Power transmission and transformation project ecological influence space-time boundary determination method and system based on multi-source remote sensing information deep fusion interpretation

Abstract

The invention provides a power transmission and transformation project ecological influence space-time boundary determination method and system based on multi-source remote sensing information deep fusion interpretation, and belongs to the technical field of power transmission and transformation project management. The method comprises the steps of data acquisition, data preprocessing and multi-source data integration, multi-scale space-time analysis, ecological influence index construction, remote sensing ecological index model construction, ecological influence space-time boundary determination, dynamic monitoring and early warning system platform establishment and long-term monitoring and evaluation. By integrating satellite remote sensing, unmanned aerial vehicle aerial photography and ground monitoring data and combining an image fusion algorithm, a principal component analysis method and a random forest algorithm technology, the method is beneficial to promoting accurate evaluation of the influence of the power transmission and transformation project on the ecological environment, visualizes the space-time boundary of the ecological influence, breaks through the limitation of a traditional evaluation method on time and space coverage, and improves the evaluation efficiency of the power transmission and transformation project. And a scientific method system for analyzing and evaluating the ecological influence of the power transmission and transformation project is further improved.

Description

Technical Field

[0001] The present invention relates to a method and system for determining the spatiotemporal boundary of the ecological impact of a power transmission and transformation project based on deep fusion interpretation of multi-source remote sensing information, and belongs to the technical field of power transmission and transformation project management. Background Art

[0002] As global energy demand continues to grow, power transmission and transformation projects, as an indispensable part of the power supply system, play a key role in ensuring energy supply. However, during the construction and operation of power transmission and transformation projects, factors such as electromagnetic radiation, vegetation destruction, and soil erosion will have a variety of adverse effects on the surrounding ecological environment. For example, electromagnetic radiation may affect biological growth and reproduction; the construction of transmission lines requires the felling of trees, which will affect vegetation coverage and biodiversity, and vegetation destruction may also lead to soil erosion and soil erosion; excavation activities during construction will affect soil structure and fertility, and construction activities may also cause noise pollution. These problems have made the ecological and environmental impact of power transmission and transformation projects increasingly apparent, and gradually become a matter of public concern.

[0003] At present, the traditional environmental protection practice of assessing the impact of power transmission and transformation projects on the ecological environment mainly relies on ground surveys and limited remote sensing data. However, these methods have obvious limitations. First, in terms of coverage, ground surveys are difficult to fully cover a large area, and although remote sensing data can cover a large area, it is limited by data resolution and difficulty in acquisition, and often cannot provide sufficiently detailed information. Secondly, in terms of frequency, ground surveys can usually only conduct regular monitoring and cannot reflect changes in the ecological environment in real time; and the update frequency of remote sensing data is also limited by the flight plan and data processing capabilities of satellites or drones. Finally, in terms of accuracy, although ground surveys can provide relatively accurate data, they are often limited by manpower and material costs and cannot perform high-precision monitoring over a large area; and although remote sensing data can provide information over a large area, they are limited by data quality and interpretation technology, and often have errors and uncertainties.

[0004] In addition, the lack of multi-factor data integration is also a major bottleneck of current assessment technology. Data from different sources differ in format, resolution and time scale, resulting in incomplete information acquisition, lack of systematic analysis results, and difficulty in accurately assessing the overall impact of power transmission and transformation projects on the ecological environment. At the same time, the ability to share, integrate and apply ecological and environmental monitoring data is insufficient, and there is a lack of unified planning and construction between different monitoring systems, resulting in scattered resources and inefficiency.

[0005] Therefore, it is particularly urgent to develop a method that can comprehensively, accurately and efficiently evaluate the impact of power transmission and transformation projects on the ecological environment. It is necessary to integrate data from different remote sensing information sources to achieve comprehensive monitoring and analysis of changes in the ecological environment during the construction and operation of power transmission and transformation projects. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for determining the spatiotemporal boundaries of the ecological impact of power transmission and transformation projects based on the deep fusion and interpretation of multi-source remote sensing information, which can accurately define the spatiotemporal boundaries of the impact of power transmission and transformation projects on the ecological environment, provide a comprehensive, multi-angle monitoring perspective for environmental protection, and provide more effective decision-making support.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions: A method for determining the spatiotemporal boundary of ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information includes the following steps: Through geographic information system software, the planning scheme of the power transmission and transformation project is determined, including the specific geographical scope, time period, line direction and site location, and the ecological and environmental areas that may be involved in the project are identified, and the data types that need to be collected and the key ecological factors to be monitored are clarified.

