A Geographic Information Multi-Source Data Fusion Processing Method for Ecological Impact Assessment

Abstract

This invention belongs to the field of geographic information science and data processing technology, and discloses a method for multi-source geographic information data fusion processing for ecological impact assessment. The method includes the following steps: acquiring basic land use data and the latest multi-source geographic information data; converting the format and correcting the coordinates of the basic land use data; fusing and overlaying the multi-source data to construct vegetation type data and ecosystem type data, thus improving the basic land use data; updating administrative division information to obtain the final basic land use data; determining the vegetation cover level; and generating a land use status map, vegetation type map, ecosystem map, and vegetation cover map. This invention enables in-depth mining and efficient utilization of multi-source geographic data.

Description

Technical Field

[0001] This invention belongs to the field of geographic information science and data processing technology, specifically relating to a method for multi-source geographic information data fusion processing for ecological impact assessment. Background Technology

[0002] In the current era of rapid development in geographic information science, the acquisition of multi-source geographic data is becoming increasingly convenient, but data processing and analysis face severe challenges. While the National Second National Land Use Survey (NPT) data, as an important foundational data source for land use, is authoritative, its MDB format storage results in poor compatibility with mainstream GIS software. Furthermore, its early collection date leads to discrepancies with actual land use conditions, and its coordinate system is inconsistent with the latest remote sensing imagery, causing difficulties in data fusion. In addition, differences between the administrative divisions in the NPT data and the latest administrative divisions affect the accuracy of statistical and analytical data. Regarding data fusion, traditional methods struggle to effectively integrate land use raster and vector data of different resolutions and time periods, resulting in insufficient accuracy in constructed vegetation and ecosystem type data. Moreover, in the output stage, existing mapping templates lack intelligence and cannot automatically adjust mapping elements according to the data range, failing to meet diverse analytical needs. Therefore, a multi-source geographic information data fusion processing method is needed to address these issues. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention proposes a multi-source geographic information data fusion processing method for ecological impact assessment, aiming to solve the complex challenges of multi-source data processing in the geographic information field and achieve in-depth mining and efficient utilization of geographic data.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a method for multi-source geographic information data fusion processing for ecological impact assessment, comprising the following steps:

[0005] Step 1: Obtain basic land use data and the latest multi-source geographic information data, including road network data, water system data, remote sensing satellite imagery data, and administrative division data;

[0006] Step 2: Perform format conversion and coordinate correction on the basic land use data to obtain the first basic land use data;

[0007] Step 3: Integrate and overlay the road network data, water system data, and the first land use basic data to obtain the second land use basic data; construct vegetation type raster data based on the spectral and texture features of the remote sensing satellite image data; obtain ecosystem type data based on the vegetation type raster data and the second land use basic data; and improve the attribute table of the second land use basic data based on the vegetation type raster data and the ecosystem type data to obtain the third land use basic data.

[0008] Step 4: Update the administrative division information in the basic land use data based on the administrative division data to obtain the fourth basic land use data;

[0009] Step 5: Calculate the vegetation cover of each pixel within the area of ​​interest based on the remote sensing image, and determine the vegetation cover level attribute of each pixel according to the set threshold. The formula for calculating vegetation cover is:

[0010] ;

[0011] in, FVC This represents the vegetation cover of a pixel. NDVI Represents the normalized vegetation index of a pixel. NDVI soil and NDVI veg These represent the normalized vegetation index of pure soil pixels and pure vegetation pixels within the area of ​​interest, respectively.

[0012] Step Six: Use the land use data, vegetation type data, ecosystem type data, and vegetation coverage level data of the area of ​​interest from the fourth land use basic data to generate a land use status map, vegetation type map, ecosystem map, and vegetation coverage map.

[0013] In step two, the specific method for coordinate correction of land use basic data is as follows: select multiple feature points in the land use basic data, obtain the coordinates of the corresponding points in the remote sensing satellite image data, use the least squares method to fit and solve the affine transformation matrix, and perform coordinate correction of the land use basic data based on the affine transformation matrix.

[0014] In step three, vegetation type data is constructed using a decision tree classification algorithm.

[0015] In step three, the specific method for constructing vegetation type data using the decision tree classification algorithm is as follows:

[0016] First, spectral and texture features are extracted from remote sensing satellite imagery data as input features;

[0017] Then, a decision tree is generated by recursively partitioning the dataset; classification rules are generated from the decision tree to obtain the vegetation type of each region.

[0018] In step three, the decision tree classification algorithm selects the optimal splitting feature based on maximizing information gain. The formula for calculating information gain is:

[0019] ;

[0020] in, IG(D,A) Indicating splitting characteristics A The information gain, where D represents the number of samples in the dataset. Indicates the value to be v subset of D v Medium sample size; H(D) Represents the entropy of the dataset. H(D v ) Representing a subset D v The entropy of the dataset; the formula for calculating the entropy of the dataset is:

[0021] ;

[0022] in, p i Represents the first in the dataset i The proportion of class samples;

[0023] In step three, the decision tree classification algorithm selects the optimal splitting feature based on minimizing Gini impurity, where the formula for calculating Gini impurity is:

[0024] ;

[0025] in, This represents the Gini impurity of the dataset. p i Represents the first in the dataset i The proportion of samples of different classes, where n represents the number of sample types in the dataset.

[0026] In step five, thresholds are set for five different levels of vegetation coverage: high vegetation coverage, medium-high vegetation coverage, medium vegetation coverage, medium-low vegetation coverage, and low vegetation coverage. Based on the set thresholds, the vegetation coverage level attribute of each pixel is obtained, which is the vegetation coverage level data.

[0027] Step five also includes the process of calculating 10-meter NDVI data based on remote sensing images. When calculating vegetation cover, the 10-meter NDVI data is used as the normalized vegetation index value of the pixel.

[0028] Step six also includes creating mapping templates for land use status maps, vegetation type maps, ecosystem type maps, and vegetation cover maps, wherein different colors are used to map different types of data in the mapping templates.

[0029] Step six also includes the following steps: calculating the area of ​​each type of land use, vegetation, ecosystem, and vegetation coverage level within the area of ​​interest, and generating a statistical table.

[0030] Compared with existing technologies, this invention has the following advantages: This invention proposes a multi-source geographic information data fusion processing method for ecological impact assessment. First, it performs lossless transformation on basic land use data. Then, it updates and supplements the basic land use data through steps such as coordinate correction, data fusion, and administrative division unification. Combined with vegetation cover calculation, it achieves intelligent mapping of various land information such as vegetation cover through mapping templates. This invention achieves in-depth mining and efficient utilization of multi-source geographic information data by efficiently processing multi-source geographic information data and organically integrating it with basic land use data. It provides a systematic and integrated solution for applications in the field of geographic information and can be widely applied in multiple fields such as ecological environment assessment, land planning, and environmental monitoring. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating a multi-source geographic information data fusion processing method for ecological impact assessment provided in an embodiment of the present invention.

[0032] Figure 2 This is a schematic diagram of data flow in an embodiment of the present invention;

[0033] Figure 3 This is a land use status map generated in an embodiment of the present invention;

[0034] Figure 4 This is a vegetation type map generated in an embodiment of the present invention;

[0035] Figure 5 This is an ecological type diagram generated in an embodiment of the present invention;

[0036] Figure 6 This is a vegetation cover map generated in an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] like Figures 1-2 As shown in the figure, this embodiment of the invention provides a method for multi-source geographic information data fusion processing for ecological impact assessment, including the following steps:

[0039] Step 1: Data preparation.

[0040] Acquire basic land use data and the latest multi-source geographic information data, including road network data, water system data, remote sensing satellite imagery data, and administrative division data.

[0041] Specifically, in this embodiment, the land use basic data is the national second land survey data stored in MDB format. The road network data, water system data, remote sensing satellite imagery data, and administrative division data are the latest data collected in 2024. During the collection process, data with high spatial and temporal resolution accuracy were selected to ensure the accuracy and applicability of the data.

[0042] Step 2: Data processing.

[0043] The format of the land use data table in the land use basic data is converted; then, multiple feature points are selected in the land use basic data, and the coordinates of the corresponding points are obtained in the remote sensing satellite image data. The affine transformation matrix is ​​solved by fitting using the least squares method. The coordinates of the land use basic data are corrected according to the affine transformation matrix to obtain the first land use basic data.

[0044] In this embodiment, the powerful data conversion capabilities of the GDAL (Geospatial Data Abstraction Library) are utilized to write a Python script to convert the land use data table in the basic land use data format. During the conversion process, the spatial data interoperability specifications defined by the OGC (Open Geospatial Consortium) are strictly followed to ensure accurate geometric conversion of the data while guaranteeing the integrity and correctness of attribute fields. Through logging and error capture mechanisms during the conversion process, potential problems are promptly identified and resolved, achieving lossless conversion of the MDB format land use data table to the SHP format, ensuring the geometric accuracy and attribute integrity of the data.

[0045] Specifically, the formula for coordinate correction is as follows:

[0046] ; (1)

[0047] Where (x,y) are the coordinates in the original land use basic data, and (x',y') are the corrected coordinates. a,b,c,d, e,f These are the parameters of the affine transformation matrix. The optimal parameters are determined by minimizing the sum of squared residuals between the actual feature point coordinates and the transformed coordinates.

[0048] Therefore, in this embodiment, based on the principle of affine transformation, multiple evenly distributed feature points are selected in the land use basic data, and the coordinates of the corresponding feature points are obtained in the remote sensing image through ground control points (GCPs). The coordinate correspondence between the feature points in the land use basic data and the remote sensing image is fitted using the least squares method, the affine transformation matrix parameters are solved, and then substituted into formula (1) to perform coordinate correction on the original land use basic data, thereby obtaining the first land use basic data and ensuring the consistency between the location of the land use basic data and the remote sensing image.

[0049] Specifically, in this embodiment, the GDAL and Fiona libraries of Python are used in conjunction with the NumPy numerical computing library to automate the entire process of feature point selection, coordinate matching, parameter calculation and data correction.

[0050] Step 3: Data update.

[0051] By integrating and overlaying road network data, water system data, and the first land use basic data, the first land use basic data is updated and supplemented to obtain the second land use basic data. Using the spectral and texture features of remote sensing satellite imagery data, vegetation type raster data is constructed. Based on the vegetation type raster data and the second land use basic data, ecosystem type data is obtained. Based on the vegetation type raster data and the ecosystem type data, the attribute table of the second land use basic data is improved to obtain the third land use basic data.

[0052] Specifically, in this embodiment, vegetation types are categorized into evergreen coniferous forests, evergreen broad-leaved forests, grasslands, cultivated vegetation, and no vegetation. By using the spectral and textural features of remote sensing satellite imagery data, vegetation types can be identified to obtain vegetation type raster data. In addition, ecosystem types include broad-leaved forest ecosystems, coniferous forest ecosystems, grassland ecosystems, lake ecosystems, cultivated land ecosystems, orchard ecosystems, residential ecosystems, and bare land ecosystems. After obtaining the vegetation type raster data, it is compared with the second land use basic data to obtain the ecosystem type of each region, thereby obtaining ecosystem type data.

[0053] Specifically, by integrating and overlaying the primary land use basic data with the latest road network and water system data, the primary land use basic data can be supplemented and updated.

[0054] Specifically, in step three, vegetation type data is constructed using a decision tree classification algorithm.

[0055] In step three, the specific method for constructing vegetation type data using the decision tree classification algorithm is as follows:

[0056] First, spectral features (such as NDVI and NDWI) and texture features are extracted from remote sensing satellite image data as input features;

[0057] Then, a decision tree is generated by recursively partitioning the dataset. In the decision tree, each node represents a feature, each branch represents a decision rule, and the leaf nodes represent the final classification result. The recursive process continues until a stopping condition is met (such as reaching the maximum depth or the number of samples per node being less than a threshold). To prevent overfitting, the generated decision tree can be pruned, removing unimportant branches. Classification rules are generated from the decision tree to obtain the vegetation types for each region, resulting in vegetation type raster data.

[0058] After obtaining the vegetation type raster data, combined with the second land use basic data, the ecosystem type data can be obtained. Then, using the attribute table editing function of ArcGIS software, the vegetation type raster data and ecosystem type data can be added to the attribute table of the second land use basic data to improve the data attribute table and ensure the integrity and accuracy of the data.

[0059] Specifically, in step three, the decision tree classification algorithm selects the optimal splitting feature based on maximizing information gain, where the formula for calculating information gain is:

[0060] ; (2)

[0061] in, IG(D,A) Indicating splitting characteristics A The information gain, where D represents the number of samples in the dataset. H(D) Represents the entropy of the dataset. Indicates the value to be v subset of D v Medium sample size H(D v ) Representing a subset D v The entropy of the dataset; the formula for calculating the entropy of the dataset is:

[0062] ; (3)

[0063] in, p i Represents the first in the dataset i The proportion of class samples;

[0064] Furthermore, in step three, the decision tree classification algorithm can also select the optimal splitting feature based on minimizing Gini impurity, where the formula for calculating Gini impurity is:

[0065] ; (4)

[0066] in, This represents the Gini impurity of the dataset. p i Represents the first in the dataset i The proportion of samples of different classes, where n represents the number of sample types in the dataset.

[0067] Information gain measures the degree to which a feature reduces the uncertainty of a dataset, while Gini impurity reflects the impurity of the dataset. In this embodiment, selecting the splitting feature with the maximum information gain or the minimum Gini impurity as the optimal splitting feature for the decision tree classification algorithm can effectively improve the accuracy of vegetation type classification.

[0068] Step 4: Update the administrative division information in the third land use basic data according to the administrative division data to obtain the fourth land use basic data.

[0069] In this embodiment, spatial topology analysis and attribute matching algorithms are used in ArcGIS software. The spatial join tool is used to associate the county-level administrative divisions in the basic land use data with the latest administrative divisions. Based on attributes such as administrative division codes and names, and combined with topological relationships (such as intersection and containment), the administrative division information in the third basic land use data is updated to obtain the fourth basic land use data, ensuring data consistency and timeliness.

[0070] Step 5: Calculate the vegetation cover of each pixel within the area of ​​interest based on the remote sensing image, and determine the vegetation cover level attribute of each pixel according to a set threshold. The formula for calculating the vegetation cover is as follows:

[0071] (5)

[0072] in, FVC Indicates vegetation coverage. NDVI Represents the normalized vegetation index of a pixel. NDVI soil and NDVI vegThese represent the normalized vegetation index (NDI) of pure soil pixels and pure vegetation pixels in the region of interest, respectively. In this embodiment, the NDI of each pixel is calculated using the NDI of pure soil pixels and pure vegetation pixels in the region of interest. NDVI Normalization yields vegetation cover that more significantly reflects the differences in vegetation cover across individual pixels.

[0073] Specifically, in this embodiment, the 10-meter NDVI data of the remote sensing image is first calculated, and then the vegetation cover is calculated using the 10-meter NDVI data. Considering the influence of factors such as topography and atmosphere on the NDVI data, preprocessing methods such as atmospheric correction and topographic correction are used to process the remote sensing image before calculating the normalized vegetation index for each pixel to improve the accuracy of the NDVI data. The NDVI calculation formula is as follows:

[0074] (6)

[0075] in, NIR Represents the reflectivity in the near-infrared band. Red This indicates the reflectivity in the red light band.

[0076] Specifically, in step five, thresholds for five different levels of vegetation coverage are set: high vegetation coverage, medium-high vegetation coverage, medium vegetation coverage, medium-low vegetation coverage, and low vegetation coverage. Based on the set thresholds, the vegetation coverage level attribute of each pixel is obtained, which is the vegetation coverage level data.

[0077] Step Six: Retrieve land use data, vegetation type data, ecosystem type data, and vegetation cover level data from the fourth land use basic data for the area of ​​interest to generate a land use status map, vegetation type map, ecosystem map, and vegetation cover map, such as... Figures 3-6 As shown.

[0078] Step six further includes creating mapping templates for land use status maps, vegetation type maps, ecosystem type maps, and vegetation cover maps. These templates use different colors to map different types of data and add Chinese character type information to improve map readability. The mapping templates also have a dynamic update function, automatically adjusting the display style and position of the title, north arrow, scale bar, and latitude / longitude grid according to the regional data range.

[0079] Specifically, in this embodiment, the project scope and buffer are drawn using Python libraries such as Matplotlib and Basemap. Coordinate transformation tools are used to verify and transform the coordinates, ensuring consistency with the land use data coordinates. The regional data is overlaid with administrative division data to obtain the specific district / county names, and the corresponding land use, vegetation type, and ecosystem type data are retrieved based on these names.

[0080] Step six further includes the following steps: calculating the area of ​​each type of land use, vegetation, ecosystem, and vegetation cover level within the area of ​​interest, and generating a statistical table. Specifically, the area calculation tool in ArcGIS software can be used in conjunction with the Pandas library in Python for data processing to calculate the area of ​​each type of land use, vegetation type, ecosystem type, and vegetation cover within the area, and generate a statistical table to provide data support for subsequent analysis.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for multi-source geographic information data fusion processing for ecological impact assessment, characterized in that, The following steps are involved: Step 1: Obtain basic land use data and the latest multi-source geographic information data, including road network data, water system data, remote sensing satellite imagery data, and administrative division data; Step 2: Perform format conversion and coordinate correction on the basic land use data to obtain the first basic land use data; Step 3: Integrate and overlay the road network data, water system data, and the first land use basic data to obtain the second land use basic data; construct vegetation type raster data based on the spectral and texture features of the remote sensing satellite image data; obtain ecosystem type data based on the vegetation type raster data and the second land use basic data; and improve the attribute table of the second land use basic data based on the vegetation type raster data and the ecosystem type data to obtain the third land use basic data. Step 4: Update the administrative division information in the third land use basic data according to the administrative division data to obtain the fourth land use basic data; Step 5: Calculate the vegetation cover of each pixel within the area of ​​interest based on the remote sensing image, and determine the vegetation cover level attribute of each pixel according to the set threshold. The formula for calculating vegetation cover is: ； in, FVC This represents the vegetation cover of a pixel. NDVI Represents the normalized vegetation index of a pixel. NDVI soil and NDVI veg These represent the normalized vegetation index of pure soil pixels and pure vegetation pixels within the area of ​​interest, respectively. Step Six: Call the land use data, vegetation type data, ecosystem type data, and vegetation cover level data of the area of ​​interest from the fourth land use basic data to generate a land use status map, vegetation type map, ecosystem map, and vegetation cover map; The specific method for coordinate correction of the land use basic data in Step Two is as follows: select multiple feature points in the land use basic data, obtain the coordinates of the corresponding points in the remote sensing satellite image data, use the least squares method to fit and solve the affine transformation matrix, and perform coordinate correction of the land use basic data based on the affine transformation matrix.

2. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 1, characterized in that, In step three, vegetation type raster data is constructed using a decision tree classification algorithm.

3. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 2, characterized in that, In step three, the specific method for constructing vegetation type raster data using the decision tree classification algorithm is as follows: First, spectral and texture features are extracted from remote sensing satellite imagery data as input features; Then, a decision tree is generated by recursively partitioning the dataset; classification rules are generated from the decision tree to obtain the vegetation type of each region.

4. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 2, characterized in that, In step three, the decision tree classification algorithm selects the optimal splitting feature based on maximizing information gain. The formula for calculating information gain is: ； in, IG(D,A) Indicating splitting characteristics A The information gain, where D represents the number of samples in the dataset. H(D) Represents the entropy of the dataset. Indicates the value to be v subset of D v Medium sample size H(D v ) Representing a subset D v The entropy of the dataset; the formula for calculating the entropy of the dataset is: ； in, p i Represents the first in the dataset i The proportion of samples of different classes, where n represents the number of sample types in the dataset.

5. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 2, characterized in that, In step three, the decision tree classification algorithm selects the optimal splitting feature based on minimizing Gini impurity, where the formula for calculating Gini impurity is: ； in, This represents the Gini impurity of the dataset. p i Represents the first in the dataset i The proportion of samples of different classes, where n represents the number of sample types in the dataset.

6. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 1, characterized in that, In step five, thresholds are set for five different levels of vegetation coverage: high vegetation coverage, medium-high vegetation coverage, medium vegetation coverage, medium-low vegetation coverage, and low vegetation coverage. Based on the set thresholds, the vegetation coverage level attribute of each pixel is obtained, which is the vegetation coverage level data.

7. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 1, characterized in that, Step five also includes the step of calculating 10-meter NDVI data based on remote sensing images. When calculating vegetation cover, the 10-meter NDVI data is used as the normalized vegetation index value of the pixel.

8. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 1, characterized in that, Step six also includes creating mapping templates for land use status maps, vegetation type maps, ecosystem type maps, and vegetation cover maps, wherein different colors are used to map different types of data in the mapping templates.

9. The method for multi-source geographic information data fusion processing for ecological impact assessment according to claim 1, characterized in that, Step six also includes the following steps: calculating the area of ​​each type of land use, vegetation, ecosystem, and vegetation coverage level within the area of ​​interest, and generating a statistical table.

Images