Intelligent monitoring system for ecological restoration of natural engineering

Abstract

The invention relates to the field of ecological restoration, in particular to a natural engineering ecological restoration intelligent monitoring system which comprises a data acquisition module, a data transmission storage module, an intelligent decision support module, a control execution module and a user interaction module. According to the scheme, environmental data in an ecological restoration area is deeply analyzed and processed by adopting a method based on spatial change feature learning, time sequence data is converted into a one-dimensional event sequence, and a spatial change event set is constructed, so that a dynamic change mode of an ecological system is captured; according to the method, restoration categories in an ecological restoration area are divided by adopting a hot spot area pre-distribution method, a reasonable distribution ratio is set according to actual conditions in the restoration area, and optimal hot spot cells are selected for pre-distribution by calculating a transition probability and a proximity effect, so that the scientificity and rationality of pre-distribution are ensured.

Description

Technical Field

[0001] The present invention relates to the field of ecological restoration, and in particular to an intelligent monitoring system for natural engineering ecological restoration. Background Art

[0002] With the rapid development of industrialization and urbanization, natural ecosystems have suffered serious damage, and ecological restoration has become particularly important. Traditional ecological restoration monitoring methods are inefficient, lack real-time and accuracy, and cannot meet the needs of modern ecological restoration. Existing ecological restoration technologies lack effective spatial planning and insufficient understanding of the complexity of ecosystems, resulting in limitations in formulating restoration plans and integrating multiple restoration technologies. These problems not only increase the cost of ecological restoration projects and reduce the success rate, but may even cause new damage to the original ecosystem. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent monitoring system for natural engineering ecological restoration. In view of the low efficiency, lack of real-time and accuracy of traditional ecological restoration monitoring methods, which cannot meet the needs of modern ecological restoration, this solution adopts a method based on spatial change feature learning to conduct in-depth analysis and processing of environmental data in the ecological restoration area. By using spatial change feature learning technology, time series data is converted into a one-dimensional event sequence, and a spatial change event set is constructed to capture the dynamic change pattern of the ecosystem. On this basis, by constructing a prefix tree and performing feature extraction, the spatiotemporal structural characteristics that are most critical to ecological restoration are identified, providing a basis for subsequent classification and pre-allocation; in view of the existing ecological restoration technology The technology lacks effective spatial planning and insufficient understanding of the complexity of the ecosystem, which leads to limitations in formulating restoration plans and integrating multiple restoration technologies. The hot spot area pre-allocation method is used to divide the restoration categories within the ecological restoration area. This method sets a reasonable allocation ratio based on the actual situation in the restoration area, and selects the optimal hot spot cells for pre-allocation by calculating the transfer probability and proximity effect to ensure the scientificity and rationality of the pre-allocation. Through multiple iterations and adjustments, a complete set of ecological restoration plans is finally formed, which can effectively cope with the complexity and uncertainty of the ecosystem. The in-depth understanding of the ecological environment and the scientific pre-allocation strategy can make more rational use of limited resources and avoid waste of resources.

[0004] The present invention provides an intelligent monitoring system for ecological restoration of natural engineering, which includes a data acquisition module, a data transmission storage module, an intelligent decision support module, a control execution module and a user interaction module;

[0005] The data acquisition module collects environmental parameter data through environmental sensors, biodiversity monitoring equipment, water quality monitoring devices and air quality monitoring deployed in the restoration area;

[0006] The data transmission and storage module uses wireless communication technology and satellite communication to transmit the data output between the modules, uses cloud computing and database management system to provide computing power and storage space, processes the data output by each module, and organizes, stores and retrieves the data output by each module;

[0007] The intelligent decision support module uses a method based on spatial variation feature learning and hot spot area pre-allocation to analyze and process environmental parameter data, and makes intelligent decisions to make control decisions and early warning judgments for the automatic control unit and early warning unit of the control execution module;

[0008] The control execution module includes an automatic control unit and an early warning unit. The automatic control unit automatically adjusts the working state of the equipment in the repair area according to the control decision, and the early warning unit issues an alarm according to the information of the early warning judgment and takes corresponding measures;

[0009] The user interaction module constructs a user-friendly interactive interface, provides data for the data acquisition module, the intelligent decision support module and the control execution module, so that non-professionals can also access and understand complex data reports.

