A method, device and equipment for assessing carbon sink potential of ecological restoration in an open-pit mine area

Abstract

The present application relates to the technical field of ecological environment and carbon emission management, and discloses a method, device and equipment for evaluating carbon sink potential of ecological restoration in an open-pit mine area, which comprises the following steps: obtaining basic data of the mine area, and constructing a multi-dimensional remote sensing data cube, an environmental factor database and a species distribution sample database based on the basic data of the mine area; generating a closed pit spatiotemporal distribution database based on the multi-dimensional remote sensing data cube; modeling the habitat suitability probability of species based on the environmental factor database, the species distribution sample database and the closed pit spatiotemporal distribution database, and generating an ecological restoration suitability spatial zoning database; generating a carbon sink potential spatiotemporal distribution map based on the closed pit spatiotemporal distribution database and the ecological restoration suitability spatial zoning database, and evaluating the carbon sink potential of the mine area based on the carbon sink potential spatiotemporal distribution map; the present application can finely depict the spatiotemporal evolution law of the restoration of the mine area, dynamically quantify the carbon fixation potential of different restoration measures and species types, and obtain a scientific carbon sink evaluation method.

Description

Technical Field

[0001] This invention relates to the field of ecological environment and carbon emission management technology, specifically to a method, apparatus and equipment for assessing the carbon sink potential of open-pit mine ecological restoration. Background Technology

[0002] With the rapid development of energy extraction activities, the long-term operation of large-scale open-pit coal mines has not only caused serious disturbance to the ecological environment, but also created a large number of abandoned mining areas, i.e., mine closures. After mine closures, abandoned mining areas have enormous potential for ecological restoration, especially in the process of vegetation reconstruction, which can significantly increase carbon storage and provide important potential for contributing to regional carbon sequestration.

[0003] However, there are still significant deficiencies in the dynamic monitoring and quantification of the ecological restoration process and carbon sink potential of abandoned open-pit mines. Existing studies are mostly focused on case studies of local mines or assessments of single restoration measures, lacking a unified monitoring technology system covering large-scale mines, a systematic and spatialized global database, and scientific carbon sink estimation methods. Summary of the Invention

[0004] This invention provides a method, apparatus, and equipment for assessing the carbon sink potential of open-pit mine ecological restoration, in order to solve the problem of the lack of a systematic, spatialized, and comprehensive database and scientific carbon sink estimation in the existing technology.

[0005] In a first aspect, the present invention provides a method for assessing the carbon sink potential for ecological restoration in open-pit mines, the method comprising:

[0006] Acquire basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database and a species distribution sample database;

[0007] Generate a database of the spatiotemporal distribution of closed pits based on multidimensional remote sensing data cubes;

[0008] Based on environmental factor databases, species distribution sample databases, and closed pit spatiotemporal distribution databases, we conduct probabilistic modeling of species habitat suitability to generate a spatial zoning database of ecological restoration suitability.

[0009] Based on the spatial and temporal distribution database of mine closures and the spatial zoning database of ecological restoration suitability, a spatial and temporal distribution map of carbon sink potential is generated, and the carbon sink potential of the mining area is assessed based on the spatial and temporal distribution map of carbon sink potential.

[0010] This invention provides a method for assessing the carbon sequestration potential of open-pit mine ecological restoration. By acquiring basic data of the mining area and constructing a spatiotemporal geographic database based on this data, including a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database, a systematic and integrated technical route is formed, encompassing remote sensing identification of mine closure time, suitability assessment of ecological restoration, and carbon sequestration potential calculation. This results in a systematic and spatialized full-domain database, enabling end-to-end analysis of open-pit mines from "disturbance identification - restoration suitability - carbon sequestration quantification." This method can precisely depict the spatiotemporal evolution of mine restoration, dynamically quantify the carbon sequestration potential of different restoration measures and species types, and obtain a scientific carbon sequestration estimation method. It provides a scientific basis and technical support for the green transformation and carbon neutrality strategy of mining areas, solving the problem of the lack of a systematic and spatialized full-domain database and scientific carbon sequestration estimation in existing technologies.

[0011] In one optional implementation, the basic data for the mining area includes: multi-source remote sensing data of land cover, environmental factor data, and species distribution data;

[0012] Based on multi-source remote sensing data of land cover, vegetation index, bare land index and surface temperature index are calculated, and the vegetation index, bare land index and surface temperature index are reconstructed and smoothed in time series to generate a multi-dimensional remote sensing data cube that covers the mining area and is in time series continuous.

[0013] Multidimensional environmental factors are extracted from environmental factor data and integrated into a unified environmental factor database. These multidimensional environmental factors include topographic factors, soil factors, climate factors, and land use types.

[0014] Known distribution points of species were extracted from the species distribution data, and data preprocessing was performed on the known distribution points of species to unify coordinates and clean the data, generating a species distribution sample database for suitability modeling. The known distribution points of species include known distribution points of tree species, known distribution points of shrub species and known distribution points of grass species.

[0015] This invention provides a method for assessing the carbon sink potential of open-pit mine ecological restoration. By systematically integrating multi-source data such as land cover, environmental factors, and species distribution, and constructing a time-series continuous multidimensional remote sensing data cube and a standardized environmental database, it achieves consistency of data foundation, refinement of spatial expression, and reliability of modeling input in the process of assessing the ecological restoration potential of mine areas. This provides unified and high-quality data support for subsequent mine closure identification, suitability evaluation, and carbon sink calculation, significantly improving the accuracy and operability of the whole-link analysis.

[0016] In one optional implementation, the basic data of the mining area also includes: mining area archives;

[0017] Before generating a database of the spatiotemporal distribution of closure pits based on multidimensional remote sensing data cubes, this method also includes:

[0018] The boundary coordinates of the mining area are extracted from the mining area archives and imported into the geographic information system to generate a sample dataset of the mining area.

[0019] Multiple mining area vector boundary layer datasets are collected from a preset cloud processing platform and then fused to form an initial mining area boundary.

[0020] Based on multi-source remote sensing data and environmental factor data, a multi-dimensional feature space is constructed to characterize the disturbance features of mining areas.

[0021] Using a sample dataset of the mining area and a multidimensional feature space as input data, a deep learning algorithm is used to spatially correct the initial mining area boundary, forming the corrected mining area boundary.

[0022] This invention provides a method for assessing the carbon sink potential of open-pit mine ecological restoration. By integrating multi-source information such as mine archives, shared platform data, remote sensing, and environmental factors, and using deep learning algorithms to spatially correct the initial boundary, it significantly improves the accuracy and reliability of mine boundary identification. This provides an accurate spatial analysis basis for subsequent mine closure time identification, ecological restoration suitability assessment, and carbon sink potential estimation, effectively overcoming the problems of incomplete boundaries and large location deviations caused by traditional reliance on a single data source.

[0023] In one optional implementation, a closure spatiotemporal distribution database is generated based on a multidimensional remote sensing data cube, including:

[0024] Sample points and corresponding pixel time-series feature vectors of known closure years are extracted from mining area archives to form a training sample set.

[0025] Within the corrected boundary of the mining area, the BFAST temporal breakpoint algorithm is used to perform pixel-by-pixel analysis on the multidimensional remote sensing data cube to identify abrupt change points in the temporal features of pixels.

[0026] A pre-defined deep learning model is trained based on mutation points and training sample sets to obtain the judgment rules for the steady-state transition of the closure pit.

[0027] The determination rules are applied to all pixels in the entire mining area to obtain the year of closure of each pixel. The mode of the closure years of all pixels is then aggregated to generate the closure time of the entire mining area, forming a spatiotemporal distribution database of closures.

[0028] This invention provides a method for assessing the carbon sink potential of open-pit mine ecological restoration. By integrating BFAST temporal breakpoint detection with a deep learning model, it achieves high-precision and automated identification of mine closure time. It can effectively capture the temporal transition characteristics of "perturbation-recovery" at the pixel scale, overcoming the problems of poor timeliness, strong subjectivity, and coarse spatial granularity caused by traditional reliance on manual interpretation or single archival data. Finally, it generates a spatiotemporally clear database of mine closure distribution, providing a reliable time benchmark for subsequent ecological restoration and carbon sink assessment.

[0029] In one optional implementation, based on an environmental factor database, a species distribution sample database, and a closed-pit spatiotemporal distribution database, probabilistic modeling of species habitat suitability is performed to generate a spatial zoning database of ecological restoration suitability, including:

[0030] Spatial registration and association are performed between the known distribution points of species in the species distribution sample database and the multidimensional environmental factors in the environmental factor database of their location to obtain a standardized input dataset.

