A multi-source heterogeneous ecological data spatio-temporal alignment and grid standardization method and system

Abstract

The present application relates to the cross field of ecological big data processing and geographic information system, and provides a multi-source heterogeneous ecological data space-time alignment and grid standardization method and system. The multi-source heterogeneous ecological data space-time alignment and grid standardization method comprises the following steps: loading classified ecological monitoring grid data in an independent sandbox environment, and converting the classified ecological monitoring grid data into grid occupancy rate data; calculating the grid occupancy rate of classified elements in each grid pixel; adding random noise to generate public grid values; and outputting safe classified ecological monitoring grid data. The preprocessed data is subjected to spatial alignment and time alignment. The spatial alignment comprises the following steps: calculating the ecological weight factor of each grid pixel based on the data of the region to be calculated; decomposing the total value of the index of the region to be calculated to each grid pixel according to the total sum of the weight factors of all grid pixels, to obtain the decomposed index value of each grid pixel, thereby realizing high-precision, traceable and compliant safety of the data.

Description

Technical Field

[0001] This invention relates to the field of interdisciplinary technology of ecological big data processing and geographic information systems, and in particular to a method and system for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Data is the core foundation in the process of calculating the value of Genetic Products (GEP). Currently, the data required for GEP calculation comes from a wide range of sources and is diverse in type, mainly including: remote sensing raster data (NDVI, NPP, land use, resolution 10m-1km), ecological monitoring data (soil, hydrology, water quality, biomass), socio-economic statistics (GDP, population, prices, conservation inputs), and meteorological observation data (precipitation, temperature, sunshine duration).

[0004] In existing technologies, the processing of multi-source heterogeneous ecological data mainly faces the following unresolved core technical challenges: 1. Existing commonly used spatial interpolation methods (such as area weighting, Kriging interpolation, and inverse distance weighting) generally suffer from total distortion when decomposing administrative region statistics (such as GDP and population) into raster cells. Specifically, the sum of all raster values ​​decomposes significantly deviates from the original total for the administrative region. This deviation is tolerable in general GIS applications, but unacceptable in GEP accounting—because GEP accounting results are directly used for horizontal comparisons between administrative regions, ecological compensation fund calculations, and performance evaluations. Any non-systematic total distortion will lead to inaccurate policy basis. Current technology lacks a spatial downscaling method that can mathematically guarantee the conservation of total data.

[0005] 2. Remote sensing raster data represents surface physical quantities (such as vegetation cover and evapotranspiration), meteorological station data represents point observations, and administrative statistical data represents socio-economic aggregates. These three types differ not only in spatial scale and temporal granularity but also in their fundamentally different econometric logic. Existing methods directly assign point / area data to raster data through interpolation, ignoring the essential differences in "spatial representativeness" among the three types, resulting in ecologically uninterpretable fused raster data. For example, distributing the total GDP of a township equally across 30-meter raster cells according to area would lead to the clearly illogical conclusion that "the GDP contribution of farmland raster cells is the same as that of construction land raster cells."

[0006] 3. Classified data such as ecological red lines, high-resolution groundwater data, and vector data of water source protection areas cannot be exported, forcing the interruption of general data processing workflows. Existing technologies lack a "data usable but not visible" raster standardization method—one that can securely incorporate classified data into the GEP raster-level accounting process without exposing the original classified coordinates. Summary of the Invention

[0007] To address the technical problems mentioned above, this invention provides a method and system for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data. This invention employs a differential privacy sandbox to ensure secure access to classified data, uses ecological weight factor-driven spatiotemporal alignment to guarantee semantic consistency of multi-source data, and uses total quantity-preserving downscaling to mathematically ensure the accuracy and policy usability of the decomposition results. These three elements work synergistically to form a complete, high-precision, traceable, compliant, and secure multi-source heterogeneous ecological data standardization processing system, solving a long-standing technical problem that has remained unsolved in this field.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data.

[0009] A method for spatiotemporal alignment and raster normalization of multi-source heterogeneous ecological data includes: Obtain rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be accounted for. The ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. Load classified ecological monitoring raster data into an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. Preprocessing is performed on remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data; The preprocessed data undergoes spatial and temporal alignment to ensure all data have a unified spatial raster baseline and temporal baseline. The spatial alignment includes: calculating the ecological weight factor for each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data, and economic and social statistical raster data in the area to be calculated; and decomposing the total index value of the area to be calculated into each raster cell based on the sum of the weight factors of all raster cells, thereby obtaining the decomposed index value for each raster cell, which is used for GEP calculation.

[0010] Furthermore, the publicly disclosed raster value is calculated using the following formula:

[0011] in, Indicates the public raster value; This indicates the raster occupancy rate of classified elements within each raster cell. Indicates query sensitivity; Indicates privacy budget; This represents Laplace distribution noise.

[0012] Furthermore, the preprocessing includes: detecting outliers using box plots and the 3σ criterion, and then correcting them using linear interpolation / Kriging interpolation; completing missing data and deleting redundant data.

[0013] Furthermore, data standardization is performed before GEP calculation.

[0014] Furthermore, a quality traceability report is generated during the preprocessing process.

[0015] Furthermore, the classified ecological monitoring grid data does not leave the sandbox environment.

[0016] Furthermore, the calculation of the ecological weight factor for each raster cell is performed using the following formula:

[0017] in, This represents the ecological weight factor for each raster cell; Represents the land use type coefficient within a raster cell; Indicates the vegetation cover within a raster cell; This represents the relative value of population density within a raster cell; , , Represents configurable weight coefficients, satisfying .

[0018] Furthermore, the process of decomposing the total index value of the area to be calculated into each raster cell to obtain the decomposed index value of each raster cell is performed using the following formula:

[0019] in, This represents the index value after decomposition of each raster cell; It represents the total value of a certain economic statistical indicator within the region to be calculated; This represents the ecological weight factor for each raster cell; This represents the sum of the weight factors for all raster cells.

[0020] A second aspect of the present invention provides a spatiotemporal alignment and raster standardization system for multi-source heterogeneous ecological data.

[0021] A spatiotemporal alignment and raster standardization system for multi-source heterogeneous ecological data includes: The data acquisition module is configured to acquire rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be calculated, wherein the ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. The sandbox desensitization module is configured to: load classified ecological monitoring raster data in an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. The data preprocessing module is configured to preprocess remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data. The spatiotemporal alignment module is configured to perform spatial and temporal alignment on the preprocessed data, so that all data have a unified spatial raster reference and temporal reference. The spatial alignment includes: calculating the ecological weight factor of each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data and economic and social statistical raster data in the area to be calculated; and decomposing the total index value of the area to be calculated to each raster cell according to the sum of the weight factors of all raster cells, so as to obtain the decomposed index value of each raster cell for the calculation of GEP.

[0022] A third aspect of the present invention provides a computer device comprising: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data as described in the first aspect above.

[0023] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and to execute steps in the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data as described in the first aspect above.

[0024] The fifth aspect of the present invention provides a computer program product or computer program.

[0025] This invention provides a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the multi-source heterogeneous ecological data spatiotemporal alignment and raster standardization method described in the first aspect above.

[0026] Compared with the prior art, the beneficial effects of the present invention are: This invention introduces ecological weight factors and total quantity constraint normalization, through formulas... The design, in theory, strictly guarantees... This means that the sum of all raster decomposition values ​​is strictly consistent with the original total for the administrative region, with the error approaching zero. This mechanism fundamentally solves the policy risks in GEP accounting, such as the failure of horizontal comparisons between administrative regions due to total distortion, inaccurate accounting of ecological compensation funds, and ineffective performance evaluation, and breaks the technical bias in this field that spatial downscaling inevitably leads to total deviation.

[0027] This invention does not simply perform geometric registration of remote sensing pixels, sampling stations, and administrative units. Instead, it uses an ecological weighting factor to fuse the land use type coefficient, vegetation cover, and relative population density within a raster pixel into a composite index with clear ecological meaning, using configurable weighting coefficients. This data is then used for total quantity preservation decomposition. This mechanism unifies the three types of data with different measurement logics at the ecological level, ensuring the ecological interpretability of the fused raster data.

[0028] This invention proposes a differential privacy sandbox rasterization method. After the raster occupancy of classified data is calculated in an independent sandbox environment, Laplace noise is injected to generate public raster values. Only the noise-perturbed, secure classified data is output, and the original vector never leaves the sandbox environment. Unlike existing technologies that either completely avoid classified data or illegally export the original data, this invention enables the compliant participation of classified data (sensitive data such as ecological red lines and water source protection areas) in GEP raster-level accounting, and the strength of privacy protection can be quantitatively controlled through privacy budgeting, thus ensuring data security. Attached Figure Description

[0029] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0030] Figure 1 This is a flowchart illustrating the spatiotemporal alignment and raster standardization method for multi-source heterogeneous ecological data according to an embodiment of the present invention; Figure 2 This is a flowchart of another embodiment of the spatiotemporal alignment and raster standardization method for multi-source heterogeneous ecological data shown in this invention; Figure 3 This is a structural diagram of a multi-source heterogeneous ecological data spatiotemporal alignment and raster standardization system shown in an embodiment of the present invention; Figure 4 This is a structural diagram of a computer device shown in an embodiment of the present invention. Detailed Implementation

[0031] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0032] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0033] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0034] To facilitate understanding of the technical solutions of this invention, some technical terms involved in this invention will be introduced below.

[0035] GEP accounting: Gross Ecosystem Product accounting refers to the quantitative assessment of the value of final products and services provided by an ecosystem within a certain area.

[0036] Total amount preservation type spatial downscaling: refers to a constrained downscaling method that requires the sum of all raster values ​​to be strictly equal to the total amount of the original administrative region when decomposing administrative region aggregate data (such as GDP, population) into raster cells, with the error approaching zero.

[0037] Differential privacy sandbox: a secure computation method that performs irreversible transformations and adds controllable noise to confidential data in an isolated environment, outputting usable statistical features while ensuring that the original data is not leaked.

[0038] As described in the background section, existing multi-source heterogeneous ecological data processing suffers from the following problems: (1) inconsistent definitions and coding of multi-source heterogeneous data (remote sensing raster, ecological monitoring, economic and social statistics, meteorology) make them unsuitable for direct use in GEP raster-level accounting; (2) mismatch between the spatial scale (pixel, sampling point, administrative region) and temporal granularity (day, month, year) of different data types, leading to difficulties in spatiotemporal alignment and high errors; and (3) the inability to securely access and standardize classified ecological data (such as ecological red lines and groundwater data), and the lack of traceability in the standardization process. To address at least one of the above technical problems, this invention provides a method and system for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data. The following describes the solution of this invention in detail through several embodiments.

[0039] Figure 1 This is a flowchart illustrating a method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data, as shown in an embodiment of the present invention; see reference. Figure 1 The method includes: Obtain rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be accounted for. The ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. Load classified ecological monitoring raster data into an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. Preprocessing is performed on remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data; The preprocessed data undergoes spatial and temporal alignment to ensure all data have a unified spatial raster baseline and temporal baseline. The spatial alignment includes: calculating the ecological weight factor for each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data, and economic and social statistical raster data in the area to be calculated; and decomposing the total index value of the area to be calculated into each raster cell based on the sum of the weight factors of all raster cells, thereby obtaining the decomposed index value for each raster cell, which is used for GEP calculation.

[0040] This invention fundamentally solves the paradox of total data distortion, the break in physical meaning, and the security dilemma of classified data in pre-GEP accounting by using a differential privacy sandbox secure computing architecture, a total data preservation spatial downscaling algorithm, and an ecological weight factor-driven fusion mechanism. It provides high-precision, traceable, compliant, and secure basic data support for GEP grid-level accounting.

[0041] Figure 2 This is a flowchart of another embodiment of the spatiotemporal alignment and raster standardization method for multi-source heterogeneous ecological data shown in this invention; the method includes the following steps, described in detail below: Step 1: Multi-source data access.

[0042] Step 1.1: Configure the access interface.

[0043] The system supports access to various data formats, including but not limited to: TIFF, SHP, CSV, Excel, database tables, and API interfaces. For remote sensing raster data, it supports common formats such as GeoTIFF, HDF, and NetCDF; for ecological monitoring raster data, it supports point vector (SHP), tables (CSV / Excel), and direct database reading; for economic and social statistical raster data, it supports statistical yearbook tables and public data interfaces.

[0044] Step 1.2: Encrypted transmission and sandbox isolation of classified data.

[0045] For classified ecological monitoring raster data (such as ecological red line raster, high-resolution groundwater monitoring data, and water source protection area raster), after being accessed to the system through an encrypted transmission channel, permission verification is first performed, including dual verification of user identity authentication and data access authorization. Only after successful verification can the data enter an independent differential privacy sandbox environment. This sandbox is physically isolated from the external network, and the original classified data must not be exported from the sandbox in any form.

[0046] To ensure the security of classified ecological monitoring raster data, this embodiment employs a differential privacy sandbox security calculation mechanism. Specifically, after loading the classified original raster data into the sandbox environment, it is first uniformly converted to the target raster resolution R (e.g., 30m), and then the raster occupancy rate of classified elements (pre-calibrated manually) within each raster cell is calculated. This refers to the proportion of the area covered by classified elements within a raster cell to the total area of ​​the raster cells, with a value ranging from 0 to 1. To prevent the original classified information from being inferred through multiple queries, the occupancy rate of each raster cell is set. Add random noise that follows a Laplace distribution to generate public raster values. The formula is as follows: (1) in, This indicates the query sensitivity, with a value of 1 / m, where m represents the total number of raster cells covered by the classified data. This refers to the privacy budget, which is configured by the user based on their security needs. The smaller the value, the greater the noise intensity and the stronger the privacy protection, but the lower the data availability. The typical value range is [0.1, 1.0]. This represents Laplace distribution noise. Ultimately, only the security-protected raster data after noise perturbation (e.g., "the ecological red line area within this 30-meter pixel is (0,30%)") is output to participate in subsequent processing. The original security-protected data never leaves the sandbox environment.

[0047] Step 1.3: Meta-information parsing and database construction.

[0048] The system automatically parses metadata for various data types, including: data type (raster / vector / tabular / time-series), numerical units, spatial coordinate reference system (projected coordinate system or geographic coordinate system), time granularity (day / month / quarter / year), data source organization, and version number. After parsing, all metadata is stored in a unified metadata database, providing a basis for subsequent spatiotemporal alignment and standardization processing.

[0049] Step 2: Data preprocessing and quality control.

[0050] Step 2.1: Outlier detection and correction.

[0051] For all accessed data, outlier detection is performed first. A box plot method combined with the 3σ criterion is used for outlier detection: the box plot method identifies outliers based on the interquartile range (IQR), i.e., values ​​less than Q1 - 1.5 × IQR or greater than Q3 + 1.5 × IQR are considered outliers, where Q1 and Q3 represent the lower and upper quartiles of the data, respectively; the 3σ criterion is based on the mean and standard deviation, classifying values ​​exceeding the mean ± 3 times the standard deviation as outliers. For detected outliers, if the data is spatially continuous (e.g., remote sensing pixel values, raster surface data), Kriging interpolation or inverse distance-weighted interpolation is used to correct for them using surrounding normal pixel values; if the data is time-series data (e.g., daily meteorological observation values), linear interpolation is used to correct for them using normal values ​​from preceding and following time phases.

[0052] Step 2.2: Fill in missing values.

[0053] Different strategies are adopted for different types of missing data: For missing values ​​in remote sensing raster data (such as data missing due to cloud cover or sensor failure), the mean of neighboring pixels in the same period is used to fill in the missing values, or time-series interpolation of previous and subsequent time phases is used to fill in the missing values; For missing items in statistical data (such as GDP not being counted in a certain year), the historical mean of the same type of indicator in the same administrative region or the value of the same period in the neighboring region is used to fill in the missing values; For missing observations at monitoring stations, the co-kriging method is used to estimate the missing values ​​by utilizing spatial correlation and covariates.

[0054] Step 2.3: Redundant data deletion.

[0055] Identify and automatically delete duplicate data, logically contradictory data, or data that is irrelevant to the GEP accounting objectives, such as multiple identical image copies at the same spatial location and time phase, or outdated data that is no longer relevant.

[0056] Step 2.4: Generate a quality inspection report.

[0057] The system records detailed log information for the entire cleaning process, including the location and number of outliers, the correction methods and parameters used, the basis for filling missing values ​​and the interpolation method, and a list of redundant data to be deleted. Finally, it generates a structured quality traceability report to ensure that every step of the process is traceable and reproducible.

[0058] Step 3: Spatiotemporal alignment processing.

[0059] Step 3.1: Spatial alignment.

[0060] Step 3.1.1: Determine the target raster parameters.

[0061] Based on the spatial accuracy requirements of GEP calculation, uniform parameters of the target raster are pre-set, including: resolution (such as 30m, 100m or 1km, determined according to the area and accuracy requirements of the calculation area), coordinate system and pixel data type.

[0062] Step 3.1.2: Spatial alignment of remote sensing raster data.

[0063] All remote sensing raster data undergoes a projection transformation to unify them to the target coordinate system; then, bilinear interpolation is used to resample them to the target resolution. For discrete raster data such as land use classifications, nearest neighbor interpolation is used to maintain the integrity of category attributes and avoid interpolating non-existent land use codes.

[0064] Step 3.1.3: Spatial alignment of site and sampling point data.

[0065] For data from ecological monitoring stations (such as water quality monitoring points, soil sampling points, and meteorological observation stations), the station's latitude and longitude coordinates are first matched and located with the target raster spatial grid. Then, ordinary kriging interpolation or co-kriging interpolation methods are used to spatialize the discrete point observations into continuous raster surface data. During the interpolation process, covariates such as topographic elevation and land use type can be introduced to improve interpolation accuracy.

[0066] Step 3.1.4: Spatial downscaling of statistical data for administrative regions.

[0067] For aggregated data at the administrative region level, such as GDP, population, and fertilizer application, the total amount-preserving spatial downscaling algorithm proposed in this invention is applied. Let the total value of a certain economic statistical indicator (such as GDP, population, or fertilizer application) within the administrative region be... The administrative region is divided into n target raster pixels. The specific steps are as follows.

[0068] (1) Calculate the ecological weight factor for each raster cell. The following formula is used: (2) in, This represents the land use type coefficient within a raster cell. Empirical coefficients are pre-configured based on ecosystem types (forest, wetland, farmland, grassland, water area, construction land, etc.) to reflect the differences in the contribution of different land types to ecological value. For example, forests are assigned 0.8, farmland 0.5, and construction land 0.1. It represents the vegetation cover within a raster cell, obtained by inversion from the Normalized Difference Vegetation Index (NDVI) remote sensing data, with a value range of [0,1], reflecting the density of surface vegetation; This represents the relative population density within a raster cell, normalized to [0,1], reflecting the spatial distribution of human activity intensity. , , Represents configurable weight coefficients, satisfying Users can dynamically adjust the calculation based on the type of accounting indicator; for example, when decomposing GDP, they can appropriately increase the percentage of GDP. The value should be appropriately increased when calculating water source conservation. value.

[0069] (2) Calculate the sum of weight factors for all raster cells within the administrative region: (3) (3) Calculate the index value after decomposition of each raster cell: (4) It can be rigorously derived from formula (4): That is, the sum of all raster decomposition values ​​equals This achieves mathematical conservation of total quantity and completely solves the problem of 5%-15% total quantity distortion in existing methods.

[0070] Step 3.2: Time alignment.

[0071] Step 3.2.1: Determine the target time granularity.

[0072] Based on the GEP accounting cycle (usually annual or quarterly), a unified target time granularity is set, such as "year" or "quarter".

[0073] Step 3.2.2: High temporal granularity data aggregation.

[0074] For high-frequency data such as daily or monthly remote sensing indices (e.g., NDVI monthly composite products) and daily meteorological observations, the data is aggregated to the target time granularity using the mean (e.g., annual average temperature) or summation (e.g., annual precipitation).

[0075] Step 3.2.3: Upscale low-time-granularity data.

[0076] For statistical data with only annual records, if quarterly accounting is required, linear interpolation or polynomial interpolation methods are used to smoothly distribute the annual value to each quarter, while adjusting the proportions to ensure that the sum of each quarter is strictly equal to the annual total.

[0077] Step 3.2.4: Time synchronization calibration.

[0078] Ensure that the timestamps of all data layers are aligned to a unified time base. For data whose actual time intervals do not match the base, perform cropping or extension processing and generate a time consistency report for record-keeping.

[0079] Step 4: Raster normalization.

[0080] Step 4.1: Code standardization.

[0081] Establish a unified raster pixel encoding rule and adopt a combined encoding scheme of "region code + row and column number + time identifier" to ensure that each pixel has a unique identifier in the global scope, which facilitates subsequent retrieval and traceability.

[0082] Step 4.2: Unit standardization.

[0083] Convert all physical units of data to the International System of Units (SI).

[0084] Step 4.3: Standardize the numerical range.

[0085] For specific model input requirements, raster values ​​can be normalized, such as by min-max normalization or Z-score standardization, but the original value fields must be retained for total quantity conservation calculation and result verification.

[0086] Step 4.4: Generate a standardized raster dataset.

[0087] The data layers that have undergone all the above processing steps, including remote sensing index raster, ecological monitoring index raster, socio-economic statistical index decomposition raster, and security-desensitized classified data raster, are organized according to a unified spatial grid and a unified time slice to form a standardized raster dataset that can be directly input into the GEP intelligent accounting system.

[0088] Step 5: Data output and traceability.

[0089] Step 5.1: Output to GEP intelligent accounting system.

[0090] Standardized raster datasets are pushed to the data warehouse of the GEP intelligent accounting system via API interface or direct database connection, so that they can be called and calculated by the subsequent ecological product value assessment model.

[0091] Step 5.2: Generate a full-process traceability report.

[0092] The system automatically summarizes the execution logs and intermediate results of each step, including a list of data sources, parameters of each preprocessing operation, configuration of spatiotemporal alignment algorithm, standardized mapping rules, quality inspection statistics, and anomaly handling records, forming a structured, end-to-end data processing traceability report to ensure that the entire processing chain is transparent and auditable.

[0093] Step 5.3: Regularly update the mechanism.

[0094] The system supports automatically detecting the arrival of new data at preset cycles (such as annually or quarterly), triggering an incremental update process, and only processing newly added or changed data layers to maintain the continuous updating and timeliness of standardized datasets.

[0095] This invention employs a differential privacy sandbox to ensure secure access to classified data, uses ecological weight factor-driven spatiotemporal alignment to guarantee semantic consistency of multi-source data, and uses total quantity-preserving downscaling to mathematically ensure the accuracy of decomposition results and policy usability. These three elements work synergistically to form a complete, high-precision, traceable, compliant, and secure standardized processing system for multi-source heterogeneous ecological data, solving a long-standing technical problem that has remained unsolved in this field.

[0096] The above combination Figure 1 The spatiotemporal alignment and raster standardization method for multi-source heterogeneous ecological data provided in the embodiments of the present invention has been described in detail. Next, the spatiotemporal alignment and raster standardization system for multi-source heterogeneous ecological data provided in the embodiments of the present invention will be described in conjunction with the accompanying drawings.

[0097] Figure 3 This is a schematic diagram of the structure of a multi-source heterogeneous ecological data spatiotemporal alignment and raster standardization system shown in an embodiment of the present invention, with reference to... Figure 3 The system described in this invention includes: The data acquisition module is configured to acquire rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be calculated, wherein the ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. The sandbox desensitization module is configured to: load classified ecological monitoring raster data in an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. The data preprocessing module is configured to preprocess remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data. The spatiotemporal alignment module is configured to perform spatial and temporal alignment on the preprocessed data, so that all data have a unified spatial raster reference and temporal reference. The spatial alignment includes: calculating the ecological weight factor of each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data and economic and social statistical raster data in the area to be calculated; and decomposing the total index value of the area to be calculated to each raster cell according to the sum of the weight factors of all raster cells, so as to obtain the decomposed index value of each raster cell for the calculation of GEP.

[0098] According to embodiments of the present invention, the spatiotemporal alignment and raster normalization system for multi-source heterogeneous ecological data can correspond to the execution of the methods described in the embodiments of the present invention, and the above-mentioned and other operations and / or functions of each module of the spatiotemporal alignment and raster normalization system for multi-source heterogeneous ecological data are respectively for implementing Figure 1 , Figure 2 For the sake of brevity, the corresponding processes of each method in the code will not be elaborated here.

[0099] See Figure 4 The diagram shows the structure of a computer device, which includes a processor, a communication interface, and a computer-readable storage medium. The processor, communication interface, and computer-readable storage medium are connected via a bus or other means. The communication interface is used to receive and send data. The computer-readable storage medium can be stored in the computer device's memory. The computer-readable storage medium stores computer programs, including program instructions, and the processor executes the program instructions stored in the computer-readable storage medium. The processor (or CPU, Central Processing Unit) is the computing and control core of the computer device, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve the corresponding steps in the embodiment of the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data.

[0100] This embodiment provides a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the processing system of the computer device.

[0101] Furthermore, this storage space also contains one or more instructions suitable for loading and execution by the processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM memory or non-volatile memory, such as at least one disk storage device; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0102] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes one or more instructions stored in the computer-readable storage medium to implement the corresponding steps in the above-described embodiment of the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data.

[0103] This embodiment provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the corresponding steps in the above-described embodiment of the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data.

[0104] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0105] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0108] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0109] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data, characterized in that, include: Obtain rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be accounted for. The ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. Load classified ecological monitoring raster data into an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. Preprocessing is performed on remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data; Spatial and temporal alignment are performed on the preprocessed data to ensure that all data have a unified spatial raster reference and temporal reference. The spatial alignment includes: calculating the ecological weight factor for each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data, and economic and social statistical raster data in the area to be calculated; decomposing the total index value of the area to be calculated to each raster cell according to the sum of the weight factors of all raster cells, obtaining the decomposed index value of each raster cell, which is used for GEP calculation; the ecological weight factor for each raster cell is calculated using the following formula: in, This represents the ecological weight factor for each raster cell; Represents the land use type coefficient within a raster cell; Indicates the vegetation cover within a raster cell; This represents the relative population density within a raster cell; , , Represents configurable weight coefficients, satisfying ; Calculate the sum of weight factors for all raster cells within the administrative region: The process of decomposing the total index value of the area to be calculated into each raster cell to obtain the decomposed index value of each raster cell is carried out using the following formula: in, This represents the index value after decomposition of each raster cell; It represents the total value of a certain economic statistical indicator within the region to be calculated; This represents the ecological weight factor for each raster cell; This represents the sum of the weight factors for all raster cells; The above formula leads to the following: That is, the sum of all raster decomposition values ​​equals .

2. The method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data according to claim 1, characterized in that, The publicly disclosed raster value is calculated using the following formula: in, Indicates the public raster value; This indicates the raster occupancy rate of classified elements within each raster cell. Indicates query sensitivity; Indicates privacy budget; This represents Laplace distribution noise.

3. The method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data according to claim 1, characterized in that, The preprocessing includes: detecting outliers using box plots and the 3σ criterion, and then correcting them using linear interpolation / Kriging interpolation; completing missing data and deleting redundant data; and standardizing the data before GEP calculation.

4. The method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data according to claim 1, characterized in that, A quality traceability report is also generated during the preprocessing process; the classified ecological monitoring grid data does not leave the sandbox environment.

5. A spatiotemporal alignment and raster standardization system for multi-source heterogeneous ecological data, characterized in that, include: The data acquisition module is configured to acquire rasterized remote sensing raster data, ecological monitoring raster data, and economic and social statistical raster data of the area to be calculated, wherein the ecological monitoring raster data includes non-classified ecological monitoring raster data and classified ecological monitoring raster data. The sandbox desensitization module is configured to: load classified ecological monitoring raster data in an independent sandbox environment, convert it into raster occupancy data at the target raster resolution, calculate the raster occupancy of classified elements in each raster cell, add random noise, generate public raster values, and then output only the secure classified ecological monitoring raster data after noise perturbation. The data preprocessing module is configured to preprocess remote sensing raster data, non-classified ecological monitoring raster data, secure and classified ecological monitoring raster data, and economic and social statistical raster data. The spatiotemporal alignment module is configured to perform spatial and temporal alignment on the preprocessed data, so that all data have a unified spatial raster reference and temporal reference. The spatial alignment includes: calculating the ecological weight factor for each raster cell based on remote sensing raster data, non-classified ecological monitoring raster data / security-classified ecological monitoring raster data, and economic and social statistical raster data in the area to be calculated; decomposing the total index value of the area to be calculated to each raster cell according to the sum of the weight factors of all raster cells, obtaining the decomposed index value of each raster cell, which is used for GEP calculation; the ecological weight factor for each raster cell is calculated using the following formula: in, This represents the ecological weight factor for each raster cell; Represents the land use type coefficient within a raster cell; Indicates the vegetation cover within a raster cell; This represents the relative population density within a raster cell; , , Represents configurable weight coefficients, satisfying ; Calculate the sum of weight factors for all raster cells within the administrative region: The process of decomposing the total index value of the area to be calculated into each raster cell to obtain the decomposed index value of each raster cell is carried out using the following formula: in, This represents the index value after decomposition of each raster cell; It represents the total value of a certain economic statistical indicator within the region to be calculated; This represents the ecological weight factor for each raster cell; This represents the sum of the weight factors for all raster cells; The above formula leads to the following: That is, the sum of all raster decomposition values ​​equals .

6. A computer device, characterized in that, A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the steps in the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and execute the steps in the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data as described in any one of claims 1-4.

8. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps in the method for spatiotemporal alignment and raster standardization of multi-source heterogeneous ecological data as described in any one of claims 1-4.

Images