[0008] According to the planning scheme, multi-source data from the space segment, the sky segment, and the surface segment are collected, and the collected data are pre-processed and integrated using data processing tools to build an air-space-ground multi-source remote sensing information differentiated storage database.

[0009] Through the multi-source remote sensing data set of the air-space-ground multi-source remote sensing information differentiation storage database, spatiotemporal analysis is carried out to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all aspects, local areas and spatial units.

[0010] According to the characteristics of power transmission and transformation projects and regional ecosystems, key ecological indicators are extracted from the database, and integrated analysis is carried out to construct an ecological impact indicator system.

[0011] Through the constructed ecological impact indicator system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into the RSEI value, and the impact of power transmission and transformation projects on the ecological environment is quantified according to the RSEI value.

[0012] The RSEI values ​​are visualized through geographic information system software to determine the spatiotemporal boundaries of the ecological impact of power transmission and transformation projects and identify the key affected areas.

[0013] Preferably, the data types of the multi-source data include satellite remote sensing data in the space segment, drone monitoring data in the sky segment, and ground monitoring station data in the surface segment; the data collection method is as follows: Space segment satellite remote sensing data: Remote sensing data is regularly received into the database through satellite data receiving equipment or satellite data center platform, including optical images, radar data, thermal imaging data, and multispectral data, which are obtained through data subscription or direct purchase of services.

[0014] Sky segment drone monitoring data: obtain aerial monitoring data of designated areas through drone platforms, including videos, thermal images and high-resolution images.

[0015] Surface ground monitoring station data: Meteorological stations, water quality monitoring stations and environmental sensors are deployed in designated areas to collect temperature, humidity, precipitation and water quality environmental parameters, and the data are transmitted to the database using wireless communication technology.

[0016] Preferably, the preprocessing and integration methods include format conversion, geo-referencing, image processing, image fusion, and multi-source data integration.

[0017] Format conversion: Use data processing tools to read multi-source remote sensing data, extract source coordinate information, determine the coordinate reference system of each data set, convert multi-source format data into a universal geographic information system format, and convert to the WGS84 coordinate system.

[0018] Georeferencing: Georeferencing is performed through GDAL to align multi-source data to the same coordinate system.

[0019] Image processing: Use the open source computer vision library platform to process images, select the reference image, correct the multi-source remote sensing data to the reference image through control points, and use the camera calibration and distortion correction algorithm on the OpenCV platform to correct the geometric distortion of satellite images and aerial images to eliminate image geometric distortion.

[0020] Image fusion: Use the image fusion algorithm in the OpenCV platform to fuse data from different sources and resolutions into a single high-resolution data set; fuse low-resolution multispectral images with high-resolution panchromatic images to generate high-resolution images.

[0021] Multi-source data integration: Integrate the fused remote sensing data with related data to build an air-space-ground multi-source remote sensing information differentiated storage database.

[0022] Preferably, the spatiotemporal analysis of the multi-source remote sensing data set in the air-space-ground multi-source remote sensing information differentiated storage database includes macroscopic, mesoscopic and microscopic scales.