[0031] Based on the standardized input dataset, the maximum entropy model was used to calculate the probability distribution of habitat suitability for various restoration measures and species, and a spatial partition map of suitability probability was generated.

[0032] Based on the suitability probability spatial zoning map, the optimal restoration measures or species types are determined for each cell through overlay analysis and the principle of probabilistic optimality, and integrated and expressed as an ecological restoration suitability spatial zoning database.

[0033] This invention provides a method for assessing the carbon sink potential of open-pit mine ecological restoration. By integrating multi-source environmental variables, species distribution data, and mine closure time information, and using a maximum entropy model for quantitative suitability probability modeling, it achieves refined spatial zoning of ecological restoration measures and species selection in mining areas. This significantly improves the scientific rigor and relevance of restoration plans, overcomes the limitations of the "one-size-fits-all" approach in traditional empirical planning, and provides a reliable spatial decision-making basis for the precise implementation of ecological restoration projects in mining areas and the maximization of carbon sink potential.

[0034] In one optional implementation, a spatiotemporal distribution database of the closure pit and a spatial zoning database of ecological restoration suitability are used to generate a spatiotemporal distribution map of carbon sink potential, including:

[0035] Based on the spatial zoning database of ecological restoration suitability, the optimal restoration measures and species types are mapped to vegetation functional types;

[0036] Based on the spatiotemporal distribution database of closed pits, the simulated starting year of the closed pit is set for each cell, and an initial vegetation cover matrix is ​​constructed.

[0037] Based on vegetation functional type, initial vegetation coverage matrix and closure start year, the model parameters of the preset Biome-BGC model are initialized by combining multidimensional environmental factors. The vegetation growth and carbon cycle process is simulated day by day starting from the closure start year to obtain pixel-by-pixel biomass dynamic data.

[0038] The dynamic biomass data of each pixel is converted into the carbon sequestration of vegetation components based on the preset carbon conversion coefficient and regional measured parameters. The total annual carbon sequestration of each pixel is obtained by superimposing the data. The total annual carbon sequestration of different vegetation functional types is then aggregated to generate a spatiotemporal distribution map of carbon sequestration potential for different restoration measures and species types.

[0039] This invention provides a method for assessing the carbon sequestration potential of open-pit mine ecological restoration. By mapping the optimal restoration scheme to vegetation functional types and simulating daily and pixel-by-pixel vegetation growth and carbon cycle based on the Biome-BGC ecological process model, it achieves a mechanistic and dynamic characterization of the carbon sequestration process in the mining area ecosystem, significantly improving the scientific rigor and accuracy of carbon sequestration potential estimation. By coupling the initial vegetation state with the year of mine closure, it ensures that the starting point of the carbon sequestration simulation is consistent with the actual restoration process of the mining area. Combining pixel-level vegetation functional types and environmental factors, a carbon sequestration distribution map with clear spatiotemporal dimensions is generated, intuitively revealing the spatial heterogeneity and time-varying patterns of carbon sequestration potential. The final generated spatiotemporal distribution map of carbon sequestration potential can clearly quantify the expected carbon sequestration benefits of different restoration measures and species types, providing a quantitative and visualized scientific basis for scheme selection, priority delineation, and carbon neutrality benefit prediction in mining area ecological restoration projects.

[0040] In one optional implementation, assessing the carbon sequestration potential of a mining area based on a spatiotemporal distribution map of carbon sequestration potential includes:

[0041] Spatial statistics were performed on the spatiotemporal distribution map of carbon sequestration potential to obtain statistical results on the total amount and average density of carbon in the mining area as a whole and in different remediation zones.

[0042] Based on statistical results and spatiotemporal distribution maps of carbon sink potential, we identify carbon sink hotspots and spatial distribution patterns, and conduct correlation analysis with remediation measures and environmental driving factors to generate decision-making basis for optimizing ecological restoration strategies.

[0043] This invention provides a method for assessing the carbon sequestration potential of open-pit mine ecological restoration. By systematically analyzing the spatial distribution and statistical characteristics of carbon sequestration potential, it achieves multi-dimensional analysis from macro-level total amount to local hotspot identification. It not only accurately quantifies the overall carbon sequestration benefits of mine ecological restoration, but also reveals its inherent spatial heterogeneity and its correlation with driving factors. This provides scientific and intuitive decision support for optimizing restoration layout, improving carbon sequestration efficiency, and formulating differentiated ecological management strategies.

[0044] Secondly, the present invention provides a device for assessing the carbon sequestration potential of open-pit mine ecological restoration, the device comprising:

[0045] The spatiotemporal geodatabase construction module is used to acquire basic data of the mining area and construct a spatiotemporal geodatabase based on the basic data of the mining area; the spatiotemporal geodatabase includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database;

[0046] The closure time identification module is used to generate a closure spatiotemporal distribution database based on a multidimensional remote sensing data cube;

[0047] The ecological restoration suitability assessment module is used to perform probabilistic modeling of species habitat suitability based on environmental factor databases, species distribution sample databases, and closed pit spatiotemporal distribution databases, and to generate a spatial zoning database of ecological restoration suitability.

[0048] The open-pit mine ecological restoration carbon sink potential assessment module is used to generate a carbon sink potential spatiotemporal distribution map based on the closed pit spatiotemporal distribution database and the ecological restoration suitability spatial zoning database, and to assess the carbon sink potential of the mining area based on the carbon sink potential spatiotemporal distribution map.

[0049] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the above-described method for assessing the carbon sink potential for ecological restoration of open-pit mines or any of its corresponding embodiments.

[0050] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the open-pit mine ecological restoration carbon sink potential assessment method described in the first aspect or any corresponding embodiment thereof.

[0051] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the open-pit mine ecological restoration carbon sink potential assessment method described in the first aspect or any corresponding embodiment. Attached Figure Description

[0052] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram of the first process of a method for assessing the carbon sink potential of open-pit mine ecological restoration according to an embodiment of the present invention.

[0055] Figure 3 This is a schematic diagram of the second process of an open-pit mine ecological restoration carbon sink potential assessment method according to an embodiment of the present invention;

[0056] Figure 4 This is a schematic diagram of the third process of an open-pit mine ecological restoration carbon sink potential assessment method according to an embodiment of the present invention.

[0057] Figure 5 This is a schematic diagram of the fourth process of an open-pit mine ecological restoration carbon sink potential assessment method according to an embodiment of the present invention;

[0058] Figure 6 This is a structural block diagram of an open-pit mine ecological restoration carbon sink potential assessment device according to an embodiment of the present invention;

[0059] Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0062] As an optional application scenario of this invention, such as Figure 1 As shown, application 101 is installed in terminal device 110, and user 130 can interact with application 101 through terminal device 110 and / or access device of terminal device 110.

[0063] For example, application 101 can be any application that provides question-and-answer related services. For instance, application 101 could be a question-and-answer interactive application, such as a text-to-text application, an image-to-text application, etc. Figure 1In the application scenario shown, if application 101 is active, the terminal device 110 can display the interface 102 of application 101. The interface 102 may include various pages that application 101 can provide, such as interactive pages, settings pages, query pages, etc.

[0064] In some embodiments, terminal device 110 is communicatively connected to server 120 to provide services to application 101. Terminal device 110 may be a mobile terminal, fixed terminal, or portable terminal, etc., including but not limited to mobile phones, desktop computers, laptop computers, multimedia tablets, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 may also support any type of interface, and server 120 may be various types of computing systems or servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0065] It should be noted that, Figure 1 This is merely an example of an application scenario and does not limit the scope of protection of this invention.

[0066] The embodiments of the present invention will now be described with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations; one or more elements may be omitted or replaced, and one or more other elements may also be present, without any limitation in the embodiments of the present invention. Furthermore, the embodiments described below primarily pertain to terminal device 110. It should be understood that the actions described relative to terminal device 110 can be performed by application 101 on terminal device 110, or can be performed by application 101 in conjunction with its server (e.g., server 120).

[0067] Existing research largely focuses on case studies of localized mining areas or assessments of single remediation measures, lacking a unified monitoring technology system covering large-scale mining areas. The duration of mine closure is a crucial factor influencing vegetation restoration and carbon sequestration, but traditional methods relying on archival data or statistical information struggle to achieve high-precision spatial positioning and cannot dynamically update closure information. Furthermore, abandoned mining areas exhibit high heterogeneity in topography, soil, climate, moisture conditions, and existing vegetation, directly impacting the suitability of different remediation measures and species. Currently, there is a lack of technical means to comprehensively integrate multi-source environmental data and achieve suitability assessments for multiple measures and species.

