Method and apparatus for mapping biodiversity, electronic device, and storage medium

Abstract

The application relates to a biodiversity mapping method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring remote sensing observation data, ground observation data and species information data, constructing an ecological data cube, extracting statistical features, frequency features and phenological features according to the ecological data cube, constructing a species diversity spatial map, a phylogenetic diversity map and a global genetic diversity map, fusing the maps to obtain a fusion result, identifying high diversity areas and low protection areas according to the fusion result, and evaluating the high diversity areas and the low protection areas to obtain an evaluation result. Thus, the application can fuse multi-source satellite remote sensing and ground data, improve the comprehensiveness and scientificity of the diversity evaluation, and solve the problems that related technologies depend on sample quantity and data precision, it is difficult to reveal the phylogenetic and genetic patterns, and it is difficult to meet the needs of global scale decision and management.

Description

Technical Field

[0001] This application relates to the field of biodiversity monitoring technology, and in particular to a biodiversity mapping method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continued loss of global biodiversity, the scientific and policy communities have an increasing need for species conservation and sustainable ecosystem management. Spatial biodiversity information is considered a key basis for setting conservation priorities and assessing the impact of human activities.

[0003] Species diversity mapping methods in related technologies are mostly based on species occurrence point data, using niche models (such as MaxEnt) to predict their distribution range, and then overlaying them with environmental variables to identify potential habitats.

[0004] However, such methods typically rely on the number of site samples and the accuracy of environmental data, have limited spatial resolution, and are difficult to reveal in depth the patterns of biodiversity at the phylogenetic and genetic levels, thus failing to meet the needs of global-scale decision-making and management. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for mapping biodiversity to address the problem that related technologies rely on sample size and data accuracy, making it difficult to reveal phylogenetic and genetic patterns and meet the needs of global-scale decision-making and management. This application can integrate multi-source satellite remote sensing and ground-based data to improve the comprehensiveness and scientific rigor of biodiversity assessment.

[0006] The first aspect of this application provides a method for mapping biodiversity, comprising the following steps:

[0007] Acquire remote sensing observation data, ground-based observation data, and species information data.

[0008] An ecological data cube is constructed based on the remote sensing observation data, ground-based observation data, and species information data, and statistical features, frequency features, and phenological features are extracted from the ecological data cube.

[0009] Based on the statistical characteristics, frequency characteristics, and phenological characteristics, a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map are constructed. The spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are then fused to obtain a fusion result. Based on the fusion result, high-diversity regions and low-protection regions are identified, and the high-diversity regions and low-protection regions are evaluated to obtain an evaluation result.

[0010] Optionally, in some embodiments, constructing a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on the statistical characteristics, the frequency characteristics, and the phenological characteristics includes:

[0011] Based on the statistical characteristics, frequency characteristics, and phenological characteristics, a species habitat suitability model is constructed using a preset maximum entropy model and a preset random forest model, and the species diversity spatial map is obtained based on the species habitat suitability model.

[0012] Based on the statistical characteristics, frequency characteristics, and phenological characteristics, a phylogenetic diversity index is calculated, and a phylogenetic diversity map is obtained based on the phylogenetic diversity index.

[0013] Based on the statistical characteristics, frequency characteristics, and phenological characteristics, the expected heterozygosity and / or nucleotide diversity are calculated, and the global genetic diversity map is obtained based on the expected heterozygosity and / or nucleotide diversity.

[0014] Optionally, in some embodiments, the fusion of the species diversity spatial map, the phylogenetic diversity map, and the global genetic diversity map to obtain the fusion result includes:

[0015] Based on a preset fusion formula, the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are fused to obtain a fusion result, wherein the preset fusion formula is:

[0016] D(x,y)=w1·P AOH (x,y)+w2·PD(x,y)+w3·He(x,y)

[0017] Where D(x,y) is the value of the comprehensive diversity index at position (x,y), and P AOH (x,y) represents the species richness at location (x,y), PD(x,y) represents the phylogenetic diversity at location (x,y), He(x,y) represents the genetic diversity at location (x,y), w1 represents the fusion weight of the spatial map of species diversity, w2 represents the fusion weight of the phylogenetic diversity map, and w3 represents the fusion weight of the global genetic diversity map.

[0018] Optionally, in some embodiments, the remote sensing data includes at least one of: high-resolution optical image data, synthetic aperture radar data, lidar data, nighttime light data, terrain data, climate reanalysis data, and future simulation product data;

[0019] The ground-based observation data includes at least one of the following: meteorological station records, flux tower data, ecological station plot monitoring data, near-ground phenological camera time series data, and hyperspectral observation data.

[0020] Optionally, in some embodiments, the statistical characteristics include at least one of the following: annual mean, annual standard deviation, annual coefficient of variation, interannual variation, seasonal variation, and greenness growth period length;

[0021] The frequency characteristics include at least one of high temperature frequency and low temperature frequency.

[0022] A second aspect of this application provides a biodiversity mapping apparatus, comprising:

[0023] The acquisition module is used to acquire remote sensing observation data, ground-based observation data, and species information data.

[0024] The construction module is used to construct an ecological data cube based on the remote sensing observation data, ground-based observation data, and species information data, and to extract statistical features, frequency features, and phenological features based on the ecological data cube;

[0025] The mapping module is used to construct a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on the statistical features, the frequency features, and the phenological features. It then merges the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map to obtain a fusion result. Based on the fusion result, it identifies high-diversity regions and low-protection regions and evaluates the high-diversity regions and low-protection regions to obtain an evaluation result.

[0026] Optionally, in some embodiments, the mapping module includes:

[0027] The first construction unit is used to construct a species habitat suitability model based on the statistical characteristics, frequency characteristics, and phenological characteristics, using a preset maximum entropy model and a preset random forest model, and to obtain the species diversity spatial map based on the species habitat suitability model.

[0028] The second construction unit is used to calculate the phylogenetic diversity index based on the statistical characteristics, the frequency characteristics, and the phenological characteristics, and to obtain the phylogenetic diversity map based on the phylogenetic diversity index.

[0029] The third building unit is used to calculate the expected heterozygosity and / or nucleotide diversity based on the statistical characteristics, the frequency characteristics, and the phenological characteristics, and to obtain the global genetic diversity map based on the expected heterozygosity and / or the nucleotide diversity.

[0030] Optionally, in some embodiments, the fusion of the species diversity spatial map, the phylogenetic diversity map, and the global genetic diversity map to obtain the fusion result includes:

[0031] Based on a preset fusion formula, the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are fused to obtain a fusion result, wherein the preset fusion formula is:

[0032] D(x,y)=w1·P AOH (x,y)+w2·PD(x,y)+w3·He(x,y)

[0033] Where D(x,y) is the value of the comprehensive diversity index at position (x,y), and P AOH (x,y) represents the species richness at location (x,y), PD(x,y) represents the phylogenetic diversity at location (x,y), He(x,y) represents the genetic diversity at location (x,y), w1 represents the fusion weight of the spatial map of species diversity, w2 represents the fusion weight of the phylogenetic diversity map, and w3 represents the fusion weight of the global genetic diversity map.

[0034] Optionally, in some embodiments, the remote sensing data includes at least one of: high-resolution optical image data, synthetic aperture radar data, lidar data, nighttime light data, terrain data, climate reanalysis data, and future simulation product data;

[0035] The ground-based observation data includes at least one of the following: meteorological station records, flux tower data, ecological station plot monitoring data, near-ground phenological camera time series data, and hyperspectral observation data.

[0036] Optionally, in some embodiments, the statistical characteristics include at least one of the following: annual mean, annual standard deviation, annual coefficient of variation, interannual variation, seasonal variation, and greenness growth period length;

[0037] The frequency characteristics include at least one of high temperature frequency and low temperature frequency.

[0038] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the biodiversity mapping method as described in the above embodiments.

[0039] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the biodiversity mapping method as described in the above embodiments.

[0040] Therefore, this application has at least the following beneficial effects:

[0041] (1) This application integrates multi-source satellite remote sensing data and ground-based observation data, covering multiple dimensions such as ecological structure, environmental status and biological distribution, and constructs a data cube with unified standards.

[0042] (2) This application introduces multiple types of ecological factors and time-series statistical features to improve the ability of species and diversity modeling to respond to dynamic environmental changes.

[0043] (3) This application integrates phylogenetic information and genetic sequences to achieve multi-level spatial mapping of species, phylogeny and genetic diversity, breaking through the limitation of traditional biodiversity mapping being limited to the species level.

[0044] (4) This application can identify key ecological areas and biodiversity hotspots, serving the delineation of conservation priorities and policy decisions on a global scale, and has broad scientific value and application potential.

[0045] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0046] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0047] Figure 1 This is a flowchart of a biodiversity mapping method provided according to an embodiment of this application;

[0048] Figure 2 This is a schematic diagram illustrating the principle of a biodiversity mapping method according to an embodiment of this application;

[0049] Figure 3 This is a schematic diagram of a biodiversity mapping apparatus provided according to an embodiment of this application;

[0050] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0051] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0052] The following description, with reference to the accompanying drawings, outlines a biodiversity mapping method, apparatus, electronic device, and storage medium according to embodiments of this application. Addressing the issues mentioned in the background art, where related technologies rely on sample size and data accuracy, making it difficult to reveal phylogenetic and genetic patterns and meet the needs of global-scale decision-making and management, this application provides a biodiversity mapping method. This method integrates remote sensing observation data, ground-based ecological data, and bioinformatics data to establish a multi-source modeling and spatial expression system for species diversity, phylogenetic diversity, and genetic diversity. This method not only depicts current diversity patterns but also links with climate scenario data to predict future trends, providing a scientific basis for global biodiversity conservation.

[0053] Before introducing the biodiversity mapping method of the embodiments of this application, let's first introduce the relevant technical principles.

[0054] Phylogenetic diversity quantifies the phylogenetic relationships between different species through evolutionary tree structures, identifying key species and regions with unique evolutionary histories. Genetic diversity, on the other hand, measures the adaptive potential and ecological resilience of populations through population genetic structure, forming the basis for biodiversity stability. Although relevant biological databases (such as NCBI GenBank and Open Tree of Life) have accumulated a wealth of phylogenetic and gene sequence information, effectively integrating this information with spatial environmental data and achieving large-scale spatial explicit expression still faces bottlenecks such as inconsistent methods, low efficiency, and difficulty in integration.

[0055] On the other hand, the development of remote sensing technology has provided unprecedented data sources for ecosystem monitoring. Currently, multi-source satellite and ground-based observation systems, including multispectral, hyperspectral, radar, and lidar, can acquire large-scale, multi-temporal, and high-resolution ecological and environmental data. With the support of artificial intelligence and high-performance computing, the deep integration of remote sensing and biological data has become possible, potentially breaking through the limitations of traditional ecological mapping methods and enabling the extraction of multi-dimensional, multi-scale, and multi-category biodiversity information from habitat to genetic levels, providing data support for the assessment of global biodiversity conservation strategies and objectives.

[0056] Therefore, there is an urgent need to develop a multi-level diversity mapping method for global terrestrial vertebrates and higher plants that can systematically integrate remote sensing observation, ecotaxonomy, bioinformatics, and artificial intelligence technologies. This method can not only achieve accurate mapping of species distribution and habitats but also extend to spatial expression at the phylogenetic and genetic levels. This approach will help improve the comprehensiveness and scientific rigor of diversity assessment, promote the intelligent transformation of global-scale biodiversity monitoring, and meet the practical needs of international policies for multi-dimensional, multi-scale information support.

[0057] Specifically, Figure 1 This is a schematic flowchart illustrating the biodiversity mapping method provided in an embodiment of this application.

[0058] like Figure 1 As shown, this biodiversity mapping method includes the following steps:

[0059] In step S101, remote sensing observation data, ground-based observation data, and species information data are acquired.

[0060] The remote sensing observation data includes at least one of the following: high-resolution optical image data, synthetic aperture radar data, lidar data, nighttime light data, topographic data, climate reanalysis data, and future simulation product data; the ground-based observation data includes at least one of the following: meteorological station record data, flux tower data, ecological station plot monitoring data, near-ground phenological camera time series data, and hyperspectral observation data.

[0061] Specifically, in combination Figure 2 As shown, for acquiring remote sensing observation data, the embodiments of this application acquire multi-source remote sensing observation data covering ecological elements such as spatial structure, vegetation status, climate environment, and human activities on a global scale. This mainly includes spatial structure data such as DEM (Digital Elevation Model), SAR (Synthetic Aperture Radar), and GEDI (Global Ecosystem Dynamics Investigation), as well as spatial structure data such as NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), and FAPAR (Fraction of Absorbed Photosynthetically Active) provided by MODIS (Moderate Resolution Imaging Spectroradiometer), Sentinel-2, and Landsat. Vegetation indices such as radiation (the proportion of photosynthetically active radiation absorbed), reanalysis climate data such as ERA5 and CHIRPS, and future climate scenarios provided by CMIP6 (such as SSP2-4.5 and SSP5-8.5) also include remote sensing products related to human activities such as nighttime light and land use change. All data undergo unified projection transformation, spatial resampling, temporal interpolation, and rasterization to form a structured and standardized remote sensing dataset.

[0062] For ground-based observation data, this application integrates multiple types of ground-based observation data to enhance the ground-based constraints and ecological interpretability of remote sensing, including conventional meteorological data such as temperature, precipitation, humidity, and wind speed from meteorological stations, and NPP (Net Primary Production) data recorded by the ecological flux station (FLUXNET).

