposition logic of dominant factors and background factors is clearly defined, enabling partitions to simultaneously reflect innate ecological endowments (background factors) and acquired core driving forces (dominant factors), solving the problem of traditional partitions focusing only on a single element and failing to reflect the synergistic influence of multiple factors, thus improving the ecological representativeness of the partitions.

[0088] In some embodiments, obtaining the optimal discretization scheme involves preprocessing the background factors and the optimal discretization scheme, as well as performing clustering processing to obtain ecological background units, including: obtaining the optimal discretization scheme generated by the optimal parameter geographic detector.

[0089] Specifically, based on the determined background factors and the optimal water conservation value, preprocessed 1km×1km raster data is extracted to ensure that areas without data have been filled with the neighborhood mean.

[0090] Using the merged five-category coded raster data (arable land = 1, forest land = 2, grassland = 3, construction land = 4, water area = 5), the raster data corresponding to the determined optimal water conservation value (e.g., 52.3 mm) is used to calculate the factor explanatory power.

[0091] Based on the core principle of maximizing the explanatory power (q-value) of the factor for the optimal water conservation value, discretization is performed using an optimal parameter geographic detector: Altitude: We attempted equidistant partitioning in three categories (<500m, 500-1000m, >1000m), four categories (<500m, 500-800m, 800-1200m, >1200m), and five categories (<400m, 400-700m, 700-1000m, 1000-1300m, >1300m), and calculated the q-value for each category. The q-values ​​for the three categories were 0.28, 0.25, and 0.23, respectively. Therefore, the three-category partitioning was chosen as the optimal solution.

[0092] Soil porosity: Three types (<40%, 40%-50%, >50%) and four types (<35%, 35%-45%, 45%-55%, >55%) were tried to divide the soil into natural breakpoints. The q of the three types was 0.21 (higher than the 0.18 of the four types), and it was determined to be the optimal solution.

[0093] Land use types have been merged into 5 categories based on ecological relevance. The q-value of this classification scheme is calculated to be 0.25 (higher than the original 0.20 for 8 categories), and it is determined to be the optimal scheme.

[0094] Organize the optimal discretization rules for each background factor to form a factor-discretization category-encoding correspondence table.

[0095] Furthermore, the background factors and the optimal discretization scheme are matched and preprocessed to obtain the preprocessed background factors. Based on the discretization rules, continuous values ​​are converted into categorical values ​​using the ArcGIS raster calculator tool. Altitude: Enter the formula Con("altitude grid"<500,1,Con("altitude grid"<1000,2,3)) to generate an altitude classification value grid.

[0096] Soil porosity: Input the formula Con("porosity grid"<40,1,Con("porosity grid"<50,2,3)) to generate a porosity classification value grid.

[0097] After conversion, the data needs to be verified through attribute table statistics: for example, the number of grid cells with an altitude classification value of 1 (<500m) accounts for about 35%, which is consistent with the area proportion of low-altitude regions, to ensure accurate conversion.

[0098] Check if the codes in the attribute table contain only 1-5 (corresponding to cultivated land, forest land, grassland, construction land, and water area respectively), remove abnormal codes (such as 0 or 6), and fill with the mode of the neighborhood.

[0099] The grid for water area code 5 must overlap with the spatial range of rivers and lakes in the map, and the grid for construction land code 4 must match the range of urban built-up areas to ensure that the classification conforms to the actual geographical characteristics.

[0100] By using ArcGIS raster algebra tools, the spatial range of the row / column resolution coordinate system of the three background factor rasters—elevation, soil porosity, and land use type—is unified to ensure one-to-one correspondence of pixels (without pixel misalignment).

[0101] All three types of factor rasters were converted to ASCII format. Each ASCII file contains basic raster information (ncols, nrows, xllcorner, yllcorner, cellsize, NODATA_value) and a classification value matrix.

[0102] The final output is the preprocessed background factor dataset, which contains three ASCII format categorical value rasters.

[0103] Furthermore, the preprocessed background factors are clustered using a clustering algorithm to obtain ecological background units. The clustering algorithm aims to minimize intra-class variance and maximize inter-class differences.

[0104] Specifically, the preprocessed three background factor raster cells are converted into a pixel-attribute matrix (each row represents one pixel, and the three columns are the classification values ​​of altitude, soil porosity, and land use type, respectively). The intra-class sum of squares (WCSS) is calculated for k=3-7: WCSS=8500 when k=3, WCSS=6200 when k=4, WCSS=4800 when k=5, and WCSS=4600 when k=6 (the decrease is <5%). Therefore, k=5 is chosen (to ensure intra-class uniformity and avoid over-subdivision).

[0105] Maximum number of iterations = 100, convergence threshold (change in intra-class variance) = 0.001 (iteration stops when the change in intra-class variance between two consecutive iterations is < 0.001).

[0106] The k-means++ algorithm was used to repeat the clustering process 5 times, and the result with the smallest WCSS was selected as the final clustering model.

[0107] Input the cell-attribute matrix and the parameters mentioned above, and perform clustering. After 28 iterations, the convergence condition is met, and the clustering label (1-5) of each cell is output.

[0108] The clustering label matrix was converted into raster data, and the rationality of the clustering was initially judged: for example, the raster of label 3 is concentrated in the high altitude (>1000m), high porosity (>50%), and forest (code 2) areas, which is consistent with the ecological characteristics of high altitude forest.

[0109] Calculate the background factor standard deviation of the 5-class clustering results: Label 1 (Low-altitude farmland): Standard deviation of altitude = 120m, Standard deviation of soil porosity = 2.8%, Mode of land use type = 85% (farmland code 1).

[0110] Tag 3 (High-altitude forest land type): Standard deviation of altitude = 180m, Standard deviation of soil porosity = 3.2%, Mode of land use type = 82% (Forest land code 2).

[0111] Among all categories, the standard deviation of altitude is <200m, the standard deviation of soil porosity is <4%, and the mode of land use accounts for >80%.

[0112] Based on the factor combination characteristics of the clustering results, five types of units are named according to the format of altitude-land use-core attribute: Tag 1: Low-altitude arable land type (altitude <500m, arable land accounts for 85%, soil porosity <40%).

[0113] Tag 2: Mid-altitude grassland type (altitude 500-1000m, grassland accounts for 80%, soil porosity 40%-50%).

[0114] Tag 3: High-altitude forest type (altitude > 1000m, forest area accounts for 82%, soil porosity > 50%).

[0115] Tag 4: Low-altitude construction land type (altitude <500m, construction land accounts for 75%, soil porosity <40%).

[0116] Tag 5: Water area type (altitude <500m, water area and surrounding cultivated land account for 90%, soil porosity 40%-50%).

[0117] The final output includes ecological background unit raster data and a table showing the correspondence between unit number, factor combination, and spatial range.

[0118] This application's embodiments generate a discretization scheme using an optimal parameter geographic detector, aiming to maximize the explanatory power of factors for optimal conservation values. This avoids the problems of subjective classification and weak correlation with conservation functions in traditional discretization, ensuring the scientific nature of background factor discretization. A new preprocessing step of matching background factors with the discretization scheme is added to unify factor format and spatial scale, solving the problem of inconsistent input data formats and pixel misalignment leading to distorted clustering results in traditional clustering, thus improving the spatial consistency of ecological background units. The clustering algorithm is clearly defined to minimize intra-cluster variance and maximize inter-cluster differences. The elbow rule is used to determine the k-value, avoiding the problems of subjective setting of cluster size and large differences in ecological attributes within units in traditional clustering, ensuring the homogeneity of ecological background units.

[0119] In some embodiments, the optimal water conservation value and each factor in the initial factor pool are subjected to detection processing to obtain the dominant factor and background factor, including: performing factor detection processing on the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor, wherein the dominant factor is the factor whose explanatory power for the optimal water conservation value exceeds a preset explanatory power threshold.

[0120] Specifically, the optimal water conservation values ​​are stored in raster format. The initial factor pool is constructed using preprocessed ASCII format categorical / numerical raster data. Using ArcGIS's random point creation tool, 1000 evenly distributed sample points are generated within the target area. Then, using the extract multi-value to point tool, the optimal water conservation value and the attribute values ​​of 10 factors are assigned to the sample points, generating a CSV format sample dataset. Invalid samples containing NoData are removed.

[0121] When the q-value is greater than the preset explanatory power threshold or the p-value is less than 0.01 (passing the 99% confidence level significance test), annual rainfall (q=0.42), annual maximum NDVI (q=0.38), and vegetation cover (q=0.31) meet the criteria and are identified as the dominant factors.

[0122] Furthermore, interactive probing is performed on each factor in the initial factor pool to obtain background factors, which are factors whose nonlinear enhancement frequency is higher than a preset frequency threshold.

[0123] Specifically, interaction detection determines the type of interaction by calculating the explanatory power of the interaction after combining two factors. The types of interaction include nonlinear enhancement, synergistic enhancement, independent interaction, and antagonistic interaction.

[0124] The background factor is defined as the factor whose nonlinear enhancement frequency is higher than a preset frequency threshold, which is 2 times.

[0125] Altitude (frequency 3), soil porosity (frequency 2), and land use type (frequency 2) meet the nonlinear enhancement frequency > 2 standard and are identified as background factors.

[0126] This application employs factor probing combined with q-value thresholding and significance testing to screen dominant factors. By replacing subjective judgment with quantitative indices and statistical tests, it addresses the problems of traditional dominant factor screening relying on experience and lacking quantitative evidence, ensuring that dominant factors truly reflect the core driving role. Furthermore, it uses interactive probing combined with nonlinear enhanced frequency thresholding to screen background factors, focusing on elements with strong synergistic effects with other factors. This solves the problem of traditional background factor identification neglecting inter-factor synergistic effects and only considering the impact of a single factor, clarifying the supporting role of background factors in the ecosystem and improving the dominant-background factor system.

[0127] In some embodiments, the dominant factor and ecological background unit are partitioned to obtain a theoretical joint partition, including: performing matching preprocessing on the dominant factor and the optimal discretization scheme to obtain the preprocessed dominant factor.

[0128] Specifically, based on the determined dominant factors (annual rainfall, annual maximum NDVI, and vegetation cover), a geospatial detector with the same optimal parameters as the background factors is used to generate a scheme based on the principle of maximizing the explanatory power (q value) of the factors for the optimal water conservation value.

[0129] The data input consists of the original raster data of the dominant factors (annual rainfall: mm, annual maximum NDVI: no unit, vegetation coverage: %) and the determined optimal water conservation value raster.

[0130] For each dominant factor, try 3-4 classes of equidistant / natural breakpoint partitions and calculate the q-value for each class.

[0131] The scheme with the largest q value is selected as the optimal discretization scheme.

[0132] The three dominant factor classification values ​​were all resampled to 1km×1km.

[0133] The dominant factor raster is clipped using the boundary of the target area to remove invalid data outside the area, ensuring that the spatial extent of the dominant factor and the ecological background unit completely overlaps.

[0134] The final output consists of three preprocessed dominant factor rasters, providing standardized input for classification overlay.

[0135] Furthermore, the preprocessed dominant factors and ecological background units are partitioned to obtain a theoretical joint partition.

[0136] Based on the q-values ​​of the dominant factors (annual rainfall 0.42 > annual maximum NDVI 0.38 > vegetation cover 0.31), the superposition priority was determined as follows: annual rainfall (first priority) → annual maximum NDVI (second priority) → vegetation cover (third priority). The rationale for this priority setting is that the higher the q-value, the stronger the dominant effect of the factor on water conservation. Superposition first ensures that its impact on the zoning is reflected preferentially, avoiding interference from secondary factors with core differences (e.g., first distinguishing between high and low rainfall areas, and then distinguishing between high and low NDVI areas within the same rainfall area).

[0137] For example, the high-altitude forest type (3) + high rainfall (3) + high NDVI (3) (number 333.3) zoning should be concentrated in the high precipitation area and concentrated forest area of ​​the hydrological mean map, with a spatial overlap of ≥85%, to ensure that it conforms to the actual ecological characteristics.

[0138] The final output is the theoretical joint partitioning result, which includes: Theoretical joint partitioned raster: 1km×1km resolution, WGS84 coordinate system, cell value is a unique partition number (retaining 1 decimal place).

[0139] The partition attribute table includes fields such as partition number, ecological background unit, dominant factor combination, naming, and number of pixels, which clearly define the core characteristics of each partition.

[0140] Spatial distribution map: The partition raster is rendered by ArcGIS, with different numbers corresponding to different colors, which intuitively shows the spatial distribution of the partition.

[0141] This application's embodiments match the optimal discretization scheme through preprocessing of the dominant factor, ensuring that the discretization logic of the dominant factor and the background factor is consistent. This solves the problems of inconsistent discretization standards and poor adaptability to background units in traditional superposition, improving the logical consistency of the superposition results. The superposition priority is determined according to the q-value of the dominant factor, ensuring that the influence of the core driving elements is reflected first. This avoids the problems of random sorting and interference from secondary factors with core differences in traditional superposition, enabling theoretical partitioning to clearly reflect the hierarchical influence of the core driving force and background endowment.

[0142] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in this embodiment is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in this embodiment or the accompanying drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0143] like Figure 3 As shown in the illustration, this application also provides an identification device 300 for water conservation and ecological restoration zones. The device includes: The acquisition module 301 is used to acquire the water conservation capacity of the target area and the factors affecting water conservation. The factors affecting water conservation include at least one of topography, soil, climate, vegetation and human activities.

[0144] The processing module 302 is used to screen and detect the water conservation capacity and the factors affecting water conservation, so as to obtain the optimal water conservation value, the dominant factor and the background factor.

[0145] The processing module 302 is also used to perform clustering and classification overlay processing on the background factors to obtain the processed background factors, and to perform partitioning processing on the processed background factors and the dominant factors to obtain multiple effective ecological partition units.

[0146] The processing module 302 is also used to perform statistical quantification on the optimal water conservation value and the water conservation amount corresponding to each effective ecological zone unit, so as to obtain the water conservation potential value and potential surplus of each effective ecological zone unit.

[0147] The identification module 303 is also used to classify the priority level of ecological restoration according to the water source conservation potential value and the potential surplus, and to identify the water source conservation and ecological restoration areas based on the ecological restoration priority level to obtain the identification results.

[0148] In some embodiments, the processing module 302 is further configured to perform time series screening processing on the water conservation capacity of the target area to obtain the optimal water conservation value, which is used to characterize the optimal ecological environment state of the target area during the observation period.

[0149] The processing module 302 is also used to screen and process the factors affecting water conservation to obtain basic topographic elements, soil hydrological elements, climate condition elements, vegetation ecological elements and human intervention elements.

[0150] The processing module 302 is also used to remove and integrate basic topographic elements, soil and hydrological elements, climate conditions, vegetation and ecological elements, and human intervention elements to obtain an initial factor pool.

[0151] The processing module 302 is also used to detect and process the optimal water source conservation value and each factor in the initial factor pool to obtain the dominant factor and background factor.

[0152] In some embodiments, the acquisition module 301 is further configured to acquire the optimal discretization scheme, preprocess the background factor and the optimal discretization scheme and perform clustering processing to obtain ecological background units.

[0153] The processing module 302 is also used to partition the dominant factors and ecological background units to obtain theoretical joint partitions.

[0154] The processing module 302 is also used to perform invalid factor combination elimination processing on the theoretical joint partition to obtain multiple valid ecological partition units.

[0155] In some embodiments, the acquisition module 301 is further configured to acquire the optimal discretization scheme generated by the optimal parameter geographic detector.

[0156] The processing module 302 is also used to perform matching preprocessing on the background factor and the optimal discretization scheme to obtain the preprocessed background factor.

[0157] The processing module 302 is also used to perform clustering processing on the preprocessed background factors using a clustering algorithm to obtain ecological background units. The clustering algorithm aims to minimize intra-class variance and maximize inter-class differences.

[0158] In some embodiments, the processing module 302 is further configured to perform factor detection processing on the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor, wherein the dominant factor is the factor whose explanatory power for the optimal water conservation value exceeds a preset explanatory power threshold.

[0159] The processing module 302 is also used to perform interactive detection processing on each factor in the initial factor pool to obtain background factors, which are factors whose nonlinear enhancement frequency is higher than a preset frequency threshold.

[0160] In some embodiments, the processing module 302 is further configured to perform matching preprocessing on the dominant factor and the optimal discretization scheme to obtain the preprocessed dominant factor.

[0161] The processing module 302 is also used to partition the preprocessed dominant factors and ecological background units to obtain theoretical joint partitions.

[0162] Some modules in the apparatus described in this application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0163] The apparatus or module described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. For ease of description, the above apparatus is described by dividing it into various modules according to their functions. When implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware. Of course, a module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0164] The methods, apparatus, or modules described in this application can be implemented in a computer-readable program code manner. The controller can be implemented in any suitable manner, such as a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of a memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code manner, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included within it for implementing various functions can also be considered as structures within the hardware component. Alternatively, the device used to implement various functions can be viewed as either a software module that implements the method or a structure within a hardware component.

[0165] This application also provides an apparatus, the apparatus comprising: a processor; a memory for storing processor-executable instructions; wherein, when the processor executes the executable instructions, it implements the method described in this application.

[0166] This application also provides a non-volatile computer-readable storage medium storing a computer program or instructions thereon, which, when executed, enables the method described in this application embodiment to be implemented.

[0167] Furthermore, in the various embodiments of the present invention, each functional module can be integrated into a processing module, or each module can exist independently, or two or more modules can be integrated into a single module.

[0168] The aforementioned storage media include, but are not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions.

[0169] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, or it can be embodied in the process of data migration. The computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0170] The various embodiments described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. All or part of this application can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, mobile communication terminals, multiprocessor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices, etc.

[0171] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of this application.

Claims

1. A method for identifying a water source conservation and ecological restoration area, characterized in that, The method comprises the following steps: obtaining water conservation and water conservation influencing factors of a target area, the water conservation influencing factors comprising at least one of terrain, soil, climate, vegetation and human activities; screening and detecting the water conservation and the water conservation influencing factors to obtain optimal water conservation values, dominant factors and background factors; clustering and classifying the background factors to obtain processed background factors, and performing zoning processing on the processed background factors and the dominant factors to obtain a plurality of effective ecological zoning units; performing statistical and quantitative processing on the optimal water conservation values and water conservation of each effective ecological zoning unit to obtain water conservation potential values and potential surplus of each effective ecological zoning unit; dividing ecological restoration priority levels according to the water conservation potential values and the potential surplus, identifying water conservation and ecological restoration areas based on the ecological restoration priority levels to obtain an identification result.

2. The method of claim 1, wherein, The screening and detecting of the water conservation and the water conservation influencing factors to obtain optimal water conservation values, dominant factors and background factors comprises: performing time series screening processing on the water conservation of the target area to obtain optimal water conservation values, the optimal water conservation values being used to represent the optimal state of the ecological environment in the observation period of the target area; performing screening processing on the water conservation influencing factors to obtain terrain basic factors, soil hydrological factors, climate condition factors, vegetation ecological factors and human intervention factors; performing elimination and integration processing on the terrain basic factors, the soil hydrological factors, the climate condition factors, the vegetation ecological factors and the human intervention factors to obtain an initial factor pool; performing detection processing on the optimal water conservation values and each factor in the initial factor pool to obtain dominant factors and background factors.

3. The method of claim 1, wherein, The clustering and classifying of the background factors to obtain processed background factors, and the zoning processing of the processed background factors and the dominant factors to obtain a plurality of effective ecological zoning units comprises: obtaining an optimal discretization scheme, and performing preprocessing and clustering processing on the background factors and the optimal discretization scheme to obtain ecological background units; performing zoning processing on the dominant factors and the ecological background units to obtain theoretical joint zoning; performing invalid factor combination elimination processing on the theoretical joint zoning and the dominant factors to obtain a plurality of effective ecological zoning units.

4. The method of claim 3, wherein, The obtaining of the optimal discretization scheme, and the preprocessing and clustering processing of the background factors and the optimal discretization scheme to obtain ecological background units comprises: obtaining an optimal discretization scheme generated by an optimal parameter geographic detector; performing matching preprocessing on the background factors and the optimal discretization scheme to obtain preprocessed background factors; performing clustering processing on the preprocessed background factors by a clustering algorithm to obtain ecological background units, the clustering algorithm aiming to minimize intra-class variance and maximize inter-class difference.

5. The method of claim 2, wherein, The detecting the optimal water conservation value and each factor in the initial factor pool comprises: The factor detecting processing is performed on the optimal water conservation value and each factor in the initial factor pool to obtain the dominant factor, and the dominant factor is a factor whose explanation to the optimal water conservation value exceeds a preset explanation threshold; The interaction detecting processing is performed on each factor in the initial factor pool to obtain the background factor, and the background factor is a factor whose nonlinear enhancement action frequency is higher than a preset frequency threshold.

6. The method of claim 3, wherein, The partition processing is performed on the dominant factor and the ecological background unit to obtain a theoretical joint partition, and the partition processing comprises: The matching preprocessing is performed on the dominant factor and the optimal discretization scheme to obtain a preprocessed dominant factor; The partition processing is performed on the preprocessed dominant factor and the ecological background unit to obtain the theoretical joint partition.

7. The method of claim 1, wherein, The effective ecological partition unit comprises a priority repair area, a key improvement area, a moderate optimization area, and a present situation maintenance area.

8. An identification device for water conservation and ecological restoration areas for implementing the method according to any one of claims 1 to 7, characterized in that, Comprises: An acquisition module is configured to acquire water conservation and water conservation influencing elements of a target area, wherein the water conservation influencing elements comprise at least one of terrain, soil, climate, vegetation, and human activities; A processing module is configured to perform screening and detecting processing on the water conservation and the water conservation influencing elements to obtain an optimal water conservation value, a dominant factor, and a background factor; The processing module is further configured to perform clustering and classification superimposition processing on the background factor to obtain a processed background factor, and perform partition processing on the processed background factor and the dominant factor to obtain a plurality of effective ecological partition units; The processing module is further configured to perform statistical quantification processing on the optimal water conservation value and water conservation corresponding to each effective ecological partition unit to obtain a water conservation potential value and a potential surplus corresponding to each effective ecological partition unit; An identification module is further configured to divide an ecological repair priority level according to the water conservation potential value and the potential surplus, identify a water conservation and ecological repair area based on the ecological repair priority level, and obtain an identification result. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the computer device is characterized in that, The processor executes the program to implement the steps of the method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 7.

Images