[0068] Remote sensing technology, with its advantages of high spatiotemporal resolution, low cost, and wide coverage, has become an important tool for monitoring ecological restoration in mining areas. By analyzing multi-source remote sensing information such as vegetation indices, bare land indices, and surface temperature, the disturbance and recovery processes of mining areas can be dynamically characterized, providing basic data for identifying mine closure times, assessing the suitability of restoration measures, and simulating carbon sequestration potential. However, for large-scale mining areas, traditional desktop remote sensing processing platforms have limited processing capabilities, failing to achieve rapid analysis and continuous monitoring of massive amounts of spatiotemporal data. To address this challenge, it is necessary to rely on the Google Earth Engine cloud processing platform for rapid acquisition, preprocessing, and large-scale analysis of multi-source remote sensing data. Simultaneously, deep learning methods should be used to automatically learn key temporal characteristics in the disturbance-recovery process, achieving high-precision, wide-range identification of mine closure times and the suitability of ecological restoration measures. In ecological restoration practices, managers select trees, shrubs, or herbaceous plants for revegetation based on local conditions, but the growth patterns and carbon sequestration efficiencies of different vegetation types vary significantly. Therefore, developing a carbon sink potential estimation technology that can integrate information on mine closure time, multiple environmental factors, and multi-species remediation measures is key to quantifying the ecological restoration value of abandoned mining areas.

[0069] This invention provides a method for assessing the carbon sink potential of open-pit mine ecological restoration. Relying on the Google Earth Engine cloud processing platform, multi-source remote sensing data, and deep learning methods, it integrates remote sensing identification of mine closure time, suitability evaluation of ecological restoration measures, and carbon sink potential simulation to achieve full-link monitoring and assessment of abandoned mine areas from "disturbance identification - restoration recommendation - carbon sink quantification," providing systematic technical support for the green transformation and carbon neutrality goals of mining areas.

[0070] According to an embodiment of the present invention, an embodiment of a method for assessing the carbon sink potential for ecological restoration in open-pit mines is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0071] This embodiment provides a method for assessing the carbon sink potential of open-pit mine ecological restoration, which can be used in the aforementioned electronic equipment. Figure 2 This is a flowchart of a method for assessing the carbon sequestration potential of open-pit mine ecological restoration according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0072] Step S201: Obtain basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database.

[0073] Specifically, the spatiotemporal geodatabase is a highly organized collection of data that stores all data related to mining area ecological restoration and carbon sequestration assessment, and these data all possess two key attributes:

[0074] Spatial attribute: Each data point corresponds to a specific location on Earth.

[0075] Time attribute: Many data contain time series information, which records the state of a location at different points in time.

[0076] This embodiment uses an abandoned open-pit coal mine as an example. Relevant archival data, multi-source remote sensing data, ecological restoration measures, environmental factor data, and species distribution data of the abandoned open-pit coal mine are collected. Data preprocessing is then performed to construct a spatiotemporal geographic database. The spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database, wherein:

[0077] The core dynamic monitoring data of the multidimensional remote sensing data cube consists of vegetation indices, bare land indices, and surface temperatures calculated from long-term remote sensing images, used to track year-to-year changes in the mining area.

[0078] The environmental factor database contains static background data, including topography, soil, climate, land use, and other environmental factors that determine vegetation growth. It forms the basis for suitability assessment.

[0079] The species distribution sample database is knowledge training data, which collects known distribution points of various trees, grasses, and shrubs to inform the model of the preferred growing environments of plant species.

[0080] Step S202: Generate a closure pit spatiotemporal distribution database based on the multidimensional remote sensing data cube.

[0081] Specifically, deep learning algorithms are used to identify the closure time of open-pit mines based on remote sensing temporal features (composed of vegetation index, bare land index, surface temperature, etc.) in a multidimensional remote sensing data cube, generating a spatiotemporal distribution database of closure.

[0082] Step S203: Based on the environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, perform species habitat suitability probability modeling to generate an ecological restoration suitability spatial zoning database.

[0083] Specifically, by integrating environmental factor databases, species distribution sample databases, and closed pit spatiotemporal distribution databases, ecological restoration suitability assessments are conducted using the maximum entropy model, generating an ecological restoration suitability spatial zoning database. This involves constructing an ecological restoration measures and species type suitability assessment system and conducting suitability spatial zoning for multiple species and measures.

[0084] Step S204: Based on the spatial and temporal distribution database of closed pits and the spatial zoning database of ecological restoration suitability, generate a spatial and temporal distribution map of carbon sink potential, and assess the carbon sink potential of the mining area based on the spatial and temporal distribution map of carbon sink potential.

[0085] Specifically, based on suitability zoning and vegetation growth characteristics, carbon sink potential is estimated and spatial distribution maps are generated using ecological process models. That is, based on the closed pit spatiotemporal distribution database and the ecological restoration suitability spatial zoning database, ecological process models are used to simulate vegetation growth and carbon cycle processes to generate spatiotemporal distribution maps of carbon sink potential in order to assess the carbon sink potential of the mining area.

[0086] This embodiment provides a method for assessing the carbon sequestration potential of open-pit mine ecological restoration. By acquiring basic data of the mining area, a spatiotemporal geographic database is constructed based on this data, including a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database. This forms a systematic and integrated technical route for remote sensing identification of mine closure time, ecological restoration suitability assessment, and carbon sequestration potential calculation. A systematic and spatialized full-domain database is obtained, enabling full-link analysis of open-pit mines from "disturbance identification—restoration suitability—carbon sequestration quantification." This method can precisely depict the spatiotemporal evolution of mine restoration, dynamically quantify the carbon sequestration potential of different restoration measures and species types, and obtain a scientific carbon sequestration estimation method. It provides a scientific basis and technical support for the green transformation and carbon neutrality strategy of mining areas, solving the problem of the lack of a systematic and spatialized full-domain database and scientific carbon sequestration estimation in existing technologies.

[0087] This embodiment provides a method for assessing the carbon sink potential of open-pit mine ecological restoration, which can be used in the aforementioned electronic equipment. Figure 3 This is a flowchart of a method for assessing the carbon sequestration potential of open-pit mine ecological restoration according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0088] Step S301: Obtain basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database.

[0089] Specifically, this embodiment takes an abandoned open-pit coal mine as an example. The basic data of the abandoned open-pit coal mine includes: multi-source remote sensing data of land cover, environmental factor data, and species distribution data; the above step S301 includes:

[0090] Step S3011: Based on multi-source remote sensing data of land cover, calculate vegetation index, bare land index and surface temperature index, and perform time-series reconstruction and smoothing on vegetation index, bare land index and surface temperature index to generate a multi-dimensional remote sensing data cube that covers the mining area and is time-series continuous.

[0091] Specifically, the overall attributes of abandoned open-pit coal mines (such as total carbon sequestration and average vegetation coverage) are obtained by statistically summarizing the attributes of each pixel, meaning that all specific data and information of the mining area are recorded on each pixel.

[0092] like Figure 5 As shown, based on the Google Earth Engine platform, multi-source remote sensing data and its derivative products (such as mining area boundary products, land cover products, etc.) are acquired, and data preprocessing such as radiometric calibration, atmospheric correction, geometric correction, time series stitching, and cloud removal is performed.

[0093] A multidimensional remote sensing data cube for the mining area was constructed, encompassing multi-source remote sensing data and its derivative products (such as mining area boundary products and land cover products). Based on the multidimensional remote sensing data cube, NDVI (Normalized Difference Vegetation Index), bare land index, and land surface temperature index were calculated. The specific operations are as follows:

[0094] Calculating the NDVI vegetation index: The reflectance data for the near-infrared and red bands are extracted from a data cube using the difference in reflectance between the near-infrared and red bands. These two band data are then substituted into relevant formulas for pixel-by-pixel parallel calculation on a cloud platform. A new NDVI data layer is output, with a value range of [-1, 1].

[0095] Calculating the Bare Land Index (BSI): This method comprehensively utilizes multiple wavelengths sensitive to bare land to enhance the distinction between bare land and vegetation or water bodies. Shortwave infrared (SIR), red, near-infrared, and blue wavelengths are extracted from the data cube. These wavelengths are then substituted into relevant formulas for parallel calculation. A new bare land index data layer is output; higher values ​​indicate more pronounced bare land characteristics.

[0096] Calculating the Land Surface Temperature Index (LSI): The influence of the atmosphere (water vapor, aerosols, etc.) on surface radiation is eliminated from thermal infrared data to obtain the true surface thermal radiation intensity. The surface thermal radiation efficiency (emissivity) is determined based on land cover type (estimated from land cover products or NDVI). The thermal radiation intensity and emissivity are then substituted into Planck's law for calculation, converting the radiation values ​​into surface temperature.

[0097] A pixel-by-pixel temporal consistency check is performed on the annual land cover product cubes to reduce illogical category transitions. Specifically, if a pixel... pixel pq In the year y j The land cover type is "forest land", and it is in y j-2 ,y j-1 , y j+1 , y j+2 If the land cover type for all years is "bare land", then the pixel is determined. pixel pq exist y j The forest land category for the year may be misclassified; it will be automatically corrected to "forest land". For time-series vegetation index data, the Savitzky-Golay filtering and smoothing method is used to eliminate abnormal fluctuations in the time series by setting the filter window length and smoothing method. Combined with time-series linear interpolation and other methods, if feature indices are continuously missing for more than [a certain period]... t If the time series data is for a given month, the average value of the preceding and following months is used to fit and fill the data, ensuring the continuity and authenticity of the time series data.

[0098] Step S3012: Extract multidimensional environmental factors from environmental factor data and integrate the multidimensional environmental factors into a unified environmental factor database; the multidimensional environmental factors include topographic factors, soil factors, climate factors and land use types.

[0099] Specifically, by extracting multidimensional environmental factors such as topography, soil, climate, and land use from environmental factor data and integrating them into a unified spatial database, a standardized, multidimensional, and quantifiable set of environmental driving factors (i.e., environmental factor database) is constructed for subsequent ecological restoration suitability assessment, providing a comprehensive and consistent data foundation for scientifically assessing the habitat suitability of different species.

[0100] Step S3013: Extract known distribution points of species from the species distribution data, and perform data preprocessing such as unified coordinates and data cleaning on the known distribution points of species to generate a species distribution sample database for suitability modeling. The known distribution points of species include known distribution points of tree species, known distribution points of shrub species and known distribution points of grass species.

[0101] Specifically, known distribution points of a species refer to geographical locations where a particular plant species has been confirmed to have existed through field surveys, scientific observations, or authoritative literature records.

[0102] Known distribution points of major tree species, shrub species, and grass species were extracted from publicly published literature and scientific research sharing platforms (cloud processing platforms). Carbon conversion coefficients from the IPCC (Intergovernmental Panel on Climate Change) and measured parameters of case areas from published studies were collected. Coordinate projection was unified, duplicate values ​​were cleaned up, and outliers were removed to construct a habitat suitability training sample database and a carbon conversion coefficient dataset.

[0103] Step S302, the basic data of the mining area also includes: mining area archives; extracting the boundary coordinates of the mining area from the archives and importing the boundary coordinates into the geographic information system to generate a sample dataset of the mining area; collecting multiple vector boundary layer datasets of the mining area from a preset cloud processing platform and fusing the multiple vector boundary layer datasets of the mining area to form an initial mining area boundary; constructing a multi-dimensional feature space to characterize the disturbance features of the mining area based on multi-source remote sensing data and environmental factor data; using the sample dataset of the mining area and the multi-dimensional feature space as input data, using a deep learning algorithm to spatially correct the initial mining area boundary to form a corrected mining area boundary.

[0104] Specifically, web crawling technology was used to crawl mining area archives such as mining licenses, mining plans, company announcements, and government documents to extract key mining information such as mine boundary coordinates, closure years, and mining disturbance intensity. The boundary coordinates were imported into ArcGIS (Arc Geographic Information System) software to generate a sample dataset of the mining area in Shapefile format. Multiple open-pit coal mine vector boundary datasets were collected from research data sharing platforms such as Scientific Data journals, and the data from multiple boundary layers were merged and integrated to form the initial open-pit coal mine boundary. Topographic slope data was also collected. x 1. Slope aspect x 2. Soil texture x 3. Soil factors and climate / moisture conditions x 4 (Climate Factors), Land Cover Type x Geographic raster datasets of multiple environmental factors, including land use types (5). x 1, x 2,… x n ) and multi-source remote sensing surface reflectance ( x n , x n+1 ,… x n+m ), construct a multidimensional feature space ( x 1, x 2,… x n+m Using deep learning algorithms, the crawled mining area sample dataset and multidimensional feature space are used as input to spatially correct the initial open-pit coal mine boundary, forming the corrected open-pit coal mine boundary.

[0105] Step S303: Generate a closure pit spatiotemporal distribution database based on the multidimensional remote sensing data cube.

[0106] Specifically, step S303 includes:

[0107] Step S3031: Extract sample points and corresponding pixel time-series feature vectors from the mining area archives for known closure years to form a training sample set.

[0108] Specifically, samples of mining areas with known closure years are identified from mining area archives. For each pixel within a sample mining area, complete temporal feature data (i.e., sequences of NDVI, bare land index, surface temperature, etc., changing over time) from the start to the end year of the remote sensing image are extracted from its corresponding "multidimensional remote sensing data cube." The known closure years are used as labels and paired with the corresponding temporal feature vectors to form the sample set required for model training.

[0109] Step S3032: Within the corrected boundary of the mining area, the BFAST temporal breakpoint algorithm is used to perform pixel-by-pixel analysis on the multidimensional remote sensing data cube to identify abrupt change points in the temporal features of the pixels.

[0110] Specifically, the BFAST temporal breakpoint detection algorithm is used to identify key abrupt change points in the disturbance trajectory of the annual land cover product on a pixel-by-pixel basis, capturing possible nodes where mining disturbances transition to a stable state.

[0111] Furthermore, for the pixel-by-pixel temporal features of the corrected open-pit coal mine boundary, such as the vegetation index NDVI, bare land index BSI, and surface temperature index LSI, the BFAST (Breaks For Additive Season and Trend) algorithm was applied, setting parameters such as minimum segment length and significance level to identify key abrupt change points in the disturbance trajectory. By detecting the inflection point from "disturbance to stability," potential candidate years for mine closure were captured.

[0112] Step S3033: Train a pre-set deep learning model based on the mutation point and the training sample set to obtain the judgment rules for the steady-state transition of the closed pit. Specifically, based on the training samples extracted from the mining area archives, a deep learning algorithm is used to model the temporal characteristics of the bare land index and vegetation index, automatically learn the key inflection point patterns in the disturbance-recovery process, and output the judgment rules for the steady-state transition.

[0113] For example, the preset deep learning model in this embodiment adopts the LSTM deep learning model.

[0114] Sample points representing 70% of the known closure years were extracted from the mining area archives, and their corresponding pixels were mapped to the closure year t. closedThe training samples are constructed using time-series feature data (NDVI, BSI, LSI, etc.) for the m years preceding and following the training sample (2m+1 years in total). Each training sample input is a time-series feature matrix X. i =[V t ], where V t =(NDVI t BSI t LST t ), t∈[t closed-m ,t closed+m The supervision label for this sample is set to: t <t closed The year is marked as the "perturbation period" (label 0), t≥t closed The year is labeled "steady-state period" (label 1). The LSTM model is trained using all training samples, and the sigmoid activation function of the final layer outputs a value y between 0 and 1. hat This represents the probability that the model determines that the pixel is in a "steady-state period" in the corresponding year. The training objective of the model is to minimize the predicted probability y. hat The cross-entropy loss between the model and the true label. After training convergence, by analyzing the model's response pattern to time-series data, the generalizable "steady-state transition judgment rule" learned by the model is extracted. This rule can be expressed as a weighted time-series logical judgment.

[0115] For a pixel time series data X = [V1,V2,...,V] to be determined n The criterion function F(t) for determining whether a steady-state transition occurs in year t can be quantified as:

[0116] (1);

[0117] in, It is the sigmoid function, which maps linear combinations to probabilities; Here, f(·) represents the temporal weights learned by the model; f(·) is a nonlinear function implicitly learned by the LSTM unit, used to learn from a local temporal window of length L. Key patterns related to steady state are extracted (e.g., the inflection point characteristics of the vegetation index NDVI starting to rise continuously, the bare land index BSI starting to fall continuously, and the land surface temperature index LSI remaining relatively stable or gradually decreasing); b is the bias term.

