A Method for Assessing Regional Ecological Restoration Potential Based on Multidimensional Data

Abstract

The present application relates to the technical field of ecological assessment, and particularly relates to a regional ecological restoration potential assessment method based on multidimensional data, comprising: collecting pH, moisture and nutrients; calculating micro-abnormal index and type, and determining micro-sub-regions; collecting vegetation index and coverage of the micro-sub-regions; calculating meso-abnormal index, and determining meso-sub-regions; collecting precipitation and temperature of the meso-sub-regions; calculating macro-adaptation index, and determining index mode; calculating potential index, and determining macro-abnormal sub-regions; calculating macro-sub-region aggregation, and adjusting weight; and generating a restoration potential assessment report. The present application effectively integrates micro-environmental indicators, vegetation conditions and meteorological conditions through step-by-step collection and analysis of multidimensional data, forms a hierarchical assessment system from micro to macro, and effectively solves the problem of low accuracy of assessing regional vegetation restoration potential due to reliance on only a single static indicator and a rough model.

Description

Technical Field

[0001] This invention relates to the field of ecological assessment technology, and in particular to a method for assessing regional ecological restoration potential based on multidimensional data. Background Technology

[0002] With the continuous changes in the global ecological environment and the sustained intensification of human activities, the stability and resilience of regional ecosystems have been severely affected, and ecological degradation has become an increasingly prominent problem. Faced with complex and diverse natural conditions and environmental disturbances, how to scientifically and systematically assess the ecological restoration potential of different regions has become a key challenge in the process of ecological governance and sustainable development.

[0003] Chinese Patent Application Publication No. CN120297548A discloses a method and system for assessing the potential for vegetation carbon sequestration restoration in power transmission corridors. The method includes: establishing a baseline database for the target area of ​​the proposed power transmission corridor construction; acquiring vector spatial data and statistical data of the target area, including topographic vector maps, power infrastructure distribution data, meteorological data, and vegetation distribution data; marking the target area into multiple sub-regions based on the safety requirements for power transmission line operation and a vegetation classification system, and associating these with parameters such as voltage level, line corridor length, number of tower bases, and minimum vertical distance between conductors and trees; and generating projections for each sub-region based on land use. Recommended vegetation types, vegetation height limits, carbon density, and grid security correction factor data; land parcel unit division and vegetation scheme matching: based on land use changes before and after transmission channel construction, each sub-region is divided into land parcel units; at least one recommended vegetation type scheme is matched for each land parcel unit, and the corresponding carbon sink accounting factor is associated; carbon sink recovery potential is calculated: based on the carbon sink measurement method, the carbon sink loss of each land parcel unit due to the destruction of the original vegetation caused by the construction of the transmission channel is calculated; combined with the grid security correction factor, the new carbon sink amount of each land parcel unit under the recommended vegetation scheme is calculated; the overall vegetation carbon sink recovery potential of the transmission channel is evaluated through the net carbon sink formula.

[0004] Therefore, the proposed method for assessing the carbon sequestration potential of vegetation along power transmission corridors has the following problems: Data acquisition and processing are complex, involving multi-source spatial data, statistical data, and vegetation classification information. Data integration and updating are difficult, easily leading to delayed or inaccurate assessment results. In the process of sub-regional division and plot unit matching, it relies solely on static land use and recommended vegetation types, lacking the ability to dynamically respond to changes in environmental factors (such as climate, water conditions, and soil nutrients), and thus failing to accurately reflect vegetation growth suitability. The carbon sequestration calculation process is based on static carbon density and correction factors, lacking comprehensive consideration of micro and meso-level ecological conditions, and failing to capture the differences in vegetation restoration potential at different scales. The application of power grid safety correction factors is relatively crude, failing to fully consider the impact of different terrains, corridor characteristics, and the surrounding environment of tower foundations on vegetation growth and carbon sequestration restoration. Summary of the Invention

[0005] To address this, the present invention provides a method for assessing regional ecological restoration potential based on multidimensional data. This method overcomes the problem of low accuracy in assessing regional vegetation restoration potential caused by relying solely on a single static indicator and a coarse model in existing technologies by comprehensively collecting and dynamically analyzing micro, meso, and macro ecological parameters.

[0006] To achieve the above objectives, on the one hand, the present invention provides a method for assessing regional ecological restoration potential based on multidimensional data, comprising:

[0007] Real-time data collection of pH, moisture content, and nutrient content of each sub-region to be observed within the observation area;

[0008] The microscopic anomaly index and microscopic anomaly type are determined based on the pH, moisture content and nutrient content, and several microscopic anomaly sub-regions are determined based on the microscopic anomaly index.

[0009] Real-time collection of normalized vegetation index and vegetation cover of each of the aforementioned micro-anomaly sub-regions;

[0010] The mesoscopic anomaly index is determined based on the normalized vegetation index and the vegetation coverage, and several mesoscopic anomaly sub-regions are determined based on the mesoscopic anomaly index and the microscopic anomaly type.

[0011] Real-time collection of precipitation and temperature in each of the aforementioned mesoscopic anomaly sub-regions;

[0012] The macro-adaptation index is determined based on the precipitation and temperature, and the index calculation mode is determined based on the meso-anomaly index and the micro-anomaly index.

[0013] The potential index is determined based on the index calculation model, the macro-adaptation index, the meso-anomaly index, the micro-anomaly index, and the preset potential weight reorganization, and several macro-anomaly sub-regions are determined based on the potential index.

[0014] The degree of clustering is determined based on the distribution location of the macro-abnormal sub-regions, and the preset potential weight reorganization is adjusted based on the degree of clustering and the index calculation mode.

[0015] A recovery potential assessment report is generated based on the potential index that has been redefined after the adjustment of the preset potential weights.

[0016] Furthermore, the process of determining the microscopic anomaly index and microscopic anomaly type based on the pH, moisture content, and nutrient content includes:

[0017] The pH, water content, nutrient content, and corresponding preset microscopic threshold of each of the sub-regions to be observed are compared to obtain several corresponding microscopic deviations.

[0018] The micro-abnormality index is calculated based on each of the aforementioned micro-deviation degrees and the preset micro-weighted reorganization;

[0019] The micro-anomaly type is determined based on the highest value among all the micro-deviations.

[0020] Furthermore, the process of determining several micro-anomaly sub-regions based on micro-anomaly indices includes:

[0021] When the micro-anomaly index is greater than a preset micro-anomaly threshold, the sub-region to be observed is determined to be the micro-anomaly sub-region.

[0022] Furthermore, the process of determining the mesoscopic anomaly index based on the normalized vegetation index and the vegetation cover includes:

[0023] The normalized vegetation index and vegetation coverage of each of the micro-anomaly sub-regions are compared with the corresponding preset meso-level thresholds to obtain several corresponding meso-level deviations.

[0024] The meso-level anomaly index is calculated based on the aforementioned meso-level deviation and the preset meso-level weighted reorganization.

[0025] Furthermore, the process of determining several meso-level anomaly sub-regions based on the meso-level anomaly index and the micro-level anomaly type includes:

[0026] When the meso-level anomaly index is greater than the preset meso-level anomaly threshold, the anomaly cause type of the micro-level anomaly sub-region is determined according to the corresponding micro-level anomaly type.

[0027] Several meso-level anomalous sub-regions are determined based on the anomalous cause types of other micro-level anomalous sub-regions within a preset determination range centered on each of the aforementioned micro-level anomalous sub-regions.

[0028] Furthermore, the process of determining several mesoscopic anomaly sub-regions based on the anomaly cause types of other microscopic anomaly sub-regions within a preset determination range centered on each of the aforementioned microscopic anomaly sub-regions includes:

[0029] The micro-anomaly sub-regions are designated as central regions in descending order of their micro-anomaly indices.

[0030] When the anomaly cause type of the central region is the same as that of other micro-anomaly sub-regions within the preset determination range, the central region and the other micro-anomaly sub-regions are merged to generate the meso-anomaly sub-region.

[0031] When the spatial overlap rate between the newly generated meso-level anomalous sub-region and the existing meso-level anomalous sub-region is greater than a preset overlap threshold, they are merged into one meso-level anomalous sub-region.

[0032] After merging into one meso-level anomalous sub-region, the meso-level anomalous index of the merged meso-level anomalous sub-region is updated by weighted averaging the area and meso-level anomalous index of each meso-level anomalous sub-region before merging.

[0033] The micro-anomaly sub-regions that have already been merged will not participate in subsequent merging.

[0034] Furthermore, the process of determining the macro-adaptation index based on the precipitation and temperature, and determining the index calculation model based on the meso-anomaly index and the micro-anomaly index, includes:

[0035] The precipitation and temperature of each of the mesoscopic anomaly sub-regions are compared with the corresponding preset macroscopic thresholds to obtain several corresponding macroscopic deviations.

[0036] The macroeconomic adaptation index is calculated based on the aforementioned macroeconomic deviation and the preset macroeconomic weighting.

[0037] When the average value of all the meso-level anomaly indices is greater than a preset meso-level average threshold and the average value of all the micro-level anomaly indices is within the range of a preset micro-level average threshold, the index calculation mode is determined to be the meso-macro mode.

[0038] When the average value of all the micro-anomaly indices is greater than the maximum value of the preset micro-average threshold range, and the average value of all the meso-anomaly indices is less than or equal to the preset meso-average threshold, the index calculation mode is determined to be micro-macro mode.

[0039] When the average of all the meso-level anomaly indices is greater than a preset meso-level average threshold, and the average of all the micro-level anomaly indices is greater than the maximum value of the preset micro-level average threshold range, the index calculation mode is determined to be micro-meso-level mode.

[0040] Furthermore, the process of determining a potential index based on the index calculation model, the macro-adaptation index, the meso-anomaly index, the micro-anomaly index, and a preset potential weighting, and then determining several macro-anomaly sub-regions based on the potential index, includes:

[0041] When the index calculation mode is the macro-meta mode, the potential index is calculated based on the macro-adaptation index, the meso-anomaly index, and the preset potential weight reorganization.

[0042] When the index calculation mode is the micro-macro mode, the potential index is calculated based on the macro adaptation index, the micro anomaly index, and the preset potential weight reorganization.

[0043] When the index calculation mode is the micro-medium mode, the potential index is calculated based on the meso-level anomaly index, the micro-level anomaly index, and the preset potential weight reorganization.

[0044] When the potential index is greater than a preset potential index threshold, the meso-level anomaly sub-region is determined to be the macro-level anomaly sub-region.

[0045] Furthermore, the process of determining the clustering degree based on the distribution location of the macroscopic anomaly sub-regions, and adjusting the preset potential weight reorganization based on the clustering degree and the index calculation mode, includes:

[0046] Calculate the Euclidean distance from the center of each of the macroscopic anomaly sub-regions to a preset reference point to obtain several distribution distances;

[0047] The degree of clustering is obtained by calculating the reciprocal of the standard deviation of all the distribution distances.

[0048] When the aggregation degree is greater than the preset aggregation threshold, the number of potential indices calculated according to the medium-macro mode, the micro-macro mode and the micro-medium mode are counted to obtain the number of medium-macro, micro-macro and micro-medium indices.

[0049] The preset potential weight reorganization is adjusted based on the maximum value of the number of macro-medium, the number of micro-macro, and the number of micro-medium, the aggregation degree, and the preset aggregation threshold.

[0050] On the other hand, the present invention also provides a regional ecological restoration potential assessment system based on multidimensional data, comprising:

[0051] The first acquisition module is used to collect the pH, water content and nutrient content of each sub-region to be observed in real time within the observation area;

[0052] A microscopic determination module, connected to the first acquisition module, is used to determine the microscopic anomaly index and microscopic anomaly type based on the pH, the moisture content and the nutrient content, and to determine several microscopic anomaly sub-regions based on the microscopic anomaly index.

[0053] The second acquisition module is connected to the microscopic determination module and is used to acquire the normalized vegetation index and vegetation coverage of each microscopic anomaly sub-region in real time.

[0054] The mesoscopic determination module is connected to the second acquisition module and is used to determine the mesoscopic anomaly index based on the normalized vegetation index and the vegetation coverage, and to determine several mesoscopic anomaly sub-regions based on the mesoscopic anomaly index and the microscopic anomaly type.

[0055] The third acquisition module is connected to the mesoscopic determination module and is used to acquire precipitation and temperature in each of the mesoscopic anomaly sub-regions in real time.

[0056] The mode determination module is connected to the third acquisition module, the micro-determination module and the meso-determination module respectively, and is used to determine the macro-adaptation index based on the precipitation and the temperature, and to determine the index calculation mode based on the macro-adaptation index, the meso-anomaly index and the micro-anomaly index.

[0057] A macro-determination module, connected to the pattern determination module, is used to determine a potential index based on the index calculation mode, the macro-adaptation index, the meso-anomaly index, the micro-anomaly index, and a preset potential weight reorganization, and to determine several macro-anomaly sub-regions based on the potential index.

[0058] An adjustment module, connected to the macro determination module, is used to determine the clustering degree based on the distribution location of the macro abnormal sub-regions, and to adjust the preset potential weight reorganization based on the clustering degree and the index calculation mode.

[0059] A generation module, connected to the macro-determination module, is used to generate a recovery potential assessment report based on the potential index re-determined after adjusting the preset potential weights.

[0060] Compared with existing technologies, the advantages of this invention lie in its ability to effectively integrate micro-environmental indicators, vegetation conditions, and meteorological conditions through multi-dimensional data collection and analysis, forming a hierarchical assessment system from micro to macro levels. At the micro level, pH, moisture content, and nutrient content are used to reveal the potential stress and abnormal characteristics of soil and vegetation. At the meso level, normalized vegetation index and cover reflect the spatial aggregation and health status of ecological responses. At the macro level, precipitation and temperature are considered in conjunction with the region's adaptability to climatic conditions. Through dynamic selection of the index calculation model and cluster-driven weight adjustment, the potential index is calculated with precision, ensuring that the interaction between indicators at each level fully reflects the contribution and constraint relationships of different ecological factors. The final output of the restoration potential assessment result accurately reflects the possibility of regional ecological restoration and priority restoration areas, providing a quantitative basis for the scientific formulation of ecological management and restoration strategies. This effectively solves the problem of low accuracy in assessing regional vegetation restoration potential due to reliance on a single static indicator and a coarse model.

[0061] Furthermore, by comparing the pH, moisture content, and nutrient content of each sub-region with preset thresholds, the degree of deviation of the microenvironment is quantified, and a micro-anomaly index is calculated by combining weights. This index can accurately reflect the local pressure and potential anomalies in the soil environment. At the same time, by selecting the highest deviation value to determine the type of micro-anomaly, the most critical environmental limiting factors can be identified, providing a scientific basis for subsequent meso- and macro-level restoration potential assessments. This achieves effective connection and quantitative analysis from micro-environmental conditions to ecological restoration potential.

[0062] Furthermore, by setting a micro-anomaly threshold and comparing it with the micro-anomaly index, this embodiment can effectively identify sub-regions where key factors such as soil acidity / alkalinity, moisture content, or nutrients significantly deviate from the suitable range. Marking these regions as micro-anomaly sub-regions can reflect the mutual influence and constraint relationships between various environmental parameters. For example, insufficient soil moisture may exacerbate nutrient absorption limitations, while acid-base imbalance may affect plant root growth. This allows for accurate identification of key areas with limited ecological restoration at the micro level, providing a reliable basis for subsequent comprehensive analysis at the meso and macro levels, and enabling refined classification of potential assessment.

[0063] Furthermore, by comparing the normalized vegetation index and vegetation cover of micro-anomaly sub-regions with preset meso-level thresholds, the degree of deviation between vegetation growth status and ideal growth conditions in each region can be quantified. Combined with preset meso-level weighted recombination to calculate the meso-level anomaly index, the contribution of different vegetation indicators to ecological restoration potential can be comprehensively reflected, areas with insufficient or abnormal vegetation growth can be accurately identified, and quantitative basis can be provided for subsequent meso- and macro-level ecological assessments, so that the correlation between vegetation status, cover and factors such as soil and water can be reasonably reflected.

[0064] Furthermore, by combining meso-level anomaly indices with micro-level anomaly types, and aggregating the anomaly cause types of adjacent sub-regions with micro-level anomaly sub-regions as the center, this embodiment can identify continuous regions with the same ecological limiting causes at the meso-level, thereby reflecting the cumulative effect of micro-level anomaly factors on ecological restoration at a larger spatial scale, achieving accurate delineation of potential barrier areas, and providing a reliable spatial basis for subsequent macro-level restoration potential assessment.

[0065] Furthermore, by merging adjacent micro-anomaly sub-regions with the same anomaly cause type, centered on sub-regions with higher micro-anomaly indices, continuous regions with clear ecological anomaly characteristics can be formed at the meso-scale. At the same time, the meso-scale anomaly index is updated by area-weighted averaging of spatially overlapping parts, so that the generated meso-scale anomaly sub-regions can truly reflect the strength and distribution of local ecological pressure, taking into account both anomaly intensity and spatial coherence, and providing more accurate and stable basic data for subsequent potential assessment.

[0066] Furthermore, by converting precipitation and temperature deviations into a macro-adaptation index and combining it with the average values ​​of meso- and micro-anomaly indices for stratified determination, dynamic adaptation to multi-scale environmental factors is achieved. When meso-level anomalies are significant while micro-level fluctuations are within a reasonable range, the system enters a meso-macro mode to highlight the dominant role of the overall regional environment in macro-adaptation; when micro-anomalies are significant while meso-level changes are weak, the system enters a micro-macro mode to emphasize the impact of local details on macro-level performance; and when both meso- and micro-anomalies are significant, the system enters a micro-meso mode to reflect the cumulative effect of multi-level factors. This method, through the mutual constraints and weighted combinations of parameters, allows for flexible switching of the determination logic, ensuring that the index calculation results reflect both overall trends and capture local anomalies, thereby improving the accuracy and robustness of the adaptive assessment.

[0067] Furthermore, by introducing macro-adaptation index, meso-anomaly index, micro-anomaly index, and preset potential weighting in combination under different index calculation modes, a dynamic balance of causal relationship and hierarchical progression can be achieved among multi-level indicators. This allows the potential index to reflect the adaptability of macro-environmental conditions while integrating the abnormal fluctuation characteristics of meso- and micro-scales. Thus, when the potential index exceeds the preset threshold, the macro-anomaly sub-region can be accurately identified, avoiding the bias caused by a single parameter and improving the accuracy and stability of regional anomaly identification.

[0068] Furthermore, by calculating the distribution distance of macro-anomaly sub-regions relative to a preset reference point and the reciprocal of its standard deviation, the clustering degree can be obtained, which can intuitively reflect the spatial concentration of anomaly regions. When the clustering degree exceeds a preset threshold, the number of potential indices under different calculation models is counted, which helps to identify the main factors affecting ecological restoration potential at the micro, meso, and macro levels. Based on the clustering degree, model distribution, and threshold, the preset potential weighting can be dynamically adjusted to reasonably enhance or weaken the influence of indicators at each level in the calculation of potential indices, so that the potential index can more accurately reflect the actual situation of regional ecological restoration and ensure that the evaluation results can take into account both spatial distribution characteristics and the comprehensive effect of multi-dimensional indicators.

[0069] Furthermore, through multi-level and multi-dimensional data collection and analysis, key ecological parameters such as soil pH, moisture content, nutrient content, vegetation index, vegetation cover, precipitation, and temperature can be comprehensively processed to achieve hierarchical identification and aggregation of micro, meso, and macro anomalies. By calculating the potential index and adjusting the aggregation degree, the weights of ecological anomalies of different scales and types can be reasonably allocated, thereby accurately reflecting the ecological restoration potential of each region. This enables refined judgment and scientific regulation of potential risk areas, providing quantitative, dynamic, and operable decision-making basis for regional ecological restoration. Attached Figure Description

[0070] Figure 1 This is a flowchart of the regional ecological restoration potential assessment method based on multidimensional data in this embodiment;

[0071] Figure 2 This embodiment defines the logic diagram for determining microscopic anomaly sub-regions.

[0072] Figure 3 This embodiment provides a logic diagram for determining the type of abnormality.

[0073] Figure 4 The determination logic diagram for the macro mode in this embodiment is shown. Detailed Implementation

[0074] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0075] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0076] On the one hand, please refer to Figure 1 The diagram shows a flowchart of the regional ecological restoration potential assessment method based on multidimensional data in this embodiment. This embodiment provides a method for assessing regional ecological restoration potential based on multidimensional data, including: real-time acquisition of pH, water content, and nutrient content of each sub-region to be observed within the observation area; determining a micro-anomaly index and micro-anomaly type based on the pH, water content, and nutrient content, and determining several micro-anomaly sub-regions based on the micro-anomaly index; real-time acquisition of the normalized vegetation index and vegetation cover of each of the micro-anomaly sub-regions; determining a meso-anomaly index based on the normalized vegetation index and vegetation cover, and determining several meso-anomaly sub-regions based on the meso-anomaly index and the micro-anomaly type. The system identifies several anomalous sub-regions. It collects precipitation and temperature data in each of the aforementioned meso-anomaly sub-regions in real time. A macro-adaptation index is determined based on the precipitation and temperature, and an index calculation mode is determined based on the meso-anomaly index and the micro-anomaly index. A potential index is determined based on the index calculation mode, the macro-adaptation index, the meso-anomaly index, the micro-anomaly index, and a preset potential weight reorganization. Several macro-anomaly sub-regions are identified based on the potential index. The clustering degree is determined based on the distribution location of the macro-anomaly sub-regions, and the preset potential weight reorganization is adjusted based on the clustering degree and the index calculation mode. A recovery potential assessment report is generated based on the re-determined potential index after adjusting the preset potential weight reorganization.

[0077] In this embodiment, micro-anomaly type refers to the local ecological state anomaly type determined based on soil parameters such as pH, moisture content, and nutrient content; meso-anomaly type refers to the regional ecological anomaly type determined based on micro-anomaly sub-regions combined with normalized vegetation index and vegetation cover; macro-anomaly type refers to the overall ecological anomaly type determined based on meso-anomaly sub-regions combined with precipitation and temperature; and the potential index integrates the macro-adaptation index, meso-anomaly index, and micro-anomaly index, combined with preset weights to reflect the ecological restoration potential of each sub-region, thereby quantifying the restoration priority and potential differences of different regions.

[0078] In this embodiment, data acquisition is achieved through multi-source sensing and remote sensing technologies. Specifically, soil monitoring devices are used to obtain the pH, moisture content, and nutrient content of each sub-region in real time. For micro-anomaly sub-regions, normalized vegetation index and vegetation cover are extracted by calling UAV or satellite remote sensing data. For meso-anomaly sub-regions, precipitation and temperature are obtained in real time through meteorological monitoring devices, thereby forming multi-dimensional and multi-level dynamic observation data.

[0079] The pre-defined potential weighting includes weights for the macro-adaptation index, the meso-anomaly index, and the micro-anomaly index. The macro-adaptation index weight depends on the degree of influence of regional climate adaptation capacity and is typically set between 0 and 1; in this embodiment, it is set to 0.4, reflecting the contribution of climate factors in the potential index calculation. The meso-anomaly index weight depends on the importance of vegetation cover and health status and is typically set between 0 and 1; in this embodiment, it is set to 0.35, reflecting the impact of meso-level ecological response on restoration potential. The micro-anomaly index weight depends on the degree of soil environmental anomaly and is typically set between 0 and 1; in this embodiment, it is set to 0.25, reflecting the contribution of micro-level environmental pressure to potential assessment.

[0080] In this embodiment, by adjusting the weights of the macro-adaptation index, the meso-anomaly index, and the micro-anomaly index, the contribution of each level of indicators in the potential index calculation is optimized. The recalculated potential index can comprehensively reflect the combined effects of soil environment, vegetation status, and climate adaptability. The final restoration potential assessment report clearly indicates the restoration potential level and priority restoration order of each region, providing a quantitative basis for ecological management and restoration decisions.

[0081] By collecting and analyzing multi-dimensional data at each level, micro-environmental indicators, vegetation status, and meteorological conditions are effectively integrated to form a hierarchical assessment system from micro to macro. At the micro level, pH, moisture content, and nutrient content are used to reveal the potential stress and abnormal characteristics of soil and vegetation. At the meso level, the normalized vegetation index and cover reflect the spatial aggregation and health status of ecological responses. At the macro level, precipitation and temperature are considered to assess the region's adaptability to climate conditions. Through dynamic selection of index calculation models and cluster-driven weight adjustments, the potential index is calculated with precision, ensuring that the interactions between indicators at each level fully reflect the contributions and constraints of different ecological factors. The final output of the restoration potential assessment results accurately reflects the possibility of regional ecological restoration and priority restoration areas, providing a quantitative basis for the scientific formulation of ecological management and restoration strategies. This effectively solves the problem of low accuracy in assessing regional vegetation restoration potential caused by relying solely on a single static indicator and a coarse model.

[0082] Specifically, the process of determining the micro-anomaly index and micro-anomaly type based on the pH, moisture content, and nutrient content includes: comparing the pH, moisture content, nutrient content, and corresponding preset micro-thresholds of each of the observed sub-regions to obtain several corresponding micro-deviation degrees; calculating the micro-anomaly index based on each micro-deviation degree and a preset micro-weighted recombination; and determining the micro-anomaly type based on the highest value among all the micro-deviation degrees.

[0083] In this embodiment, the preset microscopic thresholds include a pH threshold, a moisture content threshold, and a nutrient content threshold. The pH threshold is used to determine the soil's acid-base balance and depends on the suitable range for crop or vegetation growth, typically set between 5.5 and 7.5. In this embodiment, it is set between 6.0 and 7.5, which can identify abnormal areas of soil acidification or alkalization. The moisture content threshold is used to assess soil moisture conditions and depends on soil type and rainfall conditions, typically set between 15% and 40%, in this embodiment between 20% and 35%, which can determine the impact of soil drought or excessive moisture on ecological restoration. The nutrient content threshold is used to measure soil nutrient status and depends on the soil background values ​​of elements such as nitrogen, phosphorus, and potassium, typically set between 10 mg / kg and 50 mg / kg. In this embodiment, it is set between 15 mg / kg and 45 mg / kg, which can identify microscopic abnormal areas of soil nutrient deficiency or excess.

[0084] In this embodiment, the micro-deviation degree is obtained by calculating the absolute value of the difference between pH and pH threshold, or the absolute value of the difference between moisture content threshold and moisture content threshold, or the absolute value of the difference between nutrient content and nutrient content threshold. The subsequent deviation degree calculation will not be described in detail.

[0085] In this embodiment, the process of calculating the micro-abnormality index based on each micro-deviation degree and a preset micro-weighting reorganization includes: firstly, performing linear normalization on each micro-deviation degree to convert the micro-deviation degrees of different indicators to a unified dimensional range (such as 0 to 1), and then performing weighted summation calculation in combination with the preset micro-weighting reorganization to obtain the micro-abnormality index.

[0086] In this embodiment, the micro-anomaly types specifically include three categories: acid-base anomaly, moisture content anomaly, and nutrient anomaly. When the acid-base deviation from the threshold is the largest, it is determined to be an acid-base anomaly, reflecting the soil acidification or alkalization status. When the moisture content deviation from the threshold is the largest, it is determined to be a moisture content anomaly, reflecting the soil over-wetness or drought stress. When the nutrient content deviation from the threshold is the largest, it is determined to be a nutrient anomaly, reflecting the deficiency or excess of elements such as nitrogen, phosphorus, and potassium. Each type of micro-anomaly can identify the main micro-environmental factors that limit the ecological restoration potential of the sub-region and provide a basis for the determination of meso-level anomalies and the calculation of potential indices.

[0087] By comparing the pH, moisture content, and nutrient content of each sub-region with preset thresholds, the degree of deviation of the microenvironment is quantified. Combined with weighted calculations, a micro-anomaly index is obtained, which can accurately reflect the local pressure and potential anomalies of the soil environment. At the same time, by selecting the highest deviation value to determine the type of micro-anomaly, the most critical environmental limiting factors can be identified, providing a scientific basis for subsequent meso- and macro-level restoration potential assessments, and achieving effective connection and quantitative analysis from micro-environmental conditions to ecological restoration potential.

[0088] Please see Figure 2 As shown, it is the determination logic diagram for determining micro-abnormal sub-regions in this embodiment. The process of determining several micro-abnormal sub-regions based on the micro-abnormality index includes: when the micro-abnormality index is greater than a preset micro-abnormality threshold, the sub-region to be observed is determined to be the micro-abnormal sub-region.

[0089] The preset micro-anomaly threshold is a micro-anomaly index threshold, which depends on soil type, vegetation type and ecological restoration goal, and is usually set between 0.3 and 0.7. In this embodiment, it is set to 0.5, which can accurately distinguish between normal sub-regions and restricted sub-regions, providing a basis for subsequent meso- and macro-level analysis.

[0090] By setting a micro-anomaly threshold and comparing it with the micro-anomaly index, this embodiment can effectively identify sub-regions where key factors such as soil acidity / alkalinity, moisture content, or nutrients significantly deviate from the suitable range. Marking these regions as micro-anomaly sub-regions can reflect the mutual influence and constraint relationships between various environmental parameters. For example, insufficient soil moisture may exacerbate nutrient absorption limitations, while acid-base imbalance may affect plant root growth. Thus, it can accurately identify key areas with limited ecological restoration at the micro level, providing a reliable basis for subsequent comprehensive analysis at the meso and macro levels, and achieving refined classification of potential assessment.

[0091] Specifically, the process of determining the meso-level anomaly index based on the normalized vegetation index and the vegetation cover includes: comparing the normalized vegetation index and the vegetation cover of each of the micro-anomaly sub-regions with the corresponding preset meso-level thresholds to obtain several corresponding meso-level deviations; and calculating the meso-level anomaly index based on each of the meso-level deviations and the preset meso-level weighted reorganization.

[0092] In this embodiment, the preset mesoscopic thresholds include a normalized vegetation index (NVI) threshold and a vegetation cover threshold. The NVI threshold is used to assess vegetation growth vitality and depends on the vegetation type and seasonal growth characteristics. It is typically set between 0.3 and 0.8, and in this embodiment, it is set to 0.5, which can distinguish between healthy growth areas and areas with restricted growth. The vegetation cover threshold is used to measure the spatial proportion of vegetation and depends on the ecological restoration goals and land surface type. It is typically set between 20% and 70%, and in this embodiment, it is set to 40%, which can identify areas with sparse or degraded vegetation.

[0093] In this embodiment, the process of calculating the meso-level anomaly index based on each meso-level deviation and a preset meso-level weighted reorganization includes: firstly, performing linear normalization on each meso-level deviation to convert the meso-level deviation of different indicators to a unified dimensional range (such as 0 to 1), and then performing weighted summation calculation in combination with the preset meso-level weighted reorganization to obtain the micro-level anomaly index.

[0094] In this embodiment, the pre-defined meso-level weighted reorganization includes a normalized vegetation index (NVI) weight and a vegetation cover weight. The NVI weight is used to reflect the contribution of vegetation vitality to the meso-level anomaly index, and depends on the vegetation type and ecological restoration sensitivity. It is usually set between 0.4 and 0.6. In this embodiment, it is set to 0.5, which can reasonably reflect the importance of vegetation growth status to anomaly determination. The vegetation cover weight is used to reflect the impact of vegetation spatial cover on the meso-level anomaly index, and depends on the restoration target and surface cover uniformity. It is usually set between 0.4 and 0.6. In this embodiment, it is set to 0.5, which can balance the contribution of cover area and vegetation health status to meso-level anomalies.

[0095] By comparing the normalized vegetation index and vegetation cover of micro-anomaly sub-regions with preset meso-level thresholds, the degree of deviation between vegetation growth status and ideal growth conditions in each region can be quantified. Combined with preset meso-level weighted recombination to calculate the meso-level anomaly index, the contribution of different vegetation indicators to ecological restoration potential can be comprehensively reflected, accurately identifying areas with insufficient or abnormal vegetation growth, and providing quantitative basis for subsequent meso- and macro-level ecological assessments, so that the correlation between vegetation status, cover and factors such as soil and water can be reasonably reflected.

[0096] Please see Figure 3 As shown, this is a logic diagram for determining the cause type of anomalies in this embodiment. In this embodiment, the process of determining several meso-level anomaly sub-regions based on the meso-level anomaly index and the micro-level anomaly type includes: when the meso-level anomaly index is greater than a preset meso-level anomaly threshold, determining the cause type of anomalies in the micro-level anomaly sub-region based on the corresponding micro-level anomaly type; and determining several meso-level anomaly sub-regions based on the cause types of anomalies in other micro-level anomaly sub-regions within a preset determination range centered on each of the micro-level anomaly sub-regions.

[0097] The preset meso-level anomaly threshold is a meso-level anomaly index threshold, which depends on the vegetation type and recovery sensitivity of the target ecosystem. It is usually set between 0.3 and 0.6. In this embodiment, it is set to 0.45, which can effectively identify areas with abnormal vegetation growth or insufficient cover at the meso-level. The preset judgment range is a circular area with a preset radius centered on each of the micro-anomaly sub-regions. It depends on the monitoring resolution, the spatial diffusion degree of the anomaly features, and the judgment accuracy requirements. Its radius is usually set between 5mm and 20mm. In this embodiment, it is set to 10mm, which can effectively cover the local influence range of the anomaly sub-regions and avoid missing boundary anomalies.

[0098] By combining meso-level anomaly indices with micro-level anomaly types, and aggregating the anomaly cause types of adjacent sub-regions with micro-level anomaly sub-regions as the center, this embodiment can identify continuous regions with the same ecological limiting causes at the meso-level, thereby reflecting the cumulative effect of micro-level anomaly factors on ecological restoration at a larger spatial scale, achieving accurate delineation of potential barrier areas, and providing a reliable spatial basis for subsequent macro-level restoration potential assessment.

[0099] Specifically, the process of determining several meso-level anomalous sub-regions based on the anomaly cause types of other micro-level anomalous sub-regions within a preset determination range centered on each of the aforementioned micro-level anomalous sub-regions includes: using the micro-level anomalous indices of the micro-level anomalous sub-regions in descending order as central regions; merging the central region and the other micro-level anomalous sub-regions when the anomaly cause types of the central region and other micro-level anomalous sub-regions within the preset determination range are the same to generate the meso-level anomalous sub-regions; merging the newly generated meso-level anomalous sub-regions with existing meso-level anomalous sub-regions when the spatial overlap rate is greater than a preset overlap threshold, and merging them into one meso-level anomalous sub-region; after merging into one meso-level anomalous sub-region, updating the meso-level anomalous index of the merged meso-level anomalous sub-region by performing a weighted average based on the area and meso-level anomalous index of each meso-level anomalous sub-region before merging; wherein, the merged micro-level anomalous sub-regions no longer participate in subsequent merging.

[0100] The preset overlap threshold is a judgment parameter used to determine the degree of overlap between two sets of data or two structures. It depends on the data sampling accuracy, spatial resolution, and sensitivity requirements of the application scenario. It is usually set between 0.3 and 0.7. In this embodiment, it is set to 0.5, which can ensure the judgment accuracy while avoiding misjudgment caused by oversensitivity.

[0101] By merging adjacent micro-anomaly sub-regions with the same anomaly cause type, centered on sub-regions with high micro-anomaly indices, continuous regions with clear ecological anomaly characteristics can be formed at the meso-scale. At the same time, the meso-scale anomaly index is updated by area-weighted averaging of spatially overlapping parts, so that the generated meso-scale anomaly sub-regions can truly reflect the strength and distribution of local ecological pressure, taking into account both anomaly intensity and spatial coherence, and providing more accurate and stable basic data for subsequent potential assessment.

[0102] Please see Figure 4As shown, this is the logic diagram for determining the macro-medium mode in this embodiment. In this embodiment, the process of determining the macro-adaptation index based on the precipitation and temperature, and determining the index calculation mode based on the meso-level anomaly index and the micro-level anomaly index includes: comparing the precipitation and temperature of each meso-level anomaly sub-region with the corresponding preset macro-level thresholds to obtain several corresponding macro-level deviations; calculating the macro-adaptation index based on each macro-level deviation and the preset macro-level weighting; determining the index calculation mode as a macro-medium mode when the average value of all meso-level anomaly indices is greater than the preset meso-level average threshold and the average value of all micro-level anomaly indices is within the preset micro-level average threshold range; determining the index calculation mode as a micro-macro mode when the average value of all micro-level anomaly indices is greater than the maximum value of the preset micro-level average threshold range and the average value of all meso-level anomaly indices is less than or equal to the preset meso-level average threshold; and determining the index calculation mode as a micro-medium mode when the average value of all meso-level anomaly indices is greater than the preset meso-level average threshold and the average value of all micro-level anomaly indices is greater than the maximum value of the preset micro-level average threshold range.

[0103] The preset macroscopic thresholds include precipitation and temperature thresholds, which define the adaptability of precipitation and temperature, respectively. These thresholds depend on regional climate conditions and ecological adaptation needs, and are typically set between 70% and 130% of historical statistical averages. In this embodiment, they are set to 100mm of precipitation and 25℃ of temperature, accurately reflecting the impact of environmental factor deviations on macroscopic adaptability. The preset macroscopic weighting includes precipitation weight and temperature weight, which measure the relative importance of precipitation and temperature in the calculation of the macroscopic adaptability index. These weights depend on the ecosystem's dependence on water and heat, and are typically set between 0.3 and 0.7. In this embodiment... The weighting of precipitation is set to 0.6 and temperature to 0.4, which can reasonably balance the contribution of different factors. The preset meso-level average threshold is the critical value of the meso-level anomaly index, which depends on the level of abnormal fluctuations at the regional scale. It is usually set between 0.4 and 0.7. In this embodiment, it is set to 0.5, which can effectively distinguish between normal fluctuations and abnormal situations at the meso-level. The preset micro-level average threshold range is the upper and lower limits of the micro-level anomaly index, which depends on the range of detailed fluctuations at the local scale. It is usually set between 0.2 and 0.6. In this embodiment, it is set to 0.3 to 0.5, which can accurately determine whether the fluctuations at the micro-level exceed the reasonable range.

[0104] In this embodiment, the process of determining the macro-adaptation index based on the precipitation and the temperature includes: firstly, linear normalization is performed on each macro-deviation to convert the macro-deviation of different indicators to a unified dimension range (such as 0 to 1), and then weighted summation is performed in combination with a preset macro-weighted set to obtain the macro-adaptation index.

[0105] By converting precipitation and temperature deviations into macro-adaptation indices and combining them with the average values ​​of meso- and micro-anomaly indices for stratified determination, dynamic adaptation to multi-scale environmental factors is achieved. When meso-level anomalies are significant while micro-level fluctuations are within a reasonable range, the system enters a meso-macro mode to highlight the dominant role of the overall regional environment in macro-adaptation; when micro-anomalies are significant while meso-level changes are weak, the system enters a micro-macro mode to emphasize the impact of local details on macro-level performance; and when both meso- and micro-anomalies are significant, the system enters a micro-meso mode to reflect the cumulative effect of multi-level factors. This method, through the mutual constraints and weighted combinations of parameters, allows for flexible switching of the determination logic, ensuring that the index calculation results reflect both overall trends and capture local anomalies, thereby improving the accuracy and robustness of adaptive assessment.

[0106] Specifically, the process of determining a potential index based on the index calculation mode, the macro-adaptation index, the meso-level anomaly index, the micro-level anomaly index, and a preset potential weight reorganization, and determining several macro-level anomaly sub-regions based on the potential index, includes: when the index calculation mode is the meso-macro mode, calculating the potential index based on the macro-adaptation index, the meso-level anomaly index, and the preset potential weight reorganization; when the index calculation mode is the micro-macro mode, calculating the potential index based on the macro-adaptation index, the micro-level anomaly index, and the preset potential weight reorganization; when the index calculation mode is the micro-meso mode, calculating the potential index based on the meso-level anomaly index, the micro-level anomaly index, and the preset potential weight reorganization; and when the potential index is greater than a preset potential index threshold, determining the meso-level anomaly sub-region as the macro-level anomaly sub-region.

[0107] The pre-defined potential weighting includes macro-level weights, meso-level weights, and micro-level weights. Macro-level weights measure the influence of precipitation and temperature on the potential index, and are determined by regional climate conditions, typically set between 0.3 and 0.5. In this embodiment, they are set to 0.4 to ensure a reasonable reflection of macro-environmental changes on the potential index. Meso-level weights reflect the role of vegetation index and cover in the potential index, and are determined by vegetation cover patterns, typically set between 0.2 and 0.4. In this embodiment, they are set to 0.3 to highlight the impact of regional vegetation anomalies on the potential index. Micro-level weights are used to reflect the contribution of soil pH, moisture content, and nutrients to the potential index. They depend on soil ecological characteristics and are usually set between 0.2 and 0.4. In this embodiment, they are set to 0.3, which can enhance the sensitivity of micro-environmental changes in the potential index determination. The preset potential index threshold is used as the criterion for determining whether a meso-level abnormal sub-region has been upgraded to a macro-level abnormal sub-region. It depends on the adaptability level of the combined macro-, meso-, and micro-level influences and is usually set between 0.6 and 0.8. In this embodiment, it is set to 0.7, which can effectively screen out areas with high potential risks and avoid misjudgment or omission.

[0108] In this embodiment, when the index calculation mode is "Meso-Macro Mode", the potential index is calculated by weighting the macro adaptation index and the meso-abnormal index, with the weights being the macro weights and meso weights corresponding to the preset potential weight reorganization; when the index calculation mode is "Micro-Macro Mode", the potential index is calculated by weighting the macro adaptation index and the micro-abnormal index, with the weights being the macro weights and micro weights corresponding to the preset potential weight reorganization; when the index calculation mode is "Micro-Meso Mode", the potential index is calculated by weighting the meso-abnormal index and the micro-abnormal index, with the weights being the meso weights and micro weights corresponding to the preset potential weight reorganization.

[0109] By combining macro-adaptation index, meso-anomaly index, micro-anomaly index, and preset potential weighting under different index calculation modes, a dynamic balance of causal relationship and hierarchical progression can be achieved among multi-level indicators. This allows the potential index to reflect the adaptability of macro-environmental conditions while integrating the abnormal fluctuation characteristics of meso- and micro-scales. Thus, when the potential index exceeds the preset threshold, the macro-anomaly sub-region can be accurately identified, avoiding the bias caused by a single parameter and improving the accuracy and stability of regional anomaly identification.

[0110] Specifically, the process of determining the clustering degree based on the distribution location of the macro-abnormal sub-regions and adjusting the preset potential weight reorganization based on the clustering degree and the index calculation mode includes: calculating the Euclidean distance from the center of each macro-abnormal sub-region to a preset reference point to obtain several distribution distances; calculating the reciprocal of the standard deviation of all distribution distances to obtain the clustering degree; when the clustering degree is greater than a preset clustering threshold, counting the number of calculations based on the medium-macro mode, the micro-macro mode, and the micro-medium mode in all potential indices to obtain the medium-macro quantity, the micro-macro quantity, and the micro-medium quantity; and adjusting the preset potential weight reorganization based on the maximum value of the medium-macro quantity, the micro-macro quantity, and the micro-medium quantity, the clustering degree, and the preset clustering threshold.