[0063] Data on ecological processes such as net primary productivity (NPMP), carbon exchange, and energy flux; long-term observational data on biomass, cover, and soil moisture from national ecological monitoring stations; plant physiological parameters acquired by SIF tower stations and ground-based hyperspectral instruments; and vegetation phenological images collected by systems such as PhenoCam. All ground-based data, after outlier removal, temporal interpolation, and spatial reconstruction, were matched with remote sensing data in terms of spatial resolution and temporal scale, providing high-precision ground-based observational support for modeling.

[0064] For species information data, occurrence records of target species are extracted from platforms such as GBIF (Global Biodiversity Information Facility) and national species distribution databases, and phylogenetic tree and gene sequence data are obtained from platforms such as NCBI (National Center for Biotechnology Information) and OTOL (Open Tree of Life). Distribution point information is cleaned and spatial accuracy is checked to establish positive and negative sample sets. Occurrence location information of target species is extracted from global or national species observation databases (such as GBIF, national biodiversity monitoring platforms, etc.), and records with abnormal geographical coordinates, missing collection time, or unclear species identification are screened out to establish a high-quality positive sample set. At the same time, pseudo-negative sample point sets are constructed in areas where the species has not been observed according to the principles of spatial uniformity or ecological distance.

[0065] In practice, the first step is to collect multi-source remote sensing and ground-based ecological monitoring data. Remote sensing data includes medium- and high-resolution optical imagery (such as MODIS, Landsat, Sentinel-2), synthetic aperture radar (such as Sentinel-1), lidar (such as GEDI), nighttime light (VIIRS, DMSP), topographic data (such as SRTMDEM), climate reanalysis (such as ERA5), and future simulation products (CMIP6SSP2-4.5, SSP5-8.5). This data undergoes a unified projection transformation P, spatial resampling R, and temporal reconstruction T to generate a standard raster.

[0066] G r =T(R(P(D) r )));

[0067] Among them, G r For standard raster data after projection transformation, spatial resampling, and temporal reconstruction, D r Let be the diverse raster data of the original input, P be the projection transformation, R be the spatial resampling, and T be the temporal reconstruction.

[0068] Ground-based observation data includes meteorological station records (temperature, precipitation, wind speed), flux tower data (such as NPP, NEE), ecological station plot monitoring (leaf area index, vegetation cover), near-ground phenological camera time series (GCC), and hyperspectral observations (such as SIF). For time series data {x t To perform quality control, outliers are removed using standard deviation, and time-series interpolation is performed.

[0069]

[0070] Where, x t Let x be the original observation value at time t. t ′ represents the sequence value after outlier correction, μ is the mean of the sequence, and 3σ is three times the standard deviation of the sequence, used to determine whether the data is an outlier.

[0071] Species distribution information was obtained from databases such as GBIF, Map of Life, and national platforms, and observation points were obtained after species identification, temporal location, and coordinate accuracy verification. After constructing positive samples, pseudo-negative samples were sampled from unrecorded areas using the ecological distance method to ensure a balanced distribution of positive and negative samples.

[0072] In step S102, an ecological data cube is constructed based on remote sensing observation data, ground-based observation data, and species information data, and statistical features, frequency features, and phenological features are extracted based on the ecological data cube.

[0073] The statistical characteristics include at least one of the following: annual mean, annual standard deviation, annual coefficient of variation, interannual variation range, seasonal variation range, and greenness growth period length; the frequency characteristics include at least one of the following: high temperature frequency and low temperature frequency.

[0074] Specifically, after acquiring remote sensing observation data, ground-based observation data, and species information data, this application embodiment needs to perform spatial registration on all data, uniformly rasterize them (e.g., 1km accuracy), and construct an integrated ecological data cube as the basis for diversity modeling.

[0075] The embodiments of this application extract statistical features of remote sensing and meteorological time series, such as annual mean, extreme values, standard deviation, and coefficient of variation, as well as frequency features (such as frequency of extreme high temperatures, frequency of vegetation fluctuations, and length of growing season).

[0076] For species distribution and ecological gradient, an environmental factor matrix was constructed, and correlation and collinearity analysis (such as VIF calculation) was performed between variables. Multiple rounds of screening were conducted using methods such as principal component analysis (PCA) and variable importance analysis (such as random forest) to determine the set of key environmental factors for three types of diversity modeling.

[0077] In practice, remote sensing, ground-based, and species data are spatially matched, with a unified raster resolution (e.g., 500m or 1km), cropped to the study area, and an ecological data cube is constructed.

[0078] C(x,y,t)={v1(x,y,t),v2(x,y,t),…,v n (x,y,t)};

[0079] Where C(x,y,t) is the ecological data cube of location (x,y) and time t, x is the longitude coordinate, y is the latitude coordinate, t is the time index, and v n This refers to the nth ecological variable or observation value at that spatiotemporal location.

[0080] Based on the ecological data cube, statistical, frequency, and phenological characteristics are extracted as inputs for modeling.

[0081] For a continuous variable v(t), the following statistical features are extracted:

[0082] Annual average:

[0083] Where μ is the annual average, T is the total observation time (e.g., the number of time steps within a year), v(t) is the observed value or variable value at time t, and t is the time index.

[0084] Annual standard deviation:

[0085] Where σ is the annual standard deviation, μ is the annual mean, T is the total observation time (e.g., the number of time steps within a year), v(t) is the observation value at time t, and t is the time index.

[0086] Annual coefficient of variation (CV):

[0087] Where CV is the annual coefficient of variation, μ is the annual mean, and σ is the annual standard deviation.

[0088] Interannual variation range: ΔY = v(t+1) - v(t)

[0089] Where ΔY is the interannual variation, v(t+1) is the observed value at time t+1, and v(t) is the observed value at time t.

[0090] Seasonal amplitude: S = max(vt )-min(v t );

[0091] Where S is the seasonal amplitude, max(v t ) for a year v t The maximum value, min(v) t ) for a year v t The minimum value.

[0092] Greenness growth period length: with v(t)>v (threshold) The definition of continuous time length.

[0093] Where v(t) is the observed value at time t (e.g., vegetation index), v (threshold) To determine the threshold of the growing season.

[0094] Frequency characteristics are used to characterize extreme weather interference:

[0095] High temperature frequency: F T =∑ t 1[v(t)>T0];

[0096] Among them, F T Here, v(t) represents the frequency of high temperatures, v(t) represents the meteorological observation value (such as temperature) at time t, and T0 represents the high temperature threshold.

[0097] Drought frequency: F D =∑ t 1[v(t) <D0];

[0098] Among them, F D denoted as the drought frequency, v(t) as the meteorological observation value (such as precipitation or humidity) at time t, and D0 as the drought threshold.

[0099] Species distribution information was obtained from GBIF and Map of Life. Variance inflation factor (VIF) was calculated using Pearson coefficient matrix RRR analysis.

[0100]

[0101] Among them, VIF i Let be the variance inflation factor of the i-th variable. The coefficient of determination is the coefficient of determination when the i-th variable is the dependent variable and the other variables are independent variables, where i is the variable index.

[0102] Variables with severe multicollinearity (e.g., VIF > 10) are removed. Dimensionality reduction is achieved by combining random forest variable importance scores (Gini Gain or Mean Decrease Accuracy) and principal component analysis (PCA) to select robust and informative feature subsets.

[0103] In step S103, a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map are constructed based on statistical characteristics, frequency characteristics, and phenological characteristics. The spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are then fused to obtain a fusion result. Based on the fusion result, high diversity areas and low conservation areas are identified, and the high diversity areas and low conservation areas are evaluated to obtain an evaluation result.

[0104] Optionally, in some embodiments, constructing a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on statistical features, frequency features, and phenological features includes: constructing a species habitat suitability model using a preset maximum entropy model based on statistical features, frequency features, and phenological features, and obtaining a spatial map of species diversity based on the species habitat suitability model; calculating a phylogenetic diversity index based on statistical features, frequency features, and phenological features, and obtaining a phylogenetic diversity map based on the phylogenetic diversity index; and calculating expected heterozygosity and / or nucleotide diversity based on statistical features, frequency features, and phenological features, and obtaining a global genetic diversity map based on expected heterozygosity and / or nucleotide diversity.

[0105] Specifically, based on high-quality species distribution samples and environmental factors, a species habitat suitability model is constructed using a pre-defined maximum entropy model MaxEnt and a pre-defined maximum entropy model, and a species diversity spatial map (such as an AOH map) is generated.

[0106] Based on phylogenetic tree information and combined with the spatial distribution of species, the Faith phylogenetic diversity index is calculated and mapped to a global scale to form a phylogenetic diversity map.

[0107] Based on species genetic sequence information and spatial distribution, genetic diversity indicators such as expected heterozygosity (He) and nucleotide diversity (π) are calculated, and a global genetic diversity map is constructed through spatial interpolation.

[0108] Based on the above data processing results, the three types of diversity results are integrated and overlaid for analysis. High diversity areas and low protection areas are identified by methods such as clustering, principal component analysis, or weighted scoring. Combined with land use, protected area boundaries, and climate scenario predictions, the threat level and protection priority of diversity hotspots are assessed, providing a basis for decision-making for the global biodiversity strategic layout and the identification of key ecological areas.

[0109] In actual implementation, the embodiments of this application construct three types of diversity mapping models respectively:

[0110] 1. Diversity modeling.

[0111] Based on the established sample and variable set, construct a habitat suitability model using MaxEnt or random forest models:

[0112] max p [-∑ x p(x)logp(x)], so that

[0113] Where p(x) is the probability distribution of the sample points, f j (x) is the j-th environmental feature function. This represents the expected value of the feature function at the sample point.

[0114] The output fitness probability map P(x,y) is combined with the species habitat threshold θ to generate a binary habitat map:

[0115]

[0116] Where P(x,y) is the suitability probability of position (x,y), and θ is the threshold.

[0117] 2. Developmental diversity modeling.

[0118] Based on the phylogenetic tree TTT, the set of species within each spatial unit is mapped to the branch set B(A), and the Faith index is calculated:

[0119] PD A =∑ b∈B(A) L b ;

[0120] Among them, PD A Let b be the phylogenetic diversity of set A, b be a branch of the phylogenetic tree, B(A) be the set of branches covered by set A, and L be the phylogenetic diversity of set A. b Let be the length of branch b.

[0121] To emphasize the uniqueness and rarity of a branch, weighted phylogenetic diversity can be introduced:

[0122]

[0123] Where ω is the weighting coefficient, f b Let b be the frequency of occurrence of branch b.

[0124] 3. Genetic diversity modeling.

[0125] Genetic indices for the population within each grid cell are calculated based on species genetic data. Expected heterozygosity is the primary metric used.

[0126]

[0127] Where He represents the expected heterozygosity. Let be the squared frequency of the i-th allele, and k be the number of allele types.

[0128] Alternatively, nucleotide diversity can also be introduced:

[0129]

[0130] Where π represents nucleotide diversity, d ij Let represent the base difference between the i-th and j-th sequences, and n be the number of individuals. Raster expression is achieved using Kriging or IDW interpolation.

[0131] Optionally, in some embodiments, the fusion of the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map to obtain a fusion result includes: fusing the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map based on a preset fusion formula to obtain a fusion result, wherein the preset fusion formula is:

[0132] D(x,y)=w1·P AOH (x,y)+w2·PD(x,y)+w3·He(x,y)

[0133] Where D(x,y) is the value of the comprehensive diversity index at position (x,y), and P AOH (x,y) represents the species richness at location (x,y), PD(x,y) represents the phylogenetic diversity at location (x,y), He(x,y) represents the genetic diversity at location (x,y), w1 represents the fusion weight of the spatial map of species diversity, w2 represents the fusion weight of the phylogenetic diversity map, and w3 represents the fusion weight of the global genetic diversity map.

[0134] The three diversity maps were standardized and overlaid to construct a fused diversity index. The Jenks natural break method was used to partition the fused results, and overlay analysis was performed in conjunction with existing protected area boundaries to identify "high diversity – low protected area coverage" zones. Furthermore, habitat simulation results for 2050 and 2100 under SSP2 / SSP5 scenarios were used to calculate the rate of change in suitable habitat.

[0135]

[0136] Where ΔS is the suitable raster change rate, S future S is the appropriate number of grid cells for the future scenario.current The appropriate number of grid cells at present.

[0137] It also analyzes the spatial migration direction, clustering changes and fragmentation trends of diverse hotspots to assist in the formulation of priority protection zone layout plans and the identification of key migration channels.

[0138] Therefore, the biodiversity mapping method proposed in this application integrates multi-source remote sensing data and ground-based observation information, and combines artificial intelligence and supercomputing acceleration technology to achieve multi-level spatial mapping of global terrestrial vertebrate and higher plant species diversity, phylogenetic diversity and genetic diversity. It is applicable to scenarios such as ecological protection assessment, biodiversity monitoring and policy support.

[0139] The biodiversity mapping method proposed in this application involves acquiring remote sensing data, ground-based observation data, and species information data. An ecological data cube is constructed based on these data, and statistical, frequency, and phenological features are extracted from the ecological data cube. Based on these features, spatial maps of species diversity, phylogenetic diversity, and global genetic diversity are constructed. These maps are then fused to obtain a fusion result. Based on the fusion result, high-diversity areas and low-protection areas are identified, and these areas are evaluated to obtain an assessment result. This addresses the problem that related technologies rely heavily on sample size and data accuracy, making it difficult to reveal phylogenetic and genetic patterns and meet the needs of global-scale decision-making and management. This application can integrate multi-source satellite remote sensing and ground-based data, improving the comprehensiveness and scientific rigor of diversity assessment.

[0140] Next, a biodiversity mapping apparatus according to an embodiment of this application is described with reference to the accompanying drawings.

[0141] Figure 3 This is a block diagram of a biodiversity mapping device according to an embodiment of this application.

[0142] like Figure 3 As shown, the biodiversity mapping device 10 includes: an acquisition module 100, a construction module 200, and a mapping module 300.

[0143] The acquisition module 100 is used to acquire remote sensing observation data, ground-based observation data, and species information data.

[0144] Module 200 is used to construct an ecological data cube based on remote sensing observation data, ground-based observation data, and species information data, and to extract statistical features, frequency features, and phenological features from the ecological data cube.

[0145] The mapping module 300 is used to construct a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on statistical features, frequency features, and phenological features. It then merges the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map to obtain a fusion result. Based on the fusion result, it identifies high-diversity areas and low-protection areas and evaluates these areas to obtain an assessment result.

[0146] Optionally, in some embodiments, the mapping module 300 includes: a first building unit, a second building unit, and a third building unit.

[0147] The first building unit is used to construct a species habitat suitability model based on statistical features, frequency features, and phenological features, using a preset maximum entropy model and a preset random forest model, and to obtain a species diversity spatial map based on the species habitat suitability model.

[0148] The second building block is used to calculate the phylogenetic diversity index based on statistical characteristics, frequency characteristics, and phenological characteristics, and to obtain a phylogenetic diversity map based on the phylogenetic diversity index.

[0149] The third building block is used to calculate the expected heterozygosity and / or nucleotide diversity based on statistical, frequency, and phenological characteristics, and to obtain a global genetic diversity map based on the expected heterozygosity and / or nucleotide diversity.

[0150] Optionally, in some embodiments, the fusion of the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map to obtain a fusion result includes: fusing the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map based on a preset fusion formula to obtain a fusion result, wherein the preset fusion formula is:

[0151] D(x,y)=w1·P AOH (x,y)+w2·PD(x,y)+w3·He(x,y)

[0152] Where D(x,y) is the value of the comprehensive diversity index at position (x,y), and P AOH (x,y) represents the species richness at location (x,y), PD(x,y) represents the phylogenetic diversity at location (x,y), He(x,y) represents the genetic diversity at location (x,y), w1 represents the fusion weight of the spatial map of species diversity, w2 represents the fusion weight of the phylogenetic diversity map, and w3 represents the fusion weight of the global genetic diversity map.

[0153] Optionally, in some embodiments, the remote sensing observation data includes at least one of the following: high-resolution optical image data, synthetic aperture radar data, lidar data, nighttime light data, topographic data, climate reanalysis data, and future simulation product data; the ground-based observation data includes at least one of the following: meteorological station record data, flux tower data, ecological station plot monitoring data, near-ground phenological camera time series data, and hyperspectral observation data.

[0154] Optionally, in some embodiments, the statistical characteristics include at least one of the following: annual mean, annual standard deviation, annual coefficient of variation, interannual variation, seasonal variation, and greenness growth period length; the frequency characteristics include at least one of the following: high temperature frequency and low temperature frequency.

[0155] It should be noted that the explanation of the aforementioned embodiment of the biodiversity mapping method also applies to the biodiversity mapping device of this embodiment, and will not be repeated here.

[0156] The biodiversity mapping device proposed in this application acquires remote sensing observation data, ground-based observation data, and species information data. Based on these data, an ecological data cube is constructed. Statistical, frequency, and phenological characteristics are extracted from the ecological data cube. Based on these characteristics, spatial, phylogenetic, and global genetic diversity maps are constructed. These maps are then fused to obtain a fusion result. Based on the fusion result, high-diversity and low-protection areas are identified, and these areas are evaluated to obtain an assessment result. This solves the problem that related technologies rely on sample size and data accuracy, making it difficult to reveal phylogenetic and genetic patterns and meet the needs of global-scale decision-making and management. This application can fuse multi-source satellite remote sensing and ground-based data, improving the comprehensiveness and scientific rigor of diversity assessment.

[0157] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0158] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0159] When the processor 402 executes the program, it implements the biodiversity mapping method provided in the above embodiments.

[0160] Furthermore, electronic devices also include:

[0161] Communication interface 403 is used for communication between memory 401 and processor 402.

[0162] The memory 401 is used to store computer programs that can run on the processor 402.

[0163] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0164] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0165] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0166] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0167] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described biodiversity mapping method.

[0168] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0169] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0170] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0171] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0172] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0173] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for mapping biodiversity, characterized in that, Includes the following steps: Acquire remote sensing observation data, ground-based observation data, and species information data. An ecological data cube is constructed based on the remote sensing observation data, ground-based observation data, and species information data, and statistical features, frequency features, and phenological features are extracted from the ecological data cube. Based on the statistical characteristics, frequency characteristics, and phenological characteristics, a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map are constructed. The spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are then fused to obtain a fusion result. Based on the fusion result, high-diversity areas and low-protection areas are identified, and the high-diversity areas and low-protection areas are evaluated to obtain an evaluation result. The construction of a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on the statistical features, frequency features, and phenological features includes: constructing a species habitat suitability model using a preset maximum entropy model or a preset random forest model based on the statistical features, frequency features, and phenological features, and obtaining the spatial map of species diversity based on the species habitat suitability model; calculating a phylogenetic diversity index based on the statistical features, frequency features, and phenological features, and obtaining the phylogenetic diversity map based on the phylogenetic diversity index; and calculating expected heterozygosity and / or nucleotide diversity based on the statistical features, frequency features, and phenological features, and obtaining the global genetic diversity map based on the expected heterozygosity and / or the nucleotide diversity.

2. The method according to claim 1, characterized in that, The fusion result obtained by fusing the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map includes: Based on a preset fusion formula, the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are fused to obtain a fusion result, wherein the preset fusion formula is: in, To integrate the diversity index at the location The value of , For position Species richness, For position phylogenetic diversity, For position Genetic diversity, For the fusion weights of the spatial map of species diversity, For the fusion weights of phylogenetic diversity maps, The fusion weights are those of the global genetic diversity map.

3. The method according to claim 1, characterized in that, The remote sensing data includes at least one of the following: high-resolution optical image data, synthetic aperture radar data, lidar data, nighttime light data, topographic data, climate reanalysis data, and future simulation product data; The ground-based observation data includes at least one of the following: meteorological station records, flux tower data, ecological station plot monitoring data, near-ground phenological camera time series data, and hyperspectral observation data.

4. The method according to claim 1, characterized in that, The statistical characteristics include at least one of the following: annual mean, annual standard deviation, annual coefficient of variation, interannual variation, seasonal variation, and greenness growth period length. The frequency characteristics include at least one of high temperature frequency and low temperature frequency.

5. A biodiversity mapping device, characterized in that, include: The acquisition module is used to acquire remote sensing observation data, ground-based observation data, and species information data. The construction module is used to construct an ecological data cube based on the remote sensing observation data, ground-based observation data, and species information data, and to extract statistical features, frequency features, and phenological features based on the ecological data cube; The mapping module is used to construct a spatial map of species diversity, a phylogenetic diversity map, and a global genetic diversity map based on the statistical features, the frequency features, and the phenological features; to fuse the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map to obtain a fusion result; to identify high-diversity areas and low-protection areas based on the fusion result; and to evaluate the high-diversity areas and low-protection areas to obtain an evaluation result. The mapping module includes: The first construction unit is used to construct a species habitat suitability model based on the statistical characteristics, frequency characteristics, and phenological characteristics, using a preset maximum entropy model or a preset random forest model, and to obtain the species diversity spatial map based on the species habitat suitability model. The second construction unit is used to calculate the phylogenetic diversity index based on the statistical characteristics, the frequency characteristics, and the phenological characteristics, and to obtain the phylogenetic diversity map based on the phylogenetic diversity index. The third building unit is used to calculate the expected heterozygosity and / or nucleotide diversity based on the statistical characteristics, the frequency characteristics, and the phenological characteristics, and to obtain the global genetic diversity map based on the expected heterozygosity and / or the nucleotide diversity.

6. The apparatus according to claim 5, characterized in that, The fusion result obtained by fusing the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map includes: Based on a preset fusion formula, the spatial map of species diversity, the phylogenetic diversity map, and the global genetic diversity map are fused to obtain a fusion result, wherein the preset fusion formula is: in, To integrate the diversity index at the location The value of , For position Species richness, For position phylogenetic diversity, For position Genetic diversity, For the fusion weights of the spatial map of species diversity, For the fusion weights of phylogenetic diversity maps, The fusion weights are those of the global genetic diversity map.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the biodiversity mapping method as described in any one of claims 1-4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the biodiversity mapping method as described in any one of claims 1-4.

Images