A robust optimization method and system for natural reserve elastic zoning

Abstract

This application discloses a robust optimization method and system for flexible zoning of nature reserves. The method includes: acquiring ecological attribute data of each planning unit under multiple future scenarios; determining the protection benefits of each spatial zoning scheme under each future scenario based on the ecological attribute data and preset protection constraint parameters; wherein each decision variable in the spatial zoning scheme is obtained by encoding whether each planning unit is assigned to a strictly protected area; for each spatial zoning scheme, obtaining a fitness function by subtracting a spatial fragmentation penalty term from the minimum protection benefit under all future scenarios; maximizing the minimum protection benefit under all future scenarios constitutes the robust optimization objective; using a genetic algorithm to search for the spatial zoning scheme that maximizes the fitness function value, thereby obtaining a flexible zoning scheme that satisfies the robust optimization objective and preset budget constraints; and mapping the flexible zoning scheme to geographic space to generate a protected area zoning map.

Description

Technical Field

[0001] This application relates to the field of spatial planning technology for nature reserves, and relates to, but is not limited to, a robust and optimized flexible zoning method and system for nature reserves. Background Technology

[0002] Different regions within nature reserves exhibit significant variations in ecological sensitivity, resource distribution, and the intensity of human activities. Spatial zoning is necessary to achieve differentiated management of these regions and balance conservation with development. Currently, nature reserve zoning planning commonly employs deterministic optimization tools such as Marxan and Zonation. These tools, given current species distributions and threat patterns, can determine the minimum area or highest priority set of regions that meet conservation objectives. However, due to profound uncertainties such as climate change, natural disasters, and human migration, optimal zoning schemes generated based on a single current scenario may experience a sharp decline in conservation effectiveness under different future stress scenarios, potentially leading to the failure of ecosystem conservation goals.

[0003] In related technologies, deterministic optimization tools are run for multiple possible future scenarios to obtain several alternative partitioning schemes. Planners then select the optimal scheme based on expert experience or auxiliary decision-making criteria. In addition, some studies have attempted to introduce stochastic programming methods, incorporating uncertainty into the optimization model for unified solution by pre-setting the probability of occurrence for each future scenario.

[0004] However, the multi-scenario ex-post optimization paradigm essentially involves compromises among existing alternatives. The performance ceiling of the final solution is limited by the quality of the alternative set, failing to guarantee that basic protection requirements will be met even in the worst-case scenario. Stochastic programming methods rely on the accuracy of scenario probability presuppositions; under deep uncertainty, probabilities are difficult to estimate reliably, leading to results that deviate from actual needs. Both of these methods treat future predictions as deterministic states, and their decision-making logic remains within a deterministic paradigm of prediction and optimization. When different predictions present significantly different future scenarios, their decision robustness is insufficient in the face of deep uncertainty, and they cannot balance protection effectiveness across multiple scenarios. Summary of the Invention

[0005] In view of this, the embodiments of this application provide a robust and optimized flexible zoning method and system for nature reserves, which at least solves the technical problems in the related art of insufficient decision robustness of nature reserve zoning schemes when facing deep uncertainty and the inability to balance the protection effectiveness under multiple scenarios.

[0006] The technical solution of this application embodiment is implemented as follows: In a first aspect, embodiments of this application provide a robust and optimized method for the flexible zoning of nature reserves, the method comprising: Ecological attribute data of each planning unit under multiple future scenarios are obtained; the planning unit is obtained by dividing the target nature reserve into grids. Based on the ecological attribute data and preset protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are determined; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area; For each of the aforementioned spatial partitioning schemes, a fitness function is obtained by subtracting a spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective. A genetic algorithm is used to search for the spatial partitioning scheme that maximizes the value of the fitness function, thereby obtaining an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint. The flexible zoning scheme is mapped to geospatial data to generate protected area zoning maps.