[0111] In this embodiment, when the maximum value is the number of macro and meso-level macro ... 3” = w3' / (w1' + w2' + w3'), where w1' is the macro weight after one calculation, w1 is the macro weight before one calculation, w2' is the meso weight after one calculation, w2 is the meso weight before one calculation, w3' is the micro weight after one calculation, w3 is the micro weight before one calculation, w1” is the adjusted macro weight, w2” is the adjusted meso weight, w3” is the adjusted micro weight, C is the aggregation degree, C0 is the preset aggregation threshold, and α is the preset weight adjustment coefficient;

[0112] When the maximum value is the number of micro and macro quantities, the macro weight, meso weight and micro weight are adjusted according to the aggregation degree, the preset aggregation threshold and the preset weight adjustment coefficient, where w1'=w1×[1+α×(C−C0) / C0], w2'=w2×[1-α×(C−C0) / C0], w3'=w3×[1+α×(C−C0) / C0], w1”=w1' / (w1'+w2'+w3'), w2”=w2' / (w1'+w2'+w3'), w3”=w3' / (w1'+w2'+w3');

[0113] When the maximum value is the number of micro- and meso-levels, the macro-level weight, meso-level weight, and micro-level weight are adjusted according to the degree of aggregation, the preset aggregation threshold, and the preset weight adjustment coefficient. Among them, w1'=w1×[1-α×(C−C0) / C0], w2'=w2×[1+α×(C−C0) / C0], w3'=w3×[1+α×(C−C0) / C0], w1”=w1' / (w1'+w2'+w3'), w2”=w2' / (w1'+w2'+w3'), w3”=w3' / (w1'+w2'+w3').

[0114] The preset weight adjustment coefficient depends on the need to adjust the sensitivity of the potential weight, and is usually set between 0.01 and 0.5. In this embodiment, it is set to 0.1, which can moderately adjust the macro, meso, and micro weights when the aggregation degree changes, ensuring that the weight adjustment is smooth and reflects the spatial distribution characteristics of the abnormal sub-regions. The preset aggregation threshold is a reference value used to determine the spatial concentration of the macro abnormal sub-regions. It depends on the regional size and ecological restoration goals, and is usually set between 0.1 and 0.5. In this embodiment, it is set to 0.3, which can identify the high aggregation of macro abnormal sub-regions. The preset reference point is a benchmark location used to calculate the spatial distribution distance of the macro abnormal sub-regions. It depends on the geographical center of the observation area or the key area for ecological restoration, and is usually set at the geometric center of the observation area. In this embodiment, it is set at the geometric center of the observation area, which can provide a unified distance benchmark to assess the aggregation degree.

[0115] The clustering degree is obtained by calculating the distribution distance of macro-anomaly sub-regions relative to a preset reference point and the reciprocal of its standard deviation, which can intuitively reflect the spatial concentration of anomaly areas. When the clustering degree exceeds a preset threshold, the number of potential indices under different calculation models is counted, which helps to identify the main factors affecting ecological restoration potential at the micro, meso, and macro levels. Based on the clustering degree, model distribution, and threshold, the preset potential weighting can be dynamically adjusted to reasonably enhance or weaken the influence of indicators at each level in the calculation of potential indices, so that the potential index can more accurately reflect the actual situation of regional ecological restoration and ensure that the evaluation results can take into account both spatial distribution characteristics and the comprehensive role of multidimensional indicators.

[0116] On the other hand, this embodiment also provides a regional ecological restoration potential assessment system based on multidimensional data, including:

[0117] The first acquisition module is used to collect the pH, water content and nutrient content of each sub-region to be observed in real time within the observation area;

[0118] A microscopic determination module, connected to the first acquisition module, is used to determine the microscopic anomaly index and microscopic anomaly type based on the pH, the moisture content and the nutrient content, and to determine several microscopic anomaly sub-regions based on the microscopic anomaly index.

[0119] The second acquisition module is connected to the microscopic determination module and is used to acquire the normalized vegetation index and vegetation coverage of each microscopic anomaly sub-region in real time.

[0120] The mesoscopic determination module is connected to the second acquisition module and is used to determine the mesoscopic anomaly index based on the normalized vegetation index and the vegetation coverage, and to determine several mesoscopic anomaly sub-regions based on the mesoscopic anomaly index and the microscopic anomaly type.

[0121] The third acquisition module is connected to the mesoscopic determination module and is used to acquire precipitation and temperature in each of the mesoscopic anomaly sub-regions in real time.

[0122] The mode determination module is connected to the third acquisition module, the micro-determination module and the meso-determination module respectively, and is used to determine the macro-adaptation index based on the precipitation and the temperature, and to determine the index calculation mode based on the macro-adaptation index, the meso-anomaly index and the micro-anomaly index.

[0123] A macro-determination module, connected to the pattern determination module, is used to determine a potential index based on the index calculation mode, the macro-adaptation index, the meso-anomaly index, the micro-anomaly index, and a preset potential weight reorganization, and to determine several macro-anomaly sub-regions based on the potential index.

[0124] An adjustment module, connected to the macro determination module, is used to determine the clustering degree based on the distribution location of the macro abnormal sub-regions, and to adjust the preset potential weight reorganization based on the clustering degree and the index calculation mode.

[0125] A generation module, connected to the macro-determination module, is used to generate a recovery potential assessment report based on the potential index re-determined after adjusting the preset potential weights.

[0126] Through multi-level and multi-dimensional data collection and analysis, key ecological parameters such as soil pH, moisture content, nutrient content, vegetation index, vegetation cover, precipitation, and temperature can be comprehensively processed to achieve hierarchical identification and aggregation of micro, meso, and macro anomalies. By calculating the potential index and adjusting the aggregation degree, the weights of ecological anomalies of different scales and types can be reasonably allocated, thereby accurately reflecting the ecological restoration potential of each region. This enables refined judgment and scientific regulation of potential risk areas, providing quantitative, dynamic, and operable decision-making basis for regional ecological restoration.

[0127] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for regional ecological restoration potential assessment based on multi-dimensional data, characterized in that, The method comprises the following steps: collecting pH value, water content and nutrient content of each sub-region in the observation area in real time; determining micro-abnormal index and micro-abnormal type according to the pH value, the water content and the nutrient content, and determining several micro-abnormal sub-regions according to the micro-abnormal index; collecting normalized difference vegetation index (NDVI) and vegetation coverage of each micro-abnormal sub-region in real time; determining meso-abnormal index according to the NDVI and the vegetation coverage, and determining several meso-abnormal sub-regions according to the meso-abnormal index and the micro-abnormal type; collecting precipitation and temperature in each meso-abnormal sub-region in real time; determining macro-adaptation index according to the precipitation and the temperature, and determining index calculation mode according to the meso-abnormal index and the micro-abnormal index; determining potential index according to the index calculation mode, the macro-adaptation index, the meso-abnormal index, the micro-abnormal index and preset potential weight set, and determining several macro-abnormal sub-regions according to the potential index; determining aggregation degree according to the distribution position of the macro-abnormal sub-region, and adjusting the preset potential weight set according to the aggregation degree and the index calculation mode; generating a recovery potential evaluation report according to the potential index determined after the preset potential weight set is adjusted; the process of determining micro-abnormal index according to the pH value, the water content and the nutrient content comprises the following steps: comparing the pH value, the water content, the nutrient content of each sub-region to be observed with corresponding preset micro-threshold value to obtain several corresponding micro-deviation degrees; calculating the micro-abnormal index according to each micro-deviation degree and preset micro-weight set; the process of determining meso-abnormal index according to the NDVI and the vegetation coverage comprises the following steps: comparing the NDVI and the vegetation coverage of each micro-abnormal sub-region with corresponding preset meso-threshold value respectively to obtain several corresponding meso-deviation degrees; calculating the meso-abnormal index according to each meso-deviation degree and preset meso-weight set; the process of determining macro-adaptation index according to the precipitation and the temperature comprises the following steps: comparing the precipitation and the temperature of each meso-abnormal sub-region with corresponding preset macro-threshold value respectively to obtain several corresponding macro-deviation degrees; calculating the macro-adaptation index according to each macro-deviation degree and preset macro-weight set; the index calculation mode comprises meso-micro mode, micro-meso mode and micro-micro mode.

2. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 1, characterized in that, the process of determining micro-abnormal type comprises the following steps: determining the micro-abnormal type according to the highest value in all micro-deviation degrees.

3. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 2, characterized in that, the process of determining several micro-abnormal sub-regions according to the micro-abnormal index comprises the following steps: when the micro-abnormal index is greater than preset micro-abnormal threshold value, determining that the sub-region to be observed is the micro-abnormal sub-region.

4. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 3, characterized in that, the process of determining several meso-abnormal sub-regions according to the meso-abnormal index and the micro-abnormal type comprises the following steps: when the meso-abnormal index is greater than preset meso-abnormal threshold value, determining the abnormal cause type of the micro-abnormal sub-region according to the corresponding micro-abnormal type. Determine a number of mesoscopic abnormal sub-regions according to the abnormal cause types of other micro-abnormal sub-regions within a preset judging range centered on each of the micro-abnormal sub-regions.

5. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 4, characterized in that, The process of determining a number of mesoscopic abnormal sub-regions according to the abnormal cause types of other micro-abnormal sub-regions within a preset judging range centered on each of the micro-abnormal sub-regions comprises: sequentially take the micro-abnormal sub-regions as the center region in descending order of the micro-abnormal index of the micro-abnormal sub-regions; when the abnormal cause types of the center region and other micro-abnormal sub-regions within the preset judging range are the same, merge the center region and the other micro-abnormal sub-regions to generate the mesoscopic abnormal sub-region; when the spatial overlap rate of the newly generated mesoscopic abnormal sub-region and an existing mesoscopic abnormal sub-region is greater than a preset overlap threshold, merge them into one mesoscopic abnormal sub-region; after merging into one mesoscopic abnormal sub-region, perform weighted average on the area and the mesoscopic abnormal index of each mesoscopic abnormal sub-region before merging to update the mesoscopic abnormal index of the merged mesoscopic abnormal sub-region; wherein the merged micro-abnormal sub-regions no longer participate in subsequent merging.

6. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 5, characterized in that, The process of determining the index calculation mode according to the mesoscopic abnormal index and the micro-abnormal index comprises: when the average value of all the mesoscopic abnormal indexes is greater than a preset mesoscopic average threshold and the average value of all the micro-abnormal indexes is within a preset micro-abnormal average threshold range, determine that the index calculation mode is the meso-macro mode; when the average value of all the micro-abnormal indexes is greater than the maximum value of the preset micro-abnormal average threshold range and the average value of all the mesoscopic abnormal indexes is less than or equal to the preset mesoscopic average threshold, determine that the index calculation mode is the micro-macro mode; when the average value of all the mesoscopic abnormal indexes is greater than the preset mesoscopic average threshold and the average value of all the micro-abnormal indexes is greater than the maximum value of the preset micro-abnormal average threshold range, determine that the index calculation mode is the micro-meso mode.

7. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 6, characterized in that, The process of determining the potential index according to the index calculation mode, the macroscopic adaptive index, the mesoscopic abnormal index, the micro-abnormal index, and a preset potential weight set, and determining a number of macro-abnormal sub-regions according to the potential index comprises: when the index calculation mode is the meso-macro mode, calculate the potential index according to the macroscopic adaptive index, the mesoscopic abnormal index, and the preset potential weight set; when the index calculation mode is the micro-macro mode, calculate the potential index according to the macroscopic adaptive index, the micro-abnormal index, and the preset potential weight set; when the index calculation mode is the micro-meso mode, calculate the potential index according to the mesoscopic abnormal index, the micro-abnormal index, and the preset potential weight set; when the potential index is greater than a preset potential index threshold, determine that the mesoscopic abnormal sub-region is the macro-abnormal sub-region.

8. The method for regional ecological restoration potential assessment based on multi-dimensional data according to claim 7, characterized in that, The process of determining the aggregation degree according to the distribution position of the macro-abnormal sub-region and adjusting the preset potential weight set according to the aggregation degree and the index calculation mode comprises: calculating Euclidean distances from centers of each of the macroscopic abnormal sub-regions to a preset reference point to obtain a plurality of distribution distances; calculating a reciprocal of a standard deviation of all the distribution distances to obtain the aggregation degree; when the aggregation degree is greater than a preset aggregation threshold, counting numbers of all potential indexes calculated according to the meso-macro mode, the micro-macro mode and the micro-meso mode to obtain a meso-macro number, a micro-macro number and a micro-meso number; adjusting the preset potential weight set according to a maximum value of the meso-macro number, the micro-macro number and the micro-meso number, the aggregation degree and the preset aggregation threshold.

9. A system for assessing regional ecological restoration potential based on multi-dimensional data, constructed based on the method for assessing regional ecological restoration potential based on multi-dimensional data according to any one of claims 1-8, characterized in that, comprise: a first acquisition module, configured to acquire pH, water content and nutrient content of each to-be-observed sub-region in an observation region in real time; a microscopic determination module, connected with the first acquisition module, configured to determine a microscopic abnormality index and a microscopic abnormality type according to the pH, the water content and the nutrient content, and determine a plurality of microscopic abnormal sub-regions according to the microscopic abnormality index; a second acquisition module, connected with the microscopic determination module, configured to acquire a normalized vegetation index and a vegetation coverage of each of the microscopic abnormal sub-regions in real time; a mesoscopic determination module, connected with the second acquisition module, configured to determine a mesoscopic abnormality index according to the normalized vegetation index and the vegetation coverage, and determine a plurality of mesoscopic abnormal sub-regions according to the mesoscopic abnormality index and the microscopic abnormality type; a third acquisition module, connected with the mesoscopic determination module, configured to acquire precipitation and temperature in each of the mesoscopic abnormal sub-regions in real time; a mode determination module, connected with the third acquisition module, the microscopic determination module and the mesoscopic determination module respectively, configured to determine a macroscopic adaptation index according to the precipitation and the temperature, and determine an index calculation mode according to the macroscopic adaptation index, the mesoscopic abnormality index and the microscopic abnormality index; a macroscopic determination module, connected with the mode determination module, configured to determine a potential index according to the index calculation mode, the macroscopic adaptation index, the mesoscopic abnormality index, the microscopic abnormality index and a preset potential weight set, and determine a plurality of macroscopic abnormal sub-regions according to the potential index; an adjustment module, connected with the macroscopic determination module, configured to determine an aggregation degree according to a distribution position of the macroscopic abnormal sub-regions, and adjust the preset potential weight set according to the aggregation degree and the index calculation mode; a generation module, connected with the macroscopic determination module, configured to generate a recovery potential evaluation report according to the potential index determined after the preset potential weight set is adjusted.

Images