[0118] The specific, operable judgment rule is: when F(t) > threshold and for If F(τ) > threshold for all values ​​of τ∈[t, t+k] (where k is a preset number of stable years, such as 3 years), then the pixel is considered to have undergone a pit closure steady-state transition in year t. The weights are... The specific parameters of the function f(·) (i.e., the update rules for the cell and hidden states of the LSTM) and the threshold are automatically learned from the sample data during model training. The decision function F(t) and its parameters learned from the training samples are used as fixed decision rules and applied to the complete time-series data X of all pixels within the study area. This allows for the calculation of the F(t) sequence for each pixel, and the output of the steady-state transition year of each pixel based on the rules. For a single mining area, the mode of the closure years of all pixels within it is calculated as the overall closure time of the mining area.

[0119] Step S3034: Apply the judgment rule to all pixels in the entire mining area to obtain the pixel closure year, and aggregate the mode of all pixel closure years to generate the closure time of the entire mining area, forming a closure spatiotemporal distribution database.

[0120] Specifically, the judgment rules are applied to the long-term time-series data of all pixels in the study area to generate a pixel-by-pixel layer of mine closure years. The overall mine closure time is determined by the mode statistical characteristics of the closure years of pixels within the mine area. A verification sample database extracted from the mine area's archival data is used to verify the accuracy of remote sensing extraction of closure time, ultimately generating a spatial distribution database of mine closure time, i.e., a spatial-temporal distribution database of mine closure.

[0121] More specifically, the remaining 30% of sample points, containing known closure years extracted from mining area archives, were selected as validation samples. The accuracy of the closure year identification results was evaluated pixel-by-pixel using the overall accuracy parameter. If the overall accuracy is higher than 90%, the identification results are considered reliable. If the overall accuracy is lower than 90%, the structure of the LSTM deep learning model is adjusted, and iterative optimization and retraining are performed to ultimately generate a database of the temporal and spatial distribution of open-pit coal mine closures. The database deliverables include: a pixel-by-pixel GeoTIFF layer (a raster image file containing georeferenced information) for each closure year and a Shapefile file for the overall closure year of the mining area, enabling the systematic storage and application of closure time information.

[0122] Step S304 involves performing probabilistic modeling of species habitat suitability based on the environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, generating a spatial zoning database of ecological restoration suitability. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0123] Step S305: Based on the spatiotemporal distribution database of mine closures and the spatial zoning database of ecological restoration suitability, a spatiotemporal distribution map of carbon sequestration potential is generated, and the carbon sequestration potential of the mining area is assessed based on this map. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0124] The open-pit mine ecological restoration carbon sink potential assessment method provided in this embodiment achieves high-precision and automated identification of mine closure time by integrating BFAST temporal breakpoint detection and deep learning model. It can effectively capture the temporal transition characteristics of "disturbance-recovery" at the pixel scale, and overcome the problems of poor timeliness, strong subjectivity and coarse spatial granularity caused by traditional reliance on manual interpretation or single archival data. Finally, it generates a spatiotemporally clear database of mine closure distribution, providing a reliable time benchmark for subsequent ecological restoration and carbon sink assessment.

[0125] This embodiment provides a method for assessing the carbon sink potential of open-pit mine ecological restoration, which can be used in the aforementioned electronic equipment. Figure 4 This is a flowchart of a method for assessing the carbon sequestration potential of open-pit mine ecological restoration according to an embodiment of the present invention. This embodiment uses an abandoned open-pit coal mine as an example. Figure 4 As shown, the process includes the following steps:

[0126] Step S401: Obtain basic data of the mining area and construct a spatiotemporal geographic database based on this data. The spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0127] Step S402: Generate a spatiotemporal distribution database of closure cavities based on the multidimensional remote sensing data cube. For details, please refer to [link to relevant documentation]. Figure 3 Step S303 of the illustrated embodiment will not be described again here.

[0128] Step S403: Based on the environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, perform species habitat suitability probability modeling to generate an ecological restoration suitability spatial zoning database.

[0129] Specifically, step S403 includes:

[0130] Step S4031: Spatial registration and association are performed between the known distribution points of species in the species distribution sample database and the multidimensional environmental factors in the environmental factor database of their location to obtain a standardized input dataset.

[0131] Specifically, the slope and aspect of the mining area are calculated based on DEM (Digital Elevation Model) data. Continuous factors such as slope, temperature, and precipitation are normalized to ensure their values ​​are distributed in the [0, 1] interval, thus guaranteeing the comparability of the variables. Discrete factors such as soil texture are converted into multidimensional binary input variables using one-hot encoding, ultimately forming the environmental factor database required for modeling the habitat suitability of the mining area.

[0132] Meanwhile, by accurately matching spatial locations, the known distribution points of species are associated with their multidimensional environmental factors, thereby transforming abstract species distribution information into a structured "species-environment" training dataset containing complete habitat variables, providing a direct and reliable input for subsequent suitability probability calculations based on the maximum entropy model.

[0133] Step S4032: Based on the standardized input dataset, the maximum entropy model is used to calculate the habitat suitability probability distribution of various restoration measures and species, and generate a suitability probability spatial partition map.

[0134] Specifically, using known distribution points of typical tree species, grass species, and shrub species and their habitat environmental factors as training samples, the maximum entropy model (MaxEnt) is used to calculate the probability distribution of habitat suitability for various restoration measures and species, generating a spatial zoning map of suitability for multiple species and multiple measures.

[0135] More specifically, for typical restoration measures (such as afforestation, grassland restoration, and shrub restoration) and the main specific tree species, shrub species, and grass species, their known distribution points are used as training samples, and the environmental factor database is used as input. The MaxEnt model (Maximum Entropy) is called to adjust parameters such as the number of iterations, regularization coefficient, and number of background samples to conduct suitability modeling.

[0136] For the set of environmental factors =( 1, 2,…, The MaxEnt model maximizes the distribution entropy:

[0137] (2);

[0138] in, To maximize distribution entropy, This indicates that when the combination of environmental factors is x Under certain conditions, the probability of the existence of the target vegetation type for restoration is known as the habitat suitability probability.

[0139] And meet environmental factor constraints:

[0140] (3);

[0141] Its optimal solution is an exponential family distribution:

[0142] (4);

[0143] in: ( ) is a function of environmental factors (such as temperature, precipitation, slope position, soil type, etc.); The parameters are obtained from model training; Z is the normalization factor. This represents the empirical mean of the j-th environmental factor at known species distribution points (training samples), i.e., the average value calculated from the training samples.

[0144] (5);

[0145] The model outputs the fitness probability for each pixel:

[0146] (6);

[0147] in, Represents a cell The probability of suitability for a given restoration measure or vegetation species type is indicated by a higher value, suggesting greater suitability for that measure or species. Ultimately, all pixels will be... The output is spatialized to generate a suitability probability spatial partitioning map.

[0148] Step S4033: Based on the suitability probability spatial zoning map, the optimal restoration measures or species types are determined for each pixel through overlay analysis and the principle of probabilistic optimality, and integrated and expressed as an ecological restoration suitability spatial zoning database.

[0149] Specifically, the suitability probability layers of various restoration measures and vegetation types are overlaid, and the restoration measure or vegetation type with the highest probability value at each pixel is selected as the preferred option. The final result is output as a habitat suitability probability distribution map in GeoTIFF format (Georeferenced Tagged Image File Format), and a pixel-by-pixel preferred restoration type layer is generated, which is integrated into an ecological restoration suitability spatial zoning database.

[0150] Step S404: Based on the spatial and temporal distribution database of closed pits and the spatial zoning database of ecological restoration suitability, generate a spatial and temporal distribution map of carbon sink potential, and assess the carbon sink potential of the mining area based on the spatial and temporal distribution map of carbon sink potential.

[0151] Specifically, step S404 includes:

[0152] Step S4041: Based on the ecological restoration suitability spatial zoning database, the optimal restoration measures and species types are mapped to vegetation functional types.

[0153] Specifically, by establishing correspondence rules between "restoration measures - species - vegetation functional types", specific restoration schemes in the spatial zoning results are incorporated. Transform into standardized vegetation functional type This forms a pixel-by-pixel functional spatial matrix. ,in This represents the number of pixels in the mining area.

[0154] Step S4042: Based on the spatiotemporal distribution database of closed pits, set the simulated starting year of the closed pit for each pixel and construct an initial vegetation cover matrix.