[0010] Furthermore, the intelligent decision support module uses a method based on spatial variation feature learning and hot spot area pre-allocation to analyze and process the environmental parameter data, and the method based on spatial variation feature learning and hot spot area pre-allocation specifically includes the following steps:

[0011] Step S1: Data preparation and preprocessing: obtain a time series data set containing D dimensions in the environmental parameter data, normalize the time series data of each dimension to the interval [0,1], and obtain a preprocessed time series set, which contains m sequences;

[0012] Step S2: converting into a one-dimensional event sequence, calculating the spatial change direction of each sequence, and generating a D-dimensional symbol vector for each sequence according to the calculated spatial change direction to form a one-dimensional event sequence;

[0013] Step S3: construct a spatial change event set, define a symbol set E, and based on the defined symbol set E, generate all possible combinations of event sequences to form a spatial change event set;

[0014] Step S4: extracting spatiotemporal structural features, constructing a prefix tree, and performing feature extraction to obtain ecological restoration types;

[0015] Step S5: pre-allocation strategy, set allocation ratio, allocate and adjust ecological restoration types;

[0016] Step S6: Result output, obtain and output the final allocation result, and make a decision based on the final allocation result.

[0017] Furthermore, in step S4, the spatiotemporal structural features are extracted, which specifically includes the following steps:

[0018] Step S41: construct a prefix tree, organize the event sequence in the spatial change event set into a prefix tree structure, the prefix tree includes a root node, leaf nodes and paths, wherein each node represents an event, and the path represents an event sequence;

[0019] Step S42: extracting node sequence features, traversing the prefix tree, and extracting the root-to-leaf node sequence features from the path from the root node to the leaf node, which is called the RTS feature;

[0020] Step S43: feature selection, using a bottom-up pruning strategy, starting from the leaf nodes, gradually deleting unimportant nodes and paths upward to obtain a pruned prefix tree, and identifying the most critical RTS features for sequence pattern classification through the pruned prefix tree, which are recorded as key RTS features;

[0021] Step S44: Category output, using the key RTS features as the basis for classification, using the agglomerative hierarchical clustering method for classification, and obtaining k ecological restoration categories;

[0022] Furthermore, in step S5, the pre-allocation strategy specifically includes the following steps:

[0023] Step S51: Initial setting and pre-allocation: according to the actual situation in the restoration area, set the cells, determine the demand and current quantity of each ecological restoration category, and set the allocation ratio;

[0024] Step S52: Calculate the transition probability on which the pre-allocation depends, using the following formula: ;

[0025] In the formula, represents the suitability of the ecological restoration category, represents the constraint factor, represents the inertia coefficient, is the transition probability;

[0026] Step S53: Select the hotspot cell. The cells are pre-allocated as hot cells, which specifically includes the following steps:

[0027] Step S531: For the ecological restoration category, select one of the ecological restoration categories as the target type and calculate the number of hotspot cells that need to be pre-allocated , the formula used is as follows: ;

[0028] In the formula, is the distribution ratio, represents the demand for ecological restoration categories, represents the current number of ecological restoration categories, Indicates the number of hotspot cells that need to be pre-allocated;

[0029] Step S532: sorting all cells of non-target allocation types according to the transition probability, and setting the cell with the highest transition probability value as the target allocation type according to the sorting result;

[0030] Step S533: Cell allocation, determine whether the number of allocated cells is equal to the number of pre-allocated hotspot cells , if yes, continue to allocate the next target allocation type until all ecological restoration categories are allocated, otherwise, return to step S532 to continue allocation;

[0031] Step S54: Calculate the proximity effect and the overall probability. For each ecological restoration category, after pre-allocation, calculate the proximity effect. Combine the transfer probability and the proximity effect to calculate the overall probability. The formula used is as follows: ; ;

[0032] In the formula, Indicates the state of the cell after pre-allocation, express Neighborhood of Indicated in In the neighborhood of The sum of the number of cells, Represents a conditional function, when the state of the cell after pre-allocation is the target type The value is 1 when , otherwise it is 0. Indicated in The number of cells in the neighborhood of excluding the central cell, represents the overall probability, represents the proximity effect;

[0033] Step S55: Based on the overall probability, a roulette wheel selection mechanism is constructed to determine the target allocation type of each cell, and the position where the roulette wheel stops is determined by a random number between 0 and 1, so as to select a specific ecological restoration category for allocation;

[0034] Step S56: Iteration and adjustment, check whether the results of the current round meet the requirements of all ecological restoration categories. If not, adjust the allocation ratio and return to step S52 to continue the next round of iteration. If the requirements of all ecological restoration categories are met, end.

[0035] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0036] (1) In view of the low efficiency, lack of real-time and accuracy of traditional ecological restoration monitoring methods, which cannot meet the needs of modern ecological restoration, this scheme adopts a method based on spatial variation feature learning to conduct in-depth analysis and processing of environmental data in the ecological restoration area. The spatial variation feature learning technology is used to convert time series data into a one-dimensional event sequence and construct a spatial variation event set to capture the dynamic change pattern of the ecosystem. On this basis, by constructing a prefix tree and performing feature extraction, the spatiotemporal structural characteristics that are most critical to ecological restoration are identified, providing a basis for subsequent classification and pre-allocation.

[0037] (2) The existing ecological restoration technologies lack effective spatial planning and the understanding of the complexity of the ecosystem is insufficient, which leads to limitations in formulating restoration plans and integrating multiple restoration technologies. The hotspot area pre-allocation method is used to divide the restoration categories within the ecological restoration area. This method determines the demand and current quantity of each ecological restoration category based on the actual situation in the restoration area, sets a reasonable allocation ratio, and selects the optimal hotspot cells for pre-allocation by calculating the transfer probability and neighboring effect. This process not only considers the suitability and constraints of the ecological restoration category, but also combines the mutual influence between cells to ensure the scientificity and rationality of the pre-allocation. After multiple iterations and adjustments, a complete set of ecological restoration plans is finally formed, which can effectively cope with the complexity and uncertainty of the ecosystem. The in-depth understanding of the ecological environment and the scientific pre-allocation strategy can make more rational use of limited resources and avoid resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of an intelligent monitoring system for natural engineering ecological restoration provided by the present invention;

[0039] Figure 2 Schematic diagram of the process for pre-allocation of cells;

[0040] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] Example 1, see Figure 1 , a natural engineering ecological restoration intelligent monitoring system provided by the present invention includes a data acquisition module, a data transmission storage module, an intelligent decision support module, a control execution module and a user interaction module;

[0043] The data acquisition module collects environmental parameter data through environmental sensors, biodiversity monitoring equipment, water quality monitoring devices and air quality monitoring deployed in the restoration area;

[0044] The data transmission and storage module uses wireless communication technology and satellite communication to transmit the data output between the modules, uses cloud computing and database management system to provide computing power and storage space, processes the data output by each module, and organizes, stores and retrieves the data output by each module;

[0045] The intelligent decision support module uses a method based on spatial variation feature learning and hot spot area pre-allocation to analyze and process environmental parameter data, and makes intelligent decisions to make control decisions and early warning judgments for the automatic control unit and early warning unit of the control execution module;

[0046] The control execution module includes an automatic control unit and an early warning unit. The automatic control unit automatically adjusts the working state of the equipment in the repair area according to the control decision, and the early warning unit issues an alarm according to the information of the early warning judgment and takes corresponding measures;

[0047] The user interaction module constructs a user-friendly interactive interface, provides data for the data acquisition module, the intelligent decision support module and the control execution module, so that non-professionals can also access and understand complex data reports.

[0048] Embodiment 2: This embodiment is based on the above embodiment. In the data acquisition module, the environmental sensors include but are not limited to temperature, humidity, light intensity, soil moisture, and pH sensors; the biodiversity monitoring equipment is used to record the species and quantity of plants and animals, including infrared cameras, acoustic detection equipment, etc.; the water quality monitoring device measures the chemical composition and dissolved oxygen concentration in the water body; the air quality monitoring includes but is not limited to detecting the concentration of pollutants such as particulate matter and harmful gases in the air.