[0007] Secondly, embodiments of this application provide a robust and optimized flexible zoning system for nature reserves, the system comprising: a data acquisition module, a benefit determination module, a function determination module, a solution module, and a mapping module; The data acquisition module is used to acquire ecological attribute data of each planning unit under multiple future scenarios; the planning unit is obtained by dividing the target nature reserve into grids. The benefit determination module is used to determine the protection benefit of each spatial zoning scheme under each future scenario based on the ecological attribute data and preset protection constraint parameters; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area; The function determination module is used to obtain a fitness function for each spatial partitioning scheme by subtracting a spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective. The solution module is used to search for the spatial partitioning scheme that maximizes the value of the fitness function using a genetic algorithm, thereby obtaining an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint. The mapping module is used to map the flexible zoning scheme to geospatial space to generate protected area zoning maps.

[0008] The beneficial effects of the technical solutions provided in this application include at least the following: This application obtains ecological attribute data for each planning unit under multiple future scenarios; the planning unit is obtained by gridding the target nature reserve. Based on the ecological attribute data and preset protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are determined; the spatial zoning scheme consists of multiple decision variables, each of which is coded by whether each planning unit is assigned to a strictly protected area. By combining the ecological attribute data with the protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are calculated, allowing for objective comparison and ranking of the protection effects of different spatial zoning schemes under different future scenarios. For each spatial zoning scheme, a fitness function is obtained by subtracting a spatial fragmentation penalty term from the minimum protection benefit across all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; the maximization of the minimum protection benefit across all future scenarios constitutes the robust optimization objective. The fitness function simultaneously considers the protection effectiveness and spatial compactness of the spatial zoning scheme under the most unfavorable future scenario. The robust optimization objective guides the search to improve the protection performance of the spatial zoning scheme under the worst-case scenario, avoiding excessively low protection effectiveness of the scheme under certain future scenarios. A genetic algorithm is used to search for spatial partitioning schemes that maximize the fitness function, resulting in flexible partitioning schemes that satisfy robust optimization objectives and preset budget constraints. The genetic algorithm can locate the scheme with the maximum fitness function among a large number of candidate spatial partitioning schemes, ensuring that the protection benefits of the flexible partitioning scheme remain at a high level under the most unfavorable future scenario, while meeting the preset budget constraints in terms of area and resource consumption. The flexible partitioning scheme is mapped to geospatial data to generate protected area partitioning maps. The binary-coded flexible partitioning schemes obtained by the genetic algorithm are converted into visual geographic information layers. This transforms the abstract flexible partitioning scheme into practical protected area partitioning maps that can be directly used for the optimization and adjustment of protected area boundaries and hierarchical management, facilitating use by managers in practical work. Therefore, this application improves the decision robustness of nature reserve partitioning schemes in the face of deep uncertainty through robust optimization methods, ensuring the protection effectiveness of the partitioning schemes under multiple future scenarios. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 A flowchart illustrating a robust and optimized flexible zoning method for nature reserves provided in this application embodiment; Figure 2 A schematic diagram of the iterative convergence curve of the genetic algorithm for the method provided in the embodiments of this application; Figure 3 A schematic diagram of the flexible partitioning scheme of the method provided in the embodiments of this application; Figure 4 This is a schematic diagram of a robust and optimized flexible zoning system for nature reserves provided in an embodiment of this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0012] It should be noted that the terms "first, second, and third" used in the embodiments of this application are merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, and third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0013] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments of this application pertain. It should also be understood that terms such as those defined in general dictionaries should be understood to have a meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0014] This application provides a robust and optimized method for the flexible zoning of nature reserves. Figure 1 A flowchart illustrating a robust and optimized flexible zoning method for nature reserves provided in this application embodiment is shown below. Figure 1 As shown, the method includes at least the following steps: Step S110: Obtain ecological attribute data for each planning unit under multiple future scenarios; the planning unit is obtained by dividing the target nature reserve into grids.