[0155] Specifically, based on the year t of the pit closure close, Construct a pixel-by-pixel initial vegetation cover matrix ( ):

[0156] (7);

[0157] in, The initial coverage is defined as ∈ [0.1, 0.3]. ∈[0,1] represents a pixel The probability of suitability for corresponding restoration measures or vegetation species types; The adjustment coefficient (0.05~0.2) is used to reflect the impact of vegetation restoration potential and environmental suitability; the output is a pixel-by-pixel initial coverage matrix. .

[0158] Step S4043: Based on the vegetation functional type, the initial vegetation coverage matrix and the year of pit closure, the model parameters of the preset Biome-BGC model are initialized in combination with multidimensional environmental factors. Starting from the year of pit closure, the vegetation growth and carbon cycle process is simulated day by day to obtain pixel-by-pixel biomass dynamic data.

[0159] Specifically, the input to the Biome-BGC model includes:

[0160] (8);

[0161] in, It is a functional type of vegetation; Initial vegetation cover matrix; Climate factors (average annual temperature, annual precipitation, sunshine hours, etc.); Soil factors (texture, soil organic carbon, etc.); This is a remote sensing-derived spectral index. The model uses the year the pit closed. Starting from the specified time, daily simulations of vegetation growth and carbon cycle processes are performed:

[0162] (9);

[0163] in, This is for the simulated duration; Indicates the first i Each pixel in the year t Total vegetation biomass;

[0164] Output pixel-by-pixel biomass time series:

[0165] (10);

[0166] The above pixel-by-pixel biomass time series is used as pixel-by-pixel biomass dynamic data.

[0167] Step S4044: The dynamic biomass data of each pixel is converted into the carbon sequestration of vegetation components based on the preset carbon conversion coefficient and the measured parameters of the region. The total annual carbon sequestration of each pixel is obtained by superimposing the data. The total annual carbon sequestration of different vegetation functional types is aggregated to generate a spatiotemporal distribution map of carbon sequestration potential for different restoration measures and species types.

[0168] Specifically, according to the following carbon conversion formula, the pixel-by-pixel biomass data is converted into carbon sequestration based on the IPCC carbon conversion coefficient and measured parameters of case areas in existing studies, and the carbon storage (i.e., carbon sequestration) of vegetation components including leaves, stems, and roots is calculated respectively:

[0169] (11);

[0170] in, ∈{leaf, stem, root}; The carbon conversion coefficient is measured by IPCC or in the region. Indicates the first i Each pixel in the year t vegetation k The amount of carbon fixed by the component; Indicates the first i Each pixel in the year t vegetation k Biomass of the components And then the total annual carbon sequestration is generated by overlaying the data:

[0171] (12);

[0172] By overlaying carbon sequestration data of different vegetation functional types using the following formula, a spatial distribution map of annual carbon sequestration in the mining area is obtained. The final output includes a pixel-by-pixel GeoTIFF layer, which is a spatiotemporal distribution map of the carbon sequestration potential of different remediation measures and species types:

[0173] (13);

[0174] in, To measure the total carbon sequestration for each year, Spatiotemporal distribution maps of carbon sequestration potential for different remediation measures and species types. Indicates the first i The vegetation functional type of each pixel.

[0175] Step S405: Spatial statistics are performed on the spatiotemporal distribution map of carbon sink potential to obtain statistical results of total carbon amount and average density in the overall mining area and different restoration zones; based on the statistical results and the spatiotemporal distribution map of carbon sink potential, carbon sink hotspot areas and spatial distribution patterns are identified, and correlation analysis is performed with restoration measures and environmental driving factors to generate decision-making basis for optimizing ecological restoration strategies.

[0176] Specifically, by conducting statistical analysis and spatial pattern identification of carbon sequestration potential maps, abstract carbon sequestration data is transformed into intuitive total amount conclusions and spatial hotspots, thereby revealing the driving mechanisms behind them and ultimately providing precise decision support for optimizing remediation layout and improving carbon sequestration efficiency.

[0177] The carbon sequestration potential assessment method for open-pit mine ecological restoration provided in this embodiment combines pixel-level vegetation functional types and environmental factors to generate a carbon sequestration distribution map with clear spatiotemporal dimensions. This intuitively reveals the spatial heterogeneity of carbon sequestration potential and its evolution over time. The resulting spatiotemporal distribution map of carbon sequestration potential can clearly quantify the expected carbon sequestration benefits of different restoration measures and species types, providing a quantitative and visual scientific basis for scheme comparison, priority delineation, and carbon neutrality benefit prediction of mine ecological restoration projects.

[0178] As one or more specific application embodiments of the present invention, combined with Figure 5 The present invention provides a further detailed description of the method for assessing the carbon sequestration potential for ecological restoration in open-pit mines, such as... Figure 5 As shown, the specific process is as follows:

[0179] Step S1: Collect relevant archives, multi-source remote sensing data, ecological restoration measures and species distribution data of the open-pit mine area, and perform data preprocessing to construct a spatiotemporal geographic database.

[0180] Step S1 specifically includes:

[0181] S11. Utilize web crawler technology to automatically collect mining archive information related to open-pit coal mines (hereinafter referred to as open-pit coal mine archive data), and construct a training and verification sample database including closure time, mining area inflection point coordinates, etc.; at the same time, collect multiple authoritative open-pit coal mine vector boundary datasets to conduct open-pit coal mine boundary consistency verification.

[0182] S12. Based on the Google Earth Engine platform, acquire multi-source remote sensing data and its derivative products and perform data preprocessing;

[0183] S13. Based on remote sensing data, calculate and extract characteristic indices including vegetation index, bare land index, and surface temperature index, and construct a multi-dimensional remote sensing data cube covering open-pit coal mines.

[0184] S14. Perform time series consistency checks and time series interpolation on the constructed land cover product remote sensing data; for time series vegetation index and other data, use Savitzky-Golay filtering smoothing method to reduce abnormal fluctuations in time series, and combine time series linear interpolation and other methods to repair missing data to ensure the continuity and authenticity of time series data.

[0185] S15. Extract known distribution points of major tree species, shrub species and grass species from publicly published literature and scientific research sharing platforms, collect IPCC carbon conversion coefficients and measured parameters of case areas in existing published studies, unify coordinate projection, clean up duplicate values ​​and remove outliers, and construct a habitat suitability training sample database and a carbon conversion coefficient dataset.

[0186] Step S2: Using deep learning algorithms, identify the closure time of open-pit mines based on remote sensing time series features, and generate a database of the spatiotemporal distribution of closure.

[0187] Based on the data from step S1, step S2, remote sensing identification of the pit closure time, is performed, including:

[0188] S21. Using the BFAST time-series breakpoint detection method, key abrupt change points in the disturbance trajectory of the annual land cover product are identified pixel by pixel to capture possible nodes that transition from mining disturbance to a stable state.

[0189] S22. Based on training samples extracted from open-pit coal mine archives, a deep learning algorithm is used to model the temporal characteristics of bare land index and vegetation index, automatically learn the key inflection point patterns in the disturbance-recovery process, and output the judgment rules for steady-state transition.

[0190] S23. Apply the judgment rules to the long-term data of all pixels in the study area to generate a pixel-by-pixel closure year layer, and determine the overall closure time of the mining area based on the mode statistical characteristics of the closure years of pixels in the mining area.

[0191] S24. Using the verification sample database extracted from open-pit coal mine archives, the accuracy of remote sensing extraction of mine closure time is verified, and finally a spatial distribution database of mine closure time is generated.

[0192] Step S3: Construct an ecological restoration measures and species suitability evaluation system, and carry out spatial zoning of multiple species and measures based on suitability.

[0193] Based on the results of the pit closure year in step S2, step S3, the suitability assessment for ecological restoration, is conducted, including:

[0194] S31. Integrate multi-source environmental factors such as topographic slope, aspect, soil texture, climate and moisture conditions, land use type and mining area disturbance intensity to construct a database of environmental input variables required for suitability modeling;

[0195] S32. Using the known distribution points of typical tree species, grass species and shrub species and their habitat environmental factors as training samples, the maximum entropy model (MaxEnt) is used to calculate the habitat suitability probability distribution of various restoration measures and species, and generate a multi-species, multi-measure suitability spatial zoning map.

[0196] S33. Integrate and express the results of various restoration measures and the spatial distribution of species suitability to form an integrated spatial database for ecological restoration of mining areas.

[0197] Step S4: Based on suitability zoning and vegetation growth characteristics, use ecological process models to estimate carbon sink potential and generate spatial distribution maps.