[0049] Embodiment 3, based on the above embodiment, the intelligent decision support module uses a method based on spatial variation feature learning and hot spot area pre-allocation to analyze and process environmental parameter data, and the method based on spatial variation feature learning and hot spot area pre-allocation specifically includes the following steps:

[0050] Step S1: Data preparation and preprocessing: obtain a time series data set containing D dimensions in the environmental parameter data, normalize the time series data of each dimension to the interval [0,1], and obtain a preprocessed time series set, which contains m sequences;

[0051] Step S2: converting into a one-dimensional event sequence, calculating the spatial change direction of each sequence, and generating a D-dimensional symbol vector for each sequence according to the calculated spatial change direction to form a one-dimensional event sequence;

[0052] Step S3: construct a spatial change event set, define a symbol set E, and based on the defined symbol set E, generate all possible combinations of event sequences to form a spatial change event set;

[0053] Step S4: extracting spatiotemporal structural features, constructing a prefix tree, and performing feature extraction to obtain ecological restoration types;

[0054] Step S5: pre-allocation strategy, set allocation ratio, allocate and adjust ecological restoration types;

[0055] Step S6: Result output, obtain and output the final allocation result, and make a decision based on the final allocation result.

[0056] Embodiment 4: This embodiment is based on the above embodiment. In step S2, the content of calculating the spatial change direction is as follows:

[0057] Each sequence contains a D-dimensional sequence of S time points. For each time point and each dimension, the spatial change direction is calculated based on the relative position change between adjacent sequences. The formula used is as follows: ;

[0058] In the formula, Indicated in Dimensions and The value of a time point series, Indicated in Dimensions and The value of a time point series, is the preset threshold, Indicated in Dimensions and The spatial variation direction of a time point sequence.

[0059] Embodiment 5, based on the above embodiment, in step S4, the spatiotemporal structural features are extracted, specifically comprising the following steps:

[0060] Step S41: construct a prefix tree, organize the event sequence in the spatial change event set into a prefix tree structure, the prefix tree includes a root node, leaf nodes and paths, wherein each node represents an event, and the path represents an event sequence;

[0061] Step S42: extracting node sequence features, traversing the prefix tree, and extracting the root-to-leaf node sequence features from the path from the root node to the leaf node, which is called the RTS feature;

[0062] Step S43: feature selection, using a bottom-up pruning strategy, starting from the leaf nodes, gradually deleting unimportant nodes and paths upward to obtain a pruned prefix tree, and identifying the most critical RTS features for sequence pattern classification through the pruned prefix tree, which are recorded as key RTS features;

[0063] Step S44: Category output, using the key RTS features as the basis for classification, using the agglomerative hierarchical clustering method for classification, and obtaining k ecological restoration categories.

[0064] Through the above operations, in view of the fact that traditional ecological restoration monitoring methods are inefficient, lack real-time and accuracy, and cannot meet the needs of modern ecological restoration, this scheme adopts a method based on spatial change feature learning to conduct in-depth analysis and processing of environmental data in the ecological restoration area. Using spatial change feature learning technology, time series data is converted into a one-dimensional event sequence, and a spatial change event set is constructed to capture the dynamic change pattern of the ecosystem. On this basis, by constructing a prefix tree and performing feature extraction, the most critical spatiotemporal structural characteristics for ecological restoration are identified, providing a basis for subsequent classification and pre-allocation.

[0065] Example 6, see Figure 2 This embodiment is based on the above embodiment. In step S5, the pre-allocation strategy specifically includes the following steps:

[0066] Step S51: Initial setting and pre-allocation: according to the actual situation in the restoration area, set the cells, determine the demand and current quantity of each ecological restoration category, and set the allocation ratio;

[0067] Step S52: Calculate the transition probability on which the pre-allocation depends, using the following formula: ;

[0068] In the formula, represents the suitability of the ecological restoration category, represents the constraint factor, represents the inertia coefficient, is the transition probability;

[0069] Step S53: Select the hotspot cell. The cells are pre-allocated as hot cells, which specifically includes the following steps:

[0070] Step S531: For the ecological restoration category, select one of the ecological restoration categories as the target allocation type and calculate the number of hotspot cells that need to be pre-allocated , the formula used is as follows: ;

[0071] In the formula, is the distribution ratio, represents the demand for ecological restoration categories, represents the current number of ecological restoration categories, Indicates the number of hotspot cells that need to be pre-allocated;

[0072] Step S532: sorting all cells of non-target allocation types according to the transition probability, and setting the cell with the highest transition probability value as the target allocation type according to the sorting result;

[0073] Step S533: Cell allocation, determine whether the number of allocated cells is equal to the number of pre-allocated hotspot cells , if yes, continue to allocate the next target allocation type until all ecological restoration categories are allocated, otherwise, return to step S532 to continue allocation;

[0074] Step S54: Calculate the proximity effect and the overall probability. For each ecological restoration category, after pre-allocation, calculate the proximity effect. Combine the transfer probability and the proximity effect to calculate the overall probability. The formula used is as follows: ; ;

[0075] In the formula, Indicates the state of the cell after pre-allocation, express Neighborhood of Indicated in In the neighborhood of The sum of the number of cells, Represents a conditional function, when the state of the cell after pre-allocation is the target type The value is 1 when , otherwise it is 0. Indicated in The number of cells in the neighborhood of excluding the central cell, represents the overall probability, represents the proximity effect;

[0076] Step S55: Based on the overall probability, a roulette wheel selection mechanism is constructed to determine the target allocation type of each cell, and the position where the roulette wheel stops is determined by a random number between 0 and 1, so as to select a specific ecological restoration category for allocation;

[0077] Step S56: Iteration and adjustment, check whether the results of the current round meet the requirements of all ecological restoration categories. If not, adjust the allocation ratio and return to step S52 to continue the next round of iteration. If the requirements of all ecological restoration categories are met, end.

[0078] Embodiment 7: This embodiment is based on the above embodiment. In step S55, a roulette selection mechanism is constructed, which specifically includes the following steps:

[0079] Step S551: each ecological restoration category is regarded as a sector on the wheel, and the size of each sector is proportional to the overall probability of the ecological restoration category;

[0080] Step S552: Determine a random number, randomly generate a random number uniformly distributed between 0 and 1, and the random number is used to determine the position where the roulette wheel stops, and then determine the selected ecological restoration category;

[0081] Step S553: ​​Select the ecological restoration category, determine the target allocation type of the cell according to the sector where the random number falls, and update the current number of the target allocation type;

[0082] Step S554: loop iteration, repeating steps S552 to S553 until all cells are allocated.

[0083] Through the above operations, the existing ecological restoration technologies lack effective spatial planning and insufficient understanding of the complexity of ecosystems, which leads to limitations in formulating restoration plans and integrating multiple restoration technologies. The hot spot area pre-allocation method is used to divide the restoration categories within the ecological restoration area. This method determines the demand and current quantity of each ecological restoration category according to the actual situation in the restoration area, sets a reasonable allocation ratio, and selects the optimal hot spot cell for pre-allocation by calculating the transfer probability and proximity effect. This process not only considers the suitability and constraints of the ecological restoration category, but also combines the mutual influence between cells to ensure the scientificity and rationality of the pre-allocation. Through multiple iterations and adjustments, a complete set of ecological restoration plans is finally formed, which can effectively cope with the complexity and uncertainty of the ecosystem. The in-depth understanding of the ecological environment and the scientific pre-allocation strategy can make more rational use of limited resources and avoid waste of resources.

[0084] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0085] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0086] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A natural engineering ecological restoration intelligent monitoring system, characterized by: It includes data acquisition module, data transmission and storage module, intelligent decision support module, control execution module and user interaction module; The data acquisition module collects environmental parameter data through environmental sensors, biodiversity monitoring equipment, water quality monitoring devices and air quality monitoring deployed in the restoration area; The data transmission and storage module uses wireless communication technology and satellite communication to transmit the data output between the modules, uses cloud computing and database management system to provide computing power and storage space, processes the data output by each module, and organizes, stores and retrieves the data output by each module; The intelligent decision support module uses a method based on spatial variation feature learning and hot spot area pre-allocation to analyze and process environmental parameter data, and makes intelligent decisions to make control decisions and early warning judgments on the automatic control unit and early warning unit of the control execution module; The control execution module includes an automatic control unit and an early warning unit. The automatic control unit automatically adjusts the working state of the equipment in the repair area according to the control decision, and the early warning unit issues an alarm according to the information of the early warning judgment and takes corresponding measures; The user interaction module constructs a user-friendly interactive interface, provides data for the data acquisition module, the intelligent decision support module and the control execution module, so that non-professionals can also access and understand complex data reports.

2. According to claim 1, a natural engineering ecological restoration intelligent monitoring system is characterized by: The intelligent decision support module analyzes and processes the environmental parameter data using a method based on spatial variation feature learning and hot spot area pre-allocation, and the method based on spatial variation feature learning and hot spot area pre-allocation specifically includes the following steps: Step S1: Data preparation and preprocessing: obtain a time series data set containing D dimensions in the environmental parameter data, normalize the time series data of each dimension to the interval [0,1], and obtain a preprocessed time series set, which contains m sequences; Step S2: converting into a one-dimensional event sequence, calculating the spatial change direction of each sequence, and generating a D-dimensional symbol vector for each sequence according to the calculated spatial change direction to form a one-dimensional event sequence; Step S3: construct a spatial change event set, define a symbol set E, and based on the defined symbol set E, generate all possible combinations of event sequences to form a spatial change event set; Step S4: extracting spatiotemporal structural features, constructing a prefix tree, and performing feature extraction to obtain ecological restoration types; Step S5: pre-allocation strategy, set allocation ratio, allocate and adjust ecological restoration types; Step S6: Result output, obtain and output the final allocation result, and make a decision based on the final allocation result.

3. According to claim 2, a natural engineering ecological restoration intelligent monitoring system is characterized by: In step S4, the spatiotemporal structural features are extracted, which specifically includes the following steps: Step S41: construct a prefix tree, organize the event sequence in the spatial change event set into a prefix tree structure, the prefix tree includes a root node, leaf nodes and paths, wherein each node represents an event, and the path represents an event sequence; Step S42: extracting node sequence features, traversing the prefix tree, and extracting the root-to-leaf node sequence features from the path from the root node to the leaf node, which is called the RTS feature; Step S43: feature selection, using a bottom-up pruning strategy, starting from the leaf nodes, gradually deleting unimportant nodes and paths upward to obtain a pruned prefix tree, and identifying the most critical RTS features for sequence pattern classification through the pruned prefix tree, which are recorded as key RTS features; Step S44: Category output, using the key RTS features as the basis for classification, using the agglomerative hierarchical clustering method for classification, and obtaining k ecological restoration categories.

4. The natural engineering ecological restoration intelligent monitoring system according to claim 2 is characterized by: In step S5, the pre-allocation strategy specifically includes the following steps: Step S51: Initial setting and pre-allocation: according to the actual situation in the restoration area, set the cells, determine the demand and current quantity of each ecological restoration category, and set the allocation ratio; Step S52: Calculate the transition probability on which the pre-allocation depends; Step S53: Select the hotspot cell. The cells are pre-allocated as hotspot cells, which specifically includes the following steps: Step S531: For the ecological restoration category, select one of the ecological restoration categories as the target type and calculate the number of hotspot cells that need to be pre-allocated ; Step S532: sorting all cells of non-target allocation types according to the transition probability, and setting the cell with the highest transition probability value as the target allocation type according to the sorting result; Step S533: Cell allocation, determine whether the number of allocated cells is equal to the number of pre-allocated hotspot cells , if yes, continue to allocate the next target allocation type until all ecological restoration categories are allocated, otherwise, return to step S532 to continue allocation; Step S54: Calculate the proximity effect and the overall probability. For each ecological restoration category, after pre-allocation, calculate the proximity effect, and calculate the overall probability by combining the transition probability and the proximity effect. Step S55: Based on the overall probability, a roulette wheel selection mechanism is constructed to determine the target allocation type of each cell, and the position where the roulette wheel stops is determined by a random number between 0 and 1, so as to select a specific ecological restoration category for allocation; Step S56: Iteration and adjustment, check whether the results of the current round meet the requirements of all ecological restoration categories. If not, adjust the allocation ratio and return to step S52 to continue the next round of iteration. If the requirements of all ecological restoration categories are met, end.

Images