[0015] Optionally, multiple future scenarios are calculated using pre-determined ecological prediction models based on different climate pathways or the intensity of human disturbance.

[0016] Different climate pathways affect the input values ​​of environmental variables such as temperature and precipitation in ecological prediction models. Representative concentration pathways can be used, including three standard scenarios: RCP2.6, RCP4.5, and RCP8.5. Under the RCP2.6 scenario, the temperature increase is relatively small, and the precipitation pattern changes only slightly, resulting in a relatively stable suitable habitat area output by the ecological prediction model. Under the RCP8.5 scenario, the temperature increase is larger, and the spatiotemporal distribution of precipitation changes significantly, potentially leading to a reduction or shift in the suitable habitat area output by the ecological prediction model.

[0017] Anthropogenic disturbance intensity is classified into three levels: low, medium, and high, based on the type and extent of human activities. Low disturbance intensity maintains the existing land use pattern, with population density and infrastructure construction remaining at current levels; medium disturbance intensity allows for moderate development, with a land use change rate of approximately 0.5% per year and a slight increase in transportation network density; high disturbance intensity corresponds to rapid urbanization and agricultural expansion, with a land use change rate of approximately 2% per year and a significant increase in infrastructure such as roads and hydropower stations.

[0018] By combining the aforementioned climate paths with the intensity of anthropogenic disturbances—for example, pairing three climate paths with three different anthropogenic disturbance intensities—nine future scenarios are obtained. Each future scenario corresponds to a set of input parameters for an ecological prediction model. By running the pre-determined ecological prediction model, a set of ecological attribute data, including species distribution data, ecosystem service data, and conservation cost data, is generated for each planning unit.

[0019] The entire target nature reserve is divided into multiple grids of uniform specifications, serving as planning units. Specifications include shape and size.

[0020] Step S120: Based on the ecological attribute data and preset protection constraint parameters, determine the protection benefits of each spatial zoning scheme under each future scenario; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area.

[0021] The preset protection constraint parameters are pre-set and used to measure whether the spatial zoning scheme meets the protection requirements.

[0022] Optionally, the preset protection constraint parameters include the minimum number or proportion of each target species to be protected, and the lower limit threshold for the protection target of ecosystem services.

[0023] Optionally, the strictly protected area is the area with the highest level of protection in the flexible zoning scheme; all the decision variables constitute a binary vector, and the binary vector corresponds to one of the spatial zoning schemes.

[0024] Protection benefits are numerical values ​​used to evaluate the degree to which a spatial zoning scheme achieves preset protection constraints under future scenarios. The decision variable is the binary encoding of whether a planning unit is included in a strictly protected area. A strictly protected area is the region receiving the highest level of protection in the spatial zoning scheme.

[0025] By combining ecological attribute data with conservation constraint parameters, the conservation benefits of each spatial zoning scheme are calculated under each future scenario, enabling objective comparison and ranking of the conservation effects of different spatial zoning schemes under different future scenarios.

[0026] Step S130: For each of the spatial partitioning schemes, a fitness function is obtained by subtracting the spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective.

[0027] The spatial fragmentation penalty is used to reduce the fitness value of spatial morphological fragmentation schemes.

[0028] Optionally, the preset spatial constraint parameters include a boundary length penalty coefficient; the spatial fragmentation penalty term is calculated by multiplying the total boundary length of the planning unit by the boundary length penalty coefficient. The preset spatial constraint parameters are used to guide the output of a spatially compact spatial partitioning scheme, avoiding the output of a spatial partitioning scheme that lacks practical management feasibility.

[0029] The boundary length of a planning unit is the total length of the adjacent boundaries between planning units selected for strict protection zones. The fitness function is used to evaluate the merits of spatial zoning schemes. The robust optimization objective is the optimization direction that minimizes the protection benefits across all future scenarios.

[0030] The fitness function balances the protection effectiveness of the spatial partitioning scheme under the worst-case future scenario with the compactness of the spatial morphology. The robust optimization objective guides the search to improve the protection performance of the spatial partitioning scheme under the worst-case scenario, avoiding excessively low protection effectiveness in certain future scenarios.

[0031] Step S140: Use a genetic algorithm to search for the spatial partitioning scheme that maximizes the value of the fitness function, and obtain an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint.

[0032] Optionally, the preset budget constraints include an area budget cap and a resource budget cap; the area budget cap is used to constrain the total area of ​​planning units selected for strict protection zones, and the resource budget cap is used to constrain the total protection costs of planning units selected for strict protection zones. The preset budget constraints are not targeted at any specific species or ecosystem, but are used to ensure the feasibility of the spatial zoning scheme within the available resources and manageable area.

[0033] Genetic algorithms are search algorithms that simulate the natural selection process, finding the spatial partitioning scheme with the largest fitness function value among a large number of possible spatial partitioning schemes.

[0034] The fitness function is a numerical value used to evaluate the quality of a spatial partitioning scheme. The larger the fitness function value, the better the overall performance of the spatial partitioning scheme.

[0035] The goal of robust optimization is to optimize in the direction that minimizes the protection benefit in all future scenarios.

[0036] A genetic algorithm is used to search for spatial partitioning schemes that maximize the fitness function, resulting in resilient partitioning schemes that satisfy the robust optimization objective and preset budget constraints. The genetic algorithm can locate the spatial partitioning scheme with the maximum fitness function among a large number of candidate schemes, ensuring that the resilient partitioning scheme maintains a high level of protection benefit under the worst future scenario, while also meeting the preset budget constraints in terms of area and resource consumption.

[0037] Step S150: Map the flexible zoning scheme to geospatial space to generate a protected area zoning map.

[0038] Geospatial refers to the geographic coordinate system in which the target nature reserve is located. A protected area zoning map is a vector map file that includes the strict boundaries of the protected area and the boundaries of the surrounding buffer zone.

[0039] The flexible zoning scheme obtained by the genetic algorithm in binary encoding is converted into a visualized geographic information layer. This transforms the abstract flexible zoning scheme into a practical protected area zoning map that can be directly used for the optimization and adjustment of protected area boundaries and hierarchical management, making it convenient for managers to use in their work.

[0040] This application obtains ecological attribute data for each planning unit under multiple future scenarios; the planning unit is obtained by gridding the target nature reserve. Based on the ecological attribute data and preset protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are determined; the spatial zoning scheme consists of multiple decision variables, each of which is coded by whether each planning unit is assigned to a strictly protected area. By combining the ecological attribute data with the protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are calculated, allowing for objective comparison and ranking of the protection effects of different spatial zoning schemes under different future scenarios. For each spatial zoning scheme, a fitness function is obtained by subtracting a spatial fragmentation penalty term from the minimum protection benefit across all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; the maximization of the minimum protection benefit across all future scenarios constitutes the robust optimization objective. The fitness function simultaneously considers the protection effectiveness and spatial compactness of the spatial zoning scheme under the most unfavorable future scenario. The robust optimization objective guides the search to improve the protection performance of the spatial zoning scheme under the worst-case scenario, avoiding excessively low protection effectiveness of the scheme under certain future scenarios. A genetic algorithm is used to search for spatial partitioning schemes that maximize the fitness function, resulting in flexible partitioning schemes that satisfy robust optimization objectives and preset budget constraints. The genetic algorithm can locate the scheme with the maximum fitness function among a large number of candidate spatial partitioning schemes, ensuring that the protection benefits of the flexible partitioning scheme remain at a high level under the most unfavorable future scenario, while meeting the preset budget constraints in terms of area and resource consumption. The flexible partitioning scheme is mapped to geospatial data to generate protected area partitioning maps. The binary-coded flexible partitioning schemes obtained by the genetic algorithm are converted into visual geographic information layers. This transforms the abstract flexible partitioning scheme into practical protected area partitioning maps that can be directly used for the optimization and adjustment of protected area boundaries and hierarchical management, facilitating use by managers in practical work. Therefore, this application improves the decision robustness of nature reserve partitioning schemes in the face of deep uncertainty through robust optimization methods, ensuring the protection effectiveness of the partitioning schemes under multiple future scenarios.

[0041] Optionally, the preset protection constraint parameters include a preset lower protection threshold; the ecological attribute data includes species distribution data, ecosystem service data, and protection cost data; determining the protection benefit of each spatial zoning scheme under each future scenario based on the ecological attribute data and the preset protection constraint parameters includes: for each spatial zoning scheme and each future scenario, calculating the protection quantity of each protection item based on the ecological attribute data; the protection item includes target species and ecosystem services; comparing each protection quantity with the corresponding preset lower protection threshold to obtain the protection compliance rate of each protection item; and performing a weighted summation of each protection compliance rate to obtain the protection benefit of each spatial zoning scheme under each future scenario.

[0042] The protection compliance rate is calculated as shown in formula (1): Formula (1); in, To protect the compliance rate, For the first The protection quantity of each protection item under each planning unit This is the preset lower protection threshold.

[0043] The calculation of the protection benefit is shown in formula (2): Formula (2); in, The total number of planning units, For the first The weight of each planning unit, Protect profits, For a certain future scenario.

[0044] The higher the protection benefit, the better the spatial zoning scheme achieves the overall protection goal under the given future scenario.

[0045] Optionally, for each of the spatial partitioning schemes, a fitness function is obtained by subtracting a spatial fragmentation penalty term from the minimum protection benefit across all future scenarios. The spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit. The fitness function is shown in formula (3): Formula (3); in, The value of the fitness function. This is a penalty term for spatial fragmentation. Here, λ is the spatial fragmentation penalty value, and λ is the preset penalty coefficient. To minimize the protection benefits of the current spatial zoning scheme under all future scenarios, For all future scenarios.

[0046] The spatial fragmentation penalty is the total boundary length of the planning unit, which is the sum of the number of boundary segments adjacent to the unselected unit.

[0047] The value of the preset penalty coefficient is determined through sensitivity analysis. Specifically, several candidate values ​​are selected at exponential intervals within the preset range, and the genetic algorithm is run on each. By comparing the protection benefits and spatial fragmentation performance of the optimal solution set obtained under different candidate values ​​in the worst-case scenario, the parameter that can significantly reduce the boundary length while keeping the reduction in protection benefits within an acceptable threshold is selected as the final setting; or it can be directly set by referring to the empirical value of the boundary length adjustment factor in the field of protected area planning.

[0048] Optionally, the candidate scheme set of the genetic algorithm is initialized using a greedy strategy, including: for each protection item, calculating the protection contribution per unit area of ​​each planning unit; selecting planning units in descending order of the protection contribution per unit area; stopping the selection when the selected planning unit touches the upper limit of the area budget or the upper limit of the resource budget in the preset budget constraint, and generating the spatial partitioning scheme.

[0049] The spatial partitioning scheme generated by the greedy strategy has high protection efficiency and naturally satisfies the preset budget constraint, reducing the computational overhead of handling infeasible solutions in subsequent iterations and accelerating the convergence speed of the genetic algorithm.

[0050] Optionally, during the solution process, the genetic algorithm assigns negative values ​​below the normal fitness range to spatial partitioning schemes that violate the preset budget constraint, so that the spatial partitioning schemes are eliminated in the iteration of the candidate scheme set.

[0051] For spatial partitioning schemes that violate the upper limits of the area budget or resource budget in the preset budget constraints, their fitness function is assigned a negative value below the normal fitness range, causing the spatial partitioning scheme to be eliminated in the selection operation of the genetic algorithm. A greedy strategy is used to generate the initial spatial partitioning schemes in the candidate scheme set during initialization. The greedy strategy includes the following steps: for each protection item, calculate the protection contribution per unit area of ​​each planning unit, where the protection contribution per unit area is the ratio of the ecological attribute data of the planning unit on that protection item to the area of ​​the planning unit; select planning units in descending order of protection contribution per unit area; stop selection when the selected planning unit reaches the upper limit of the area budget or resource budget in the preset budget constraints, and generate the spatial partitioning schemes in the initial candidate scheme set.

[0052] As an exemplary implementation, the size of the spatial partitioning scheme set is set to 100 to 500 spatial partitioning schemes, the crossover probability is set to 0.8 to 0.9, the mutation probability is set to 0.01 to 0.05, the selection operator adopts tournament selection and the tournament size is set to 3 to 5, the termination condition is set to a maximum iteration generation of 1000 generations or the rate of change of the fitness function value of the best spatial partitioning scheme for 50 consecutive generations is less than 0.001%, and an elite retention strategy is adopted to copy the spatial partitioning scheme with the largest fitness function value in each generation to the next generation.

[0053] Figure 2 This diagram illustrates the iterative convergence curve of the genetic algorithm used in the embodiments of this application. The horizontal axis represents the number of iterations, and the vertical axis represents the value of the fitness function. The solid line represents the maximum fitness function value of the spatial partitioning scheme in each generation's candidate scheme set, and the dashed line represents the average fitness function value of each generation's candidate scheme set. Figure 2 As shown, with the iteration, the value of each fitness function gradually increases and tends to stabilize, indicating that the genetic algorithm has converged to a stable elastic partitioning scheme.

[0054] Based on the one-to-one correspondence between the division results of each zone in the converged optimal spatial zoning scheme and the planning units, the set of planning units designated as strictly protected areas is identified, and this set is mapped to geographic space to generate the boundaries of the strictly protected areas. On this basis, the area surrounding the strictly protected areas is designated as a buffer zone, forming a protected area zoning map that includes the boundaries of the strictly protected areas and the buffer zone. This protected area zoning map serves as the technical basis for the optimization, adjustment, and hierarchical management of nature reserve boundaries.

[0055] Figure 3 This is a schematic diagram of the flexible partitioning scheme of the method provided in the embodiments of this application. Figure 3 As shown, the flexible zoning scheme divides the planning area into different functional blocks, demonstrating the spatial layout and boundary delineation results of strictly protected areas, buffer zones, and other areas generated by the method of this application. The gray shaded grid represents the strictly protected area, the area outside the strictly protected area marked by a dashed box is the buffer zone, the dashed box represents the boundary of the buffer zone, and the white grid areas not included in the above two zones represent the other areas.

[0056] The following describes a robust and optimized flexible zoning method for nature reserves according to this application, with reference to a specific embodiment. This specific embodiment is merely for better illustrating the invention and does not constitute an undue limitation of the invention.

[0057] To demonstrate that the proposed solution offers higher protection benefits than traditional deterministic optimization schemes under the worst-case future scenario, three future scenarios were selected, and three methods were applied: Method A (Prior Art): Deterministic optimization was performed on Scenario 1 to obtain Solution A. Method B (Prior Art): Deterministic optimization was performed on each scenario separately, and the spatial intersection of the solutions was taken to obtain Solution B. Method C (Proposed Solution): Optimization was performed on all scenarios to obtain Flexible Partitioning Solution C. Solutions A, B, and C were then substituted into all scenarios to calculate the protection benefits under each scenario, and the worst-case benefit of each spatial partitioning solution was used as the evaluation metric.

[0058] Table 1. Comparison of protection benefits of different spatial zoning schemes

[0059] In Table 1, the worst-case scenario benefit is the core optimization objective of this embodiment. The comparison shows that the worst-case benefit of scheme C is higher than that of schemes A and B, proving that the elastic partitioning scheme generated in this embodiment can effectively improve the decision robustness of the partitioning scheme under deep uncertainty.

[0060] To verify the effectiveness of introducing a boundary length penalty term in improving the compactness of the spatial layout, this application sets up a comparative experiment. The method of this application was run in two scenarios: one without a spatial guidance mechanism and with a penalty coefficient set to 0, and the other with a spatial guidance mechanism and a penalty coefficient greater than 0. The spatial layout indicators and core optimization objectives of the spatial partitioning schemes were statistically analyzed and compared. Specific data are shown in Table 2.

[0061] Table 2 Comparison of the impact of boundary length penalty on space compactness and core benefits

[0062] Table 2 shows that after introducing the boundary length penalty term, this scheme significantly reduces spatial fragmentation, even with the worst-case benefit decreasing only from 0.84 to 0.82 (a reduction of approximately 2.4%). Specifically, the number of patches is sharply reduced from 23 to 4, the total boundary length is shortened from 1850 to 620 (a reduction of 66%), and the area share of the largest patch increases to 78%. These data demonstrate that the introduction of the boundary length penalty term guides the algorithm to generate a spatially compact, morphologically regular, and highly implementable flexible zoning scheme.

[0063] Figure 4 A schematic diagram of a robust and optimized flexible zoning system for nature reserves provided in this application embodiment is shown below. Figure 4 As shown, this application proposes a robust optimization flexible zoning system for nature reserves. The system 400 includes: a data acquisition module 410, a benefit determination module 420, a function determination module 430, a solution module 440, and a mapping module 450. The data acquisition module 410 is used to acquire ecological attribute data of each planning unit under multiple future scenarios; the planning unit is obtained by dividing the target nature reserve into grids. The benefit determination module 420 is used to determine the protection benefit of each spatial zoning scheme under each future scenario based on the ecological attribute data and preset protection constraint parameters; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area; The function determination module 430 is used to obtain a fitness function for each spatial partitioning scheme by subtracting a spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective. The solution module 440 is used to search for the spatial partitioning scheme that maximizes the value of the fitness function using a genetic algorithm, so as to obtain an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint. The mapping module 450 is used to map the flexible zoning scheme to geospatial space to generate protected area zoning maps.

[0064] It should be noted that the description of the above system embodiments is similar to the description of the above method embodiments, and has similar beneficial effects. For technical details not disclosed in the system embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0065] It should be noted that, in the embodiments of this application, if the above-mentioned robustly optimized flexible zoning method for nature reserves is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0066] Correspondingly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the steps in any of the robustly optimized resilient zoning methods for nature reserves described in the above embodiments. Correspondingly, embodiments of this application also provide a computer program product, which, when executed by a processor of an electronic device, is used to implement the steps in any of the robustly optimized resilient zoning methods for nature reserves described in the above embodiments.

[0067] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0068] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0070] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected to achieve the purpose of the embodiments of this application according to actual needs. In addition, each functional unit in the embodiments of this application may be fully integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the integrated unit may be implemented in hardware or in the form of hardware plus software functional units.

[0071] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause the device automatic test line to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0072] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined to obtain new method embodiments without conflict. The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined to obtain new method embodiments or device embodiments without conflict.

[0073] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A robust and optimized method for flexible zoning of nature reserves, characterized in that, The method includes: Ecological attribute data of each planning unit under multiple future scenarios are obtained; the planning unit is obtained by dividing the target nature reserve into grids. Based on the ecological attribute data and preset protection constraint parameters, the protection benefits of each spatial zoning scheme under each future scenario are determined; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area; For each of the aforementioned spatial partitioning schemes, a fitness function is obtained by subtracting a spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective. A genetic algorithm is used to search for the spatial partitioning scheme that maximizes the value of the fitness function, thereby obtaining an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint. The flexible zoning scheme is mapped to geospatial data to generate protected area zoning maps.

2. The method according to claim 1, characterized in that, The preset protection constraint parameters include preset protection lower limit thresholds; the ecological attribute data include species distribution data, ecosystem service data, and protection cost data; The determination of the conservation benefits of each spatial zoning scheme under each future scenario based on the ecological attribute data and preset protection constraint parameters includes: For each of the aforementioned spatial zoning schemes and each of the aforementioned future scenarios, the conservation quantity of each conservation item is calculated based on the aforementioned ecological attribute data; the conservation items include target species and ecosystem services. Each of the protection quantities is compared with its corresponding preset lower protection threshold to obtain the protection compliance rate of each protection item; The protection compliance rate of each of the above-mentioned schemes is weighted and summed to obtain the protection benefit of each of the above-mentioned spatial partitioning schemes under each of the above-mentioned future scenarios.

3. The method according to claim 1, characterized in that, The multiple future scenarios are calculated using pre-determined ecological prediction models based on different climate paths or the intensity of human disturbance.

4. The method according to claim 1, characterized in that, The preset protection constraint parameters include the minimum number or proportion of each target species to be protected, and the lower limit threshold for the protection target of ecosystem services.

5. The method according to claim 1, characterized in that, The strictly protected area is the area with the highest level of protection in the flexible zoning scheme; all the decision variables constitute a binary vector, and the binary vector corresponds to one of the spatial zoning schemes.

6. The method according to claim 1, characterized in that, The preset budget constraints include an upper limit for area budget and an upper limit for resource budget; The area budget cap is used to constrain the total area of ​​planning units selected for strict protection zones, and the resource budget cap is used to constrain the total protection cost of planning units selected for strict protection zones.

7. The method according to claim 1, characterized in that, The preset spatial constraint parameters include the boundary length penalty coefficient; The spatial fragmentation penalty term is calculated by multiplying the total boundary length of the planning unit by the boundary length penalty coefficient.

8. The method according to claim 1, characterized in that, The candidate solution set of the genetic algorithm is initialized using a greedy strategy, including: For each protection item, calculate the protection contribution per unit area for each planning unit; Planning units are selected in descending order of their protection contribution per unit area; When the selected planning unit reaches the upper limit of the area budget or the upper limit of the resource budget in the preset budget constraints, the selection stops and the spatial zoning scheme is generated.

9. The method according to claim 1, characterized in that, During the solution process, the genetic algorithm assigns negative values ​​below the normal fitness range to spatial partitioning schemes that violate the preset budget constraint, thereby eliminating the spatial partitioning schemes in the iterative candidate scheme set.

10. A robust and optimized flexible zoning system for nature reserves, characterized in that, The system includes: a data acquisition module, a profit determination module, a function determination module, a solution module, and a mapping module; The data acquisition module is used to acquire ecological attribute data of each planning unit under multiple future scenarios; the planning unit is obtained by dividing the target nature reserve into grids. The benefit determination module is used to determine the protection benefit of each spatial zoning scheme under each future scenario based on the ecological attribute data and preset protection constraint parameters; wherein, the spatial zoning scheme consists of multiple decision variables, and each decision variable is obtained by encoding whether each planning unit is assigned to a strictly protected area; The function determination module is used to obtain a fitness function for each spatial partitioning scheme by subtracting a spatial fragmentation penalty term from the minimum value of the protection benefit under all future scenarios; the spatial fragmentation penalty term is calculated based on preset spatial constraint parameters and the boundary length of the planning unit; wherein, maximizing the minimum value of the protection benefit under all future scenarios constitutes the robust optimization objective. The solution module is used to search for the spatial partitioning scheme that maximizes the value of the fitness function using a genetic algorithm, thereby obtaining an elastic partitioning scheme that satisfies the robust optimization objective and the preset budget constraint. The mapping module is used to map the flexible zoning scheme to geospatial space to generate protected area zoning maps.

Images