[0198] Based on the suitability results of step S3, step S4, carbon sequestration potential estimation, is performed, including:

[0199] S41. Based on the pit closure time in step S2 and the suitability zoning data in step S3, the restoration measures and species types corresponding to each pixel are mapped to the plant functional type (PFT). Combined with the vegetation index, vegetation cover, and environmental factors such as climate and soil retrieved from remote sensing, the input dataset required for the Biome-BGC model is constructed.

[0200] S42. Initialize the Biom-BGC model parameters and set the simulation start year to the pit closure time; use the Biom-BGC model to simulate the vegetation growth process and carbon cycle pixel by pixel.

[0201] S43. Convert the biomass data obtained from step S42 into carbon sequestration based on the IPCC carbon conversion coefficient and measured parameters of case areas in existing studies. Overlay the suitability zoning data from step S3 to generate a spatiotemporal distribution map of carbon sequestration potential for different remediation measures and species types.

[0202] The carbon sequestration potential assessment method for open-pit mine ecological restoration provided in this embodiment constructs a systematic and integrated technical route encompassing remote sensing identification of mine closure time, ecological restoration suitability assessment, and carbon sequestration potential calculation. This enables full-link analysis of open-pit mines from "disturbance identification - restoration suitability - carbon sequestration quantification." This method can precisely characterize the spatiotemporal evolution of mine restoration, dynamically quantify the carbon sequestration potential of different restoration measures and species types, and provide scientific basis and technical support for the green transformation and carbon neutrality strategy of mining areas.

[0203] This embodiment also provides a device for assessing the carbon sink potential of open-pit mine ecological restoration. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0204] This embodiment provides a device for assessing the carbon sequestration potential of open-pit mine ecological restoration, such as... Figure 6 As shown, it includes:

[0205] The spatiotemporal geographic database construction module 601 is used to acquire basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database.

[0206] The closure time identification module 602 is used to generate a closure spatiotemporal distribution database based on a multidimensional remote sensing data cube.

[0207] The Ecological Restoration Suitability Assessment Module 603 is used to perform probabilistic modeling of species habitat suitability based on environmental factor databases, species distribution sample databases, and closed pit spatiotemporal distribution databases, and to generate a spatial zoning database of ecological restoration suitability.

[0208] The open-pit mine ecological restoration carbon sink potential assessment module 604 is used to generate a carbon sink potential spatiotemporal distribution map based on the closed pit spatiotemporal distribution database and the ecological restoration suitability spatial zoning database, and to assess the carbon sink potential of the mining area based on the carbon sink potential spatiotemporal distribution map.

[0209] In some optional implementations, the basic data for the mining area includes: multi-source remote sensing data of land cover, environmental factor data, and species distribution data; the spatiotemporal geographic database construction module 601 includes:

[0210] The multidimensional remote sensing data cube generation unit is used to calculate vegetation index, bare land index and land surface temperature index based on multi-source remote sensing data of land cover, and to perform temporal reconstruction and smoothing processing on vegetation index, bare land index and land surface temperature index to generate a temporally continuous multidimensional remote sensing data cube covering the mining area.

[0211] The environmental factor database generation unit is used to extract multidimensional environmental factors from environmental factor data and integrate the multidimensional environmental factors into a unified environmental factor database; the multidimensional environmental factors include topographic factors, soil factors, climate factors and land use types.

[0212] The species distribution sample database generation unit is used to extract known distribution points of species from the species distribution data, and to perform data preprocessing such as unifying coordinates and data cleaning on the known distribution points of species to generate a species distribution sample database for suitability modeling. The known distribution points of species include known distribution points of tree species, known distribution points of shrub species and known distribution points of grass species.

[0213] In some optional implementations, the basic data for the mining area also includes: mining area archives; the open-pit mine ecological restoration carbon sequestration potential assessment device also includes:

[0214] The mining area boundary determination module is used to extract mining area boundary coordinates from mining area archives and import them into a geographic information system to generate a mining area sample dataset. It also collects multiple mining area vector boundary layer datasets from a pre-set cloud processing platform and merges these datasets to form an initial mining area boundary. Based on multi-source remote sensing data and environmental factor data, a multi-dimensional feature space is constructed to characterize mining area disturbance features. Using the mining area sample dataset and the multi-dimensional feature space as input data, a deep learning algorithm is used to spatially correct the initial mining area boundary, forming a corrected mining area boundary.

[0215] In some alternative implementations, the pit closing time identification module 602 includes:

[0216] The training sample set extraction unit is used to extract sample points and corresponding pixel time-series feature vectors from the mining area archives for known closure years, in order to form a training sample set.

[0217] The temporal disturbance trajectory breakpoint detection unit is used to perform pixel-by-pixel analysis on the multidimensional remote sensing data cube within the corrected mining area boundary using the BFAST temporal breakpoint algorithm, and to identify abrupt change points in the temporal features of pixels.

[0218] The determination rule unit is used to train a preset deep learning model based on the mutation point and the training sample set to obtain the determination rule for the steady-state transition of the closure pit.

[0219] The closure year determination unit is used to apply the determination rules to all pixels in the entire mining area to obtain the closure year of each pixel. The mode of all closure years of each pixel is aggregated to generate the closure time of the entire mining area, forming a closure spatiotemporal distribution database.

[0220] In some optional implementations, the ecological restoration suitability assessment module 603 includes:

[0221] The spatial registration and association unit is used to spatially register and associate known distribution points of species in the species distribution sample database with multidimensional environmental factors in the environmental factor database of their location to obtain a standardized input dataset.

[0222] The suitability probability distribution modeling unit is used to calculate the habitat suitability probability distribution of various restoration measures and species based on a standardized input dataset using a maximum entropy model, and generate a suitability probability spatial partition map.

[0223] The ecological restoration suitability assessment unit is used to determine the optimal restoration measures or species types in each cell based on the suitability probability spatial zoning map, through overlay analysis and the principle of probabilistic optimality, and to integrate and express them as an ecological restoration suitability spatial zoning database.

[0224] In some optional implementations, the open-pit mine ecological restoration carbon sink potential assessment module 604 includes:

[0225] The vegetation functional type generation unit is used to map the optimal restoration measures and species types to vegetation functional types based on the ecological restoration suitability spatial zoning database.

[0226] The vegetation cover matrix generation unit is used to set the simulated closure start year for each cell based on the closure spatiotemporal distribution database and to construct an initial vegetation cover matrix.

[0227] The biomass dynamics data simulation unit is used to simulate the vegetation growth and carbon cycle process on a daily basis, starting from the year of closure, based on the vegetation functional type, the initial vegetation cover matrix and the year of pit closure, combined with multidimensional environmental factors to initialize the model parameters of the preset Biome-BGC model, and obtain pixel-by-pixel biomass dynamics data.

[0228] The ecological restoration carbon sequestration calculation unit is used to convert the dynamic data of biomass per pixel into the carbon sequestration of vegetation components based on the preset carbon conversion coefficient and regional measured parameters. The total annual carbon sink of each pixel is obtained by superimposing the data, and the total annual carbon sink of different vegetation functional types is aggregated to generate a spatiotemporal distribution map of carbon sink potential for different restoration measures and species types.

[0229] In some optional implementations, the open-pit mine ecological restoration carbon sink potential assessment module 604 also includes:

[0230] The open-pit mine ecological restoration carbon sink potential assessment unit is used to perform spatial statistics on the spatiotemporal distribution map of carbon sink potential, and obtain statistical results of the total amount and average density of carbon in the entire mining area and different restoration zones. Based on the statistical results and the spatiotemporal distribution map of carbon sink potential, carbon sink hotspots and spatial distribution patterns are identified, and correlation analysis is performed with restoration measures and environmental driving factors to generate decision-making basis for optimizing ecological restoration strategies.

[0231] The open-pit mine ecological restoration carbon sink potential assessment device provided in this embodiment of the invention can execute the open-pit mine ecological restoration carbon sink potential assessment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0232] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0233] The following is a detailed reference. Figure 7 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0234] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0235] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the open-pit mine ecological restoration carbon sink potential assessment method of the present invention.

[0236] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0237] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the open-pit mine ecological restoration carbon sink potential assessment method shown in the above embodiments is implemented.

[0238] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0239] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for assessing the carbon sequestration potential for ecological restoration in open-pit mines, characterized in that, The method includes: Acquire basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database; A database of the spatiotemporal distribution of closed pits is generated based on the multidimensional remote sensing data cube; A database of the spatiotemporal distribution of closure pits is generated based on the multidimensional remote sensing data cube, including: Sample points and corresponding pixel time-series feature vectors of known closure years are extracted from mining area archives to form a training sample set. Within the corrected boundary of the mining area, the BFAST temporal breakpoint algorithm is used to perform pixel-by-pixel analysis on the multidimensional remote sensing data cube to identify abrupt change points in the temporal features of the pixels. Based on the mutation point and the training sample set, a preset deep learning model is trained to obtain the judgment rule for the steady-state transition of the closure pit; The determination rule is applied to all pixels in the entire mining area to obtain the year of closure of each pixel. The mode of the closure years of all pixels is aggregated to generate the closure time of the entire mining area, forming the closure spatiotemporal distribution database. Based on the aforementioned environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, a species habitat suitability probability model is performed to generate an ecological restoration suitability spatial zoning database. Based on the aforementioned closed pit spatiotemporal distribution database and ecological restoration suitability spatial zoning database, a carbon sink potential spatiotemporal distribution map is generated, and the carbon sink potential of the mining area is assessed based on the aforementioned carbon sink potential spatiotemporal distribution map. Based on the aforementioned database of the spatiotemporal distribution of closed pits and the spatial zoning database of ecological restoration suitability, a spatiotemporal distribution map of carbon sequestration potential is generated, including: Based on the aforementioned ecological restoration suitability spatial zoning database, the optimal restoration measures and species types are mapped to vegetation functional types. Based on the aforementioned spatiotemporal distribution database of closed pits, a simulated starting year for the closed pits is set for each pixel, and an initial vegetation coverage matrix is ​​constructed. Based on the aforementioned vegetation functional type, initial vegetation coverage matrix, and pit closure start year, the model parameters of the preset Biome-BGC model are initialized by combining multidimensional environmental factors. Starting from the pit closure start year, the vegetation growth and carbon cycle process is simulated day by day to obtain pixel-by-pixel biomass dynamic data. The pixel-by-pixel biomass dynamic data is converted into the carbon sequestration of vegetation components based on a preset carbon conversion coefficient and regional measured parameters. The total annual carbon sequestration of each pixel is then obtained by superimposing the data. The total annual carbon sequestration of different vegetation functional types is then aggregated to generate a spatiotemporal distribution map of carbon sequestration potential for different restoration measures and species types.

2. The method for assessing the carbon sequestration potential for ecological restoration in open-pit mines according to claim 1, characterized in that, The basic data for the mining area includes: multi-source remote sensing data of land cover, environmental factor data, and species distribution data; Based on the multi-source remote sensing data of land cover, vegetation index, bare land index and surface temperature index are calculated, and the vegetation index, bare land index and surface temperature index are reconstructed and smoothed in time series to generate a multi-dimensional remote sensing data cube that covers the mining area and is in time series continuous. Multidimensional environmental factors are extracted from the environmental factor data and integrated into a unified environmental factor database; the multidimensional environmental factors include topographic factors, soil factors, climate factors, and land use types; Known distribution points of species are extracted from the species distribution data, and data preprocessing is performed on the known distribution points of species to unify coordinates and clean the data, generating a species distribution sample database for suitability modeling. The known distribution points of species include known distribution points of tree species, known distribution points of shrub species, and known distribution points of grass species.

3. The method for assessing the carbon sequestration potential for ecological restoration in open-pit mines according to claim 2, characterized in that, The basic data for the mining area also includes: mining area archives; Before generating the closure spatiotemporal distribution database based on the multidimensional remote sensing data cube, the method further includes: The boundary coordinates of the mining area are extracted from the mining area archives and imported into the geographic information system to generate a sample dataset of the mining area. Multiple mining area vector boundary layer datasets are collected from a preset cloud processing platform and then fused to form an initial mining area boundary. Based on the multi-source remote sensing data and environmental factor data, a multi-dimensional feature space is constructed to characterize the disturbance features of the mining area. Using a sample dataset of the mining area and a multidimensional feature space as input data, a deep learning algorithm is used to spatially correct the initial mining area boundary, forming a corrected mining area boundary.

4. The method for assessing the carbon sequestration potential for ecological restoration in open-pit mines according to claim 1, characterized in that, Based on the aforementioned environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, a species habitat suitability probability model is performed to generate an ecological restoration suitability spatial zoning database, including: Spatial registration and association are performed between the known distribution points of species in the species distribution sample database and the multidimensional environmental factors in the environmental factor database of their location to obtain a standardized input dataset. Based on the standardized input dataset, the maximum entropy model was used to calculate the probability distribution of habitat suitability for various restoration measures and species, and a spatial partition map of suitability probability was generated. Based on the aforementioned suitability probability spatial zoning map, the optimal restoration measures or species types are determined for each pixel through overlay analysis and the principle of probabilistic optimality, and integrated and expressed as an ecological restoration suitability spatial zoning database.

5. The method for assessing the carbon sequestration potential for ecological restoration in open-pit mines according to claim 1, characterized in that, Assessing the carbon sequestration potential of the mining area based on the aforementioned spatiotemporal distribution map includes: Spatial statistics were performed on the spatiotemporal distribution map of the carbon sink potential to obtain statistical results on the total amount and average density of carbon in the entire mining area and in different remediation zones. Based on the statistical results and the spatiotemporal distribution map of carbon sink potential, carbon sink hotspots and spatial distribution patterns are identified, and correlation analysis is conducted with remediation measures and environmental driving factors to generate decision-making basis for optimizing ecological restoration strategies.

6. A device for assessing the carbon sequestration potential of open-pit mine ecological restoration, characterized in that, The device includes: A spatiotemporal geographic database construction module is used to acquire basic data of the mining area and construct a spatiotemporal geographic database based on the basic data of the mining area; the spatiotemporal geographic database includes a multidimensional remote sensing data cube, an environmental factor database, and a species distribution sample database. A crater closure time identification module is used to generate a crater closure spatiotemporal distribution database based on the multidimensional remote sensing data cube; generating the crater closure spatiotemporal distribution database based on the multidimensional remote sensing data cube includes: Sample points and corresponding pixel time-series feature vectors of known closure years are extracted from mining area archives to form a training sample set. Within the corrected boundary of the mining area, the BFAST temporal breakpoint algorithm is used to perform pixel-by-pixel analysis on the multidimensional remote sensing data cube to identify abrupt change points in the temporal features of the pixels. Based on the mutation point and the training sample set, a preset deep learning model is trained to obtain the judgment rule for the steady-state transition of the closure pit; The determination rule is applied to all pixels in the entire mining area to obtain the year of closure of each pixel. The mode of the closure years of all pixels is aggregated to generate the closure time of the entire mining area, forming the closure spatiotemporal distribution database. The ecological restoration suitability assessment module is used to perform species habitat suitability probability modeling based on the environmental factor database, species distribution sample database, and closed pit spatiotemporal distribution database, and generate an ecological restoration suitability spatial zoning database. The open-pit mine ecological restoration carbon sink potential assessment module is used to generate a carbon sink potential spatiotemporal distribution map based on the closed pit spatiotemporal distribution database and the ecological restoration suitability spatial zoning database, and to assess the carbon sink potential of the mine area based on the carbon sink potential spatiotemporal distribution map. Based on the aforementioned database of the spatiotemporal distribution of closed pits and the spatial zoning database of ecological restoration suitability, a spatiotemporal distribution map of carbon sequestration potential is generated, including: Based on the aforementioned ecological restoration suitability spatial zoning database, the optimal restoration measures and species types are mapped to vegetation functional types. Based on the aforementioned spatiotemporal distribution database of closed pits, a simulated starting year for the closed pits is set for each pixel, and an initial vegetation coverage matrix is ​​constructed. Based on the aforementioned vegetation functional type, initial vegetation coverage matrix, and pit closure start year, the model parameters of the preset Biome-BGC model are initialized by combining multidimensional environmental factors. Starting from the pit closure start year, the vegetation growth and carbon cycle process is simulated day by day to obtain pixel-by-pixel biomass dynamic data. The pixel-by-pixel biomass dynamic data is converted into the carbon sequestration of vegetation components based on a preset carbon conversion coefficient and regional measured parameters. The total annual carbon sequestration of each pixel is then obtained by superimposing the data. The total annual carbon sequestration of different vegetation functional types is aggregated to generate a spatiotemporal distribution map of carbon sequestration potential for different restoration measures and species types.

7. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the open-pit mine ecological restoration carbon sink potential assessment method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the method for assessing the carbon sink potential for ecological restoration in open-pit mines, as described in any one of claims 1 to 5.

Images