[0023] Macro scale: Use GIS software to analyze the trends of vegetation coverage, land use, biomass, and surface temperature within the entire impact area, use time series data to evaluate regional environmental changes, and determine the overall trend of the ecological impact of the power transmission and transformation project on the entire region; predict the annual trend changes in vegetation coverage, land use, and biomass during the construction and operation of the power transmission and transformation project; Mesoscale: Apply cluster analysis methods to analyze vegetation coverage, land use changes, ecosystem types, and water resource distribution in a local area within a specific period; use silhouette coefficients to determine the optimal number of clusters and combine clustering results with geographic information systems; compare clustering results in different time periods to analyze the changing trends of vegetation coverage and land use changes; Micro scale: extract high-resolution remote sensing data from the database and combine it with field survey data to conduct field sampling and analysis of ecological data, verify remote sensing analysis results, and analyze changes in the ecological environment in local areas; collect soil samples at different stages of the project, analyze soil characteristics such as pH value, organic matter content, and heavy metal content, and use remote sensing images to analyze soil moisture and temperature changes; analyze vegetation growth and coverage through sampling methods and remote sensing images; install cameras to capture wildlife activities and record the frequency and distribution of wildlife in a specific period of time; use statistical software to conduct statistical analysis on the collected data, and evaluate the relationship between ecological indicators through regression analysis methods; use geographic information system tools to draw distribution maps of ecological changes, identify hot spots, and visualize changes in various indicators.

[0024] Preferably, the key ecological indicators include vegetation greenness, soil moisture, drought index, and surface temperature.

[0025] Preferably, the steps for constructing the remote sensing ecosystem index model are as follows: The vegetation greenness, soil moisture, drought index, and surface temperature indicators are normalized. The Min-Max normalization method is used to convert each indicator to a unified scale of [0,1] and synthesize a new layer as the basic data of the RSEI model.

[0026] The normalized index layer is processed by the PCA method to generate the principal component; the RSEI value is calculated by the first principal component.

[0027] Ecological impact indicators and ground environmental monitoring data were used to train the model and analyze the ecological change trends at different time points. The remote sensing data were classified and change detected using the random forest algorithm to verify the accuracy of the RSEI model, and the cross-validation method was used to improve the accuracy of the model output values.

[0028] The variance decomposition method was used to conduct sensitivity analysis to determine the contribution of each indicator to the RSEI value.

[0029] Preferably, the normalization formula is as follows: , In the formula, is the normalized value, is the original value, is the minimum value of the indicator, is the maximum value of the indicator.

[0030] The RSEI value is calculated by the first principal component as follows: The normalized index layer was imported into GIS software, and PCA analysis was performed using spatial analysis tools. Normalization is performed to generate RSEI. The specific formula is as follows: , in, is the minimum value of the first principal component, is the maximum value of the first principal component.

[0031] Preferably, the impact of power transmission and transformation projects on the ecological environment is quantified according to the RSEI value as follows: the impact degree is divided into severe impact, relatively severe impact, moderate impact, slight impact, and relatively slight impact according to the RSEI value, and the corresponding RSEI value range is: severe impact [0.0-0.2) , relatively severe impact [0.2-0.4) , moderate impact [0.4-0.6) , slight impact [0.6-0.8) , and relatively slight impact [0.8-1.0].

[0032] Preferably, it also includes establishing a regular monitoring and automatic early warning system platform, regularly acquiring new satellite images, drone photography, and surface monitoring multi-source data, updating the database, and using the RSEI model to process remote sensing data, analyze the ecological status and its changing trends, and promptly discover and warn of ecological risks.

[0033] A load balancing system supporting QUIC multipath transmission based on VPP, comprising: Data acquisition module: According to the planning scheme, collect multi-source data from the space segment, sky segment, and surface segment, use data processing tools to pre-process and integrate the collected data, and build a space-space-ground multi-source remote sensing information differentiation storage database; Spatiotemporal analysis module: Spatiotemporal analysis is performed through the multi-source remote sensing data set of the air-space-ground multi-source remote sensing information differentiation storage database to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all directions, local areas, and spatial units.

[0034] Integrated analysis module: Based on the characteristics of power transmission and transformation projects and regional ecosystems, key ecological indicators are extracted from the database, and integrated analysis is performed to build an ecological impact indicator system.

[0035] Index quantification module: Through the constructed ecological impact index system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into the RSEI value, and the impact of the power transmission and transformation project on the ecological environment is quantified according to the RSEI value.

[0036] Boundary determination module: The RSEI value is visualized through geographic information system software to determine the spatiotemporal boundaries of the ecological impact of the power transmission and transformation project and identify the key affected areas.

[0037] The advantages of the present invention are: Improving the accuracy of ecological impact assessments By integrating multi-source remote sensing information, including high-resolution satellite images, drone aerial data, radar data, etc., it is possible to more comprehensively capture the impact of power transmission and transformation projects on the ecological environment. This deep integration of technical means can achieve accurate perception and quantitative analysis of ecological and environmental changes, thereby improving the accuracy of ecological impact assessment.

[0038] Optimizing the method of determining space-time boundaries Traditional ecological impact assessment methods are often based on a single remote sensing data source, making it difficult to accurately define the temporal and spatial impact boundaries of power transmission and transformation projects on the ecological environment. However, by introducing deep fusion and intelligent interpretation technology of multi-source remote sensing information, the present invention can more accurately determine the temporal and spatial impact boundaries of power transmission and transformation projects on the ecological environment, providing more refined data support for ecological impact assessment.

[0039] Improve assessment efficiency and reduce costs The use of multi-source remote sensing information for deep fusion interpretation can greatly improve the efficiency of ecological impact assessment. At the same time, compared with traditional ground survey methods, remote sensing technology has the advantages of wide coverage, fast data collection, and relatively low cost, which can significantly reduce the cost of ecological impact assessment.

[0040] Promoting the intelligent development of ecological impact assessment The invention promotes the development of ecological impact assessment towards intelligence and automation. By introducing artificial intelligence algorithms and deep learning technology, automatic interpretation and intelligent analysis of multi-source remote sensing information can be achieved, thereby improving the intelligence level of ecological impact assessment and providing more powerful technical support for ecological environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0042] Figure 1 It is a schematic diagram of the process of the present invention.

[0043] Figure 2 It is a flow chart of the system of the present invention.

[0044] Figure 3 The data flow chart of the present invention.

[0045] Figure 4 This is a flow chart of the remote sensing ecological index model of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1 like Figure 1 As shown, a method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information is proposed. Aiming at the limitations of existing environmental protection assessment technologies, the present invention aims to solve the problem of assessing the impact of power transmission and transformation projects on the ecological environment, and innovatively proposes a multi-source remote sensing information deep fusion interpretation technology to accurately define the spatiotemporal boundary of the impact of power transmission and transformation projects on the ecological environment. It includes the following steps: S1: Determination of the planning scheme: Through geographic information system software, determine the planning scheme of the power transmission and transformation project, including the specific geographical scope, time period, line direction and site location, identify the ecological and environmental areas that may be involved in the project, and clarify the data types that need to be collected and the key ecological factors to be monitored.

[0048] S2: Data collection, preprocessing and integration: According to the planning scheme, collect multi-source data from the space segment, sky segment and surface segment, use data processing tools to preprocess and integrate the collected data, and build an air-space-ground multi-source remote sensing information differentiated storage database.

[0049] S3: Multi-scale spatiotemporal analysis: Spatiotemporal analysis is performed using multi-source remote sensing data sets in the space-air-ground multi-source remote sensing information differentiation storage database to evaluate the spatiotemporal impact of power transmission and transformation projects on regional ecology in all directions, local areas, and spatial units.

[0050] S4: Construction of ecological impact indicator system; based on the characteristics of power transmission and transformation projects and regional ecosystems, key ecological indicators are extracted from the database, and integrated analysis is performed to construct an ecological impact indicator system.

[0051] S5: Construction of remote sensing ecological index model; through the constructed ecological impact indicator system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into RSEI values, and the impact of power transmission and transformation projects on the ecological environment is quantified according to the RSEI values.

[0052] S6: Determine the spatiotemporal boundaries of ecological impacts; visualize the RSEI value through geographic information system software, determine the spatiotemporal boundaries of the ecological impacts of the transmission and transformation project, and identify the key affected areas.

[0053] As a refinement of the above embodiment, the geographic information system software is GIS software.

[0054] As a refinement of the above embodiment, the multi-source remote sensing data type includes satellite remote sensing data in the space segment, drone monitoring data in the sky segment, and ground monitoring station data in the surface segment; the data collection method is as follows: Space segment satellite remote sensing data: Through satellite data receiving equipment or satellite data center platform, various remote sensing data are regularly received into the database, including optical images, radar data, thermal imaging data, and multi-spectral data. Obtained through data subscription or direct purchase of services.

[0055] Sky segment drone monitoring data: obtain aerial monitoring data of specific areas through drone platforms, including videos, thermal images and high-resolution images. Drones are equipped with advanced sensors to collect, store and transmit to the database.

[0056] Surface monitoring station data: By deploying meteorological stations, water quality monitoring stations and environmental sensors in specific areas, temperature, humidity, precipitation and water quality environmental parameters are collected. Wireless communication technology is used to transmit data to the database.

[0057] As a refinement of the above embodiment, the preprocessing and integration methods include format conversion, geo-referencing, image processing, image fusion, and multi-source data integration.

[0058] Format conversion: Use the data processing tool (GDAL) to read multi-source remote sensing data, extract source coordinate information, determine the coordinate reference system of each data set, and use the conversion function of GDAL to convert multi-source format data into the general geographic information system format and convert it to the WGS84 coordinate system.

[0059] Georeferencing: Georeferencing is performed through GDAL to align multi-source data to the same coordinate system.

[0060] Image processing: Use the open source computer vision library platform (OpenCV) for image processing, select the reference image, correct the multi-source remote sensing data to the reference image through control points, and use the camera calibration and distortion correction algorithm on the OpenCV platform to correct the geometric distortion of satellite images and aerial images to eliminate image geometric distortion.

[0061] Image fusion: Use the image fusion algorithm in the OpenCV platform to fuse data from different sources and resolutions into a single high-resolution dataset. Fuse low-resolution multispectral images with high-resolution panchromatic images to generate higher-resolution images.

[0062] Data integration: Integrate the fused remote sensing data with other related data to ultimately build a comprehensive air-space-ground multi-source remote sensing information differentiated storage database.

[0063] It also includes data cleaning and quality control: cleaning the data, removing duplicate or erroneous data, performing quality control, eliminating unqualified data, and ensuring data quality.

[0064] Among them, GDAL is a geospatial data abstraction library used to process raster and vector geographic data, and supports the reading, writing and conversion of geographic information system data in different formats. OpenCV is an open source computer vision and machine learning library platform that provides a wealth of functions and tools for processing images and videos, and supports real-time image processing and computer vision tasks.

[0065] Among them, the image fusion algorithm is a camera calibration and distortion correction algorithm. It uses the functions provided by the OpenCV platform to perform image registration, eliminate image geometric distortion, and improve data accuracy.

[0066] Among them, the integrated data includes multi-temporal remote sensing images, digital elevation model terrain data, soil data, biodiversity information data, surface monitoring data, etc., to build a comprehensive multi-source remote sensing information database.

[0067] As a refinement of the above embodiment, a multi-source remote sensing data set of an air-space-ground multi-source remote sensing information differentiation storage database is used for spatiotemporal analysis, covering three levels of macro, meso and micro scales. Relevant terrain, land use, vegetation cover and biomass data features are extracted from the constructed database to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all directions, local and spatial units.

[0068] At the macro scale, GIS software is used to analyze the trends of vegetation coverage, land use, biomass, and surface temperature in the entire impact area, and time series data is used to evaluate regional environmental changes and determine the overall trend of the ecological impact of the power transmission and transformation project on the entire region. The annual trend changes in vegetation coverage, land use, and biomass during the construction and operation of the power transmission and transformation project are predicted.

[0069] At the mesoscale, cluster analysis methods are applied to analyze vegetation coverage, land use changes, ecosystem types, and water resource distribution in local areas within a specific period. The silhouette coefficient is used to determine the optimal number of clusters, and the clustering results are combined with the geographic information system for spatial analysis and visualization. The clustering results of different time periods are compared to analyze the changing trends of vegetation coverage and land use changes.

[0070] At the microscopic scale, we extracted high-resolution remote sensing data from the database and combined it with on-site field surveys to conduct field sampling and analysis of ecological data to verify the results of remote sensing analysis. We collected soil samples at different stages of the project, analyzed the soil characteristics of pH value, organic matter content, and heavy metal content, and used remote sensing images to analyze soil moisture and temperature changes; analyzed vegetation growth and coverage through sampling methods and remote sensing images; installed cameras to capture wildlife activities and record the frequency and distribution of wildlife in a specific period. We used statistical software (SPSS) to conduct statistical analysis on the collected data, and applied the regression analysis method in the software to evaluate the relationship between ecological indicators. We used geographic information system tools to draw distribution maps of ecological changes, identify hot spots, and visualize changes in various indicators.

[0071] The cluster analysis method in the mesoscale is a method in the scikit-learn library in Python. This library provides a variety of cluster analysis methods for dividing data sets into different groups. Preferably, the key ecological indicators include vegetation greenness, soil moisture, drought index, and surface temperature.

[0072] As a refinement of the above-mentioned embodiment, the ecological impact index system is constructed by using the principle of land-object-organism energy value conduction, and according to the characteristics of power transmission and transformation projects and regional ecosystems, using GIS software and the PCA method, key ecological indicators are extracted from the database, and the NDVI, WET, NDSI, and LST indicators are integrated and analyzed to construct an ecological impact index system. Among them, PCA stands for "principal component analysis"; NDVI stands for "vegetation greenness"; WET stands for "soil moisture"; NDSI stands for "drought index"; LST stands for "surface temperature", and these indicators can be obtained by inversion of remote sensing data.

[0073] The principle of geo-physical-biological energy value conduction is based on geology and ecology as a theoretical framework, describing the interaction and energy transfer process between geographical elements (such as topography, soil), biological elements (such as vegetation, animal communities) and energy elements (such as solar energy input, biological energy transfer) in the earth's surface ecosystem.

[0074] The PCA method is a method applied to mathematical statistics, analysis, and modeling. PCA analysis is performed on the extracted ecological impact indicators to convert multiple variables into a few variables through mathematical transformation, reduce the data dimension, and retain the main information.

[0075] Specifically, the PCA method steps include the following: (1) Calculate the covariance matrix; (2) Solve for eigenvalues ​​and eigenvectors; (3) Select the first few principal components based on the eigenvalues ​​to ensure that the cumulative explained variance reaches more than 80%.

[0076] To describe PCA mathematically, for a set of n samples, , a data set X of N variables, the data matrix is: , in, .

[0077] The PCA method transforms the original N observed variables Comprehensively, N new variables are formed, namely , In short: .

[0078] As a refinement of the above embodiment, the PCA analysis results are used to construct the RSEI model when constructing the remote sensing ecological index model, which integrates multiple ecological indicators into one indicator to quantify the impact of power transmission and transformation projects on the ecological environment. A machine learning model is developed, the random forest algorithm is used to verify the model accuracy, and the variance decomposition method is used for sensitivity analysis.

[0079] Among them, RSEI stands for "Remote Sensing Ecosystem Index", an indicator that comprehensively reflects the health of the ecosystem. It is calculated by analyzing remote sensing data. The value range is [0,1]. The higher the value, the better the ecosystem condition; the random forest algorithm is a machine learning algorithm based on decision trees with strong generalization ability and robustness.

[0080] Among them, a RSEI model construction step is characterized by comprising the following: Normalization: Normalize the NDVI, WET, NDSI, and LST indicators. Use the Min-Max normalization method to convert each indicator to a unified scale of [0,1], thereby synthesizing a new layer as the basic data for the RSEI model.

[0081] PCA method processing: Apply the PCA method to process the normalized indicator layer to generate a series of principal components. Specifically, it includes: calculating the covariance matrix, solving the eigenvalues ​​and eigenvectors, selecting the first few principal components according to the eigenvalues, and ensuring that the cumulative explained variance reaches more than 80% to retain enough information. Usually, the first principal component (PC1) contains the largest amount of information. The RSEI value is calculated using PC1 to quantify the ecological factors. Among them, the RSEI value usually ranges from 0 to 1. An RSEI value close to 1 indicates that the ecological environment is in good condition, and an RSEI value close to 0 indicates that the ecological environment is negatively affected.

[0082] Model validation: Use the random forest algorithm to classify and detect changes in remote sensing data, verify the accuracy of the RSEI model, and analyze ecological change trends at different time points. Use ecological impact indicators and ground environmental monitoring data for model training, divide the data set into training and test sets, optimize model performance by adjusting the number and depth of random forest trees, and use cross-validation methods to improve the reliability of model output values.

[0083] Sensitivity analysis: The variance decomposition method is used to conduct sensitivity analysis to determine the contribution of each indicator to the RSEI value.

[0084] Specifically, the NDVI, WET, NDSI, and LST indicators are normalized so that their range is between [0, 1]. The normalization formula is as follows: , In the formula, is the normalized value, is the original value, is the minimum value of the indicator, is the maximum value of the indicator.

[0085] The RSEI value is calculated by the first principal component as follows: The normalized index layer was imported into GIS software, and PCA analysis was performed using spatial analysis tools. Normalization is performed to generate RSEI. The specific formula is as follows: , in, is the minimum value of the first principal component, is the maximum value of the first principal component.

[0086] Optionally, the impact of the power transmission and transformation project on the ecological environment is quantified according to the RSEI value as follows: the impact degree is divided into severe impact, relatively severe impact, moderate impact, slight impact, and relatively slight impact according to the RSEI value, and the corresponding RSEI value ranges are: severe impact [0.0-0.2) , relatively severe impact [0.2-0.4) , moderate impact [0.4-0.6) , slight impact [0.6-0.8) , and relatively slight impact [0.8-1.0].

[0087] Example 2 A method for determining the spatiotemporal boundary of ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information, including the following: planning scheme determination, data collection, preprocessing and integration, multi-scale spatiotemporal analysis, ecological impact indicator system construction, remote sensing ecological index model construction, ecological impact spatiotemporal boundary determination, dynamic monitoring and early warning system construction; As a refinement of the above embodiment, the steps for constructing a dynamic monitoring and early warning system are as follows: Establish a regular monitoring and automatic early warning system platform, regularly obtain new satellite images, drone photography, surface monitoring multi-source data, and update the database. Use the RSEI model to process remote sensing data, analyze ecological status and its changing trends, and promptly discover and warn of ecological risks. Set the normal range and early warning threshold of the RSEI value based on historical data. Once the monitoring indicators change abnormally, the RSEI value output by the model exceeds or falls below the threshold, and an early warning signal is automatically issued to indicate the area where ecological risks occur.

[0088] Among them, further content is the ecological environment monitoring method during the project implementation phase: during the project implementation phase, regularly monitor the impact of the project on the ecological environment, use an automated monitoring system to collect regular data, and conduct ecological index analysis, set the normal range and early warning threshold of the ecological index, and ensure rapid response and handling of ecological problems.

[0089] This embodiment also includes: long-term monitoring and evaluation steps: establish a long-term remote sensing monitoring plan, conduct annual or seasonal analysis, compare data changes in different periods, and track the dynamic process of ecological changes. Combined with time series analysis, use GIS software to analyze the changing trend of RSEI values ​​over time, and evaluate the cumulative impact of power transmission and transformation projects on the ecological environment. Combined with the specific conditions of the project and the trend of ecological changes, the spatiotemporal boundaries of ecological impacts are optimized and adjusted to achieve accurate analysis and intuitive presentation of complex ecological scenes. Different RSEI models are formulated according to the ecological characteristics of different regions to improve the accuracy and applicability of the model.

[0090] Among them, further content, ecological impact monitoring and assessment methods during the operation phase of power transmission and transformation projects: During the operation phase of the project, ecological impact monitoring and assessment shall be continuously carried out. According to the monitoring results, ecological protection measures shall be adjusted and optimized to ensure the harmonious coexistence of the project and the ecological environment. Ecological impact assessment reports shall be generated regularly to provide transparent information to relevant management departments and the public. Feedback shall be collected, and the assessment model and monitoring system shall be continuously optimized to improve the efficiency of assessment and management.

[0091] It should be noted that the present invention can integrate data from different remote sensing platforms (such as satellites, drones, and ground monitoring stations) and achieve a comprehensive assessment of the impact on the ecological environment through advanced data fusion technology. This deep fusion technology improves the accuracy and efficiency of monitoring.

[0092] The present invention can automatically issue early warnings based on monitoring data. This system can timely discover potential ecological problems and provide support for the timely adoption of environmental protection measures.

[0093] The present invention can accurately determine the spatial and temporal boundaries of the impact of power transmission and transformation projects on the ecological environment through remote sensing monitoring and time series analysis combined with field survey data. This visual determination method not only improves the accuracy of ecological impact assessment, but also provides intuitive and easy-to-understand decision support for ecological protection and project planning.

[0094] In summary, the technical solution of the present invention effectively solves the time-consuming and inefficient problems faced by traditional ground survey methods, and is committed to overcoming the defects of big data technology in the application of ecological and environmental protection, including improving multi-dimensional perception capabilities, strengthening all-factor monitoring capabilities, and improving data sharing and integrated application capabilities. Through deep fusion and interpretation of data from different remote sensing information sources, this technology can accurately monitor and analyze the impact of power transmission and transformation projects on ecological and environmental changes during construction and operation, providing a comprehensive and efficient monitoring and evaluation technology, effectively improving the efficiency and accuracy of environmental protection work.

[0095] Example 3 This example provides a specific implementation plan, further illustrating an implementation method of a method for determining the spatiotemporal boundary of the ecological impact of a power transmission and transformation project based on deep fusion interpretation of multi-source remote sensing information; including: (1) System construction steps: Hardware equipment: including satellite data receiving equipment, UAV platform, ground monitoring station hardware equipment, and server and network environment construction.

[0096] Software platform: Install GIS software (ArcGIS), image processing software (OpenCV / ENVI), machine learning software (Python), and database software (MySQL) software platforms.

[0097] Database construction: Use database software (MySQL) to build an air-space-ground multi-source remote sensing information differentiated storage database, design data structure, and facilitate data storage and management.

[0098] (2) Steps for determining the planning scheme: Analyze the characteristics of power transmission and transformation projects: Understand the specific conditions of the project, including line direction, site location, and construction period.

[0099] Identify ecological and environmental areas: determine the ecological and environmental areas that the project may involve, including forests, grasslands, wetlands, waters, etc.

[0100] Select key ecological factors: Select key ecological factors based on project characteristics and ecological environment areas, including vegetation coverage, soil moisture, drought index, and surface temperature.

[0101] (3) Multi-source data collection steps: Regularly download the required remote sensing data from platforms such as China Remote Sensing Data Network and Geospatial Data Cloud. At the same time, obtain data from drones, ground monitoring stations and other channels. Data quality standards (such as cloud coverage less than 10%, image resolution not less than 5 meters). Store the collected multi-source data in the constructed database platform.

[0102] Satellite remote sensing data collection: Optical images, radar data, thermal imaging data, multispectral data, etc. are regularly received through satellite data receiving equipment or satellite data center platforms.

[0103] Drone aerial data collection: Use drone platforms to obtain aerial monitoring data of specific areas, including video, thermal images and high-resolution images.

[0104] Ground monitoring data collection: By deploying meteorological stations, water quality monitoring stations and environmental sensors in specific areas, environmental parameters such as temperature, humidity, precipitation and water quality are collected.

[0105] (4) Data preprocessing and integration steps: Data format conversion: Use data processing tools such as GDAL to convert remote sensing data in different formats into common geographic information system formats.

[0106] Geo-reference: Use tools such as GDAL to align multi-source data to the same coordinate system.

[0107] Image processing: Use OpenCV image processing software to perform image correction, cropping, enhancement and other operations.

[0108] Image fusion: Use image fusion algorithms from software such as OpenCV to fuse data from different sources and resolutions into a single high-resolution dataset.

[0109] Data integration: Integrate the preprocessed remote sensing data with other relevant data to build a comprehensive multi-source remote sensing information database.

[0110] (5) Multi-scale spatiotemporal analysis steps: Macro-scale analysis: GIS software is used to analyze the trends of vegetation coverage, land use, biomass, and surface temperature within the entire impact area, and to assess the overall impact of the power transmission and transformation project on the ecology of the entire region.

[0111] Meso-scale analysis: Cluster analysis is used to analyze vegetation coverage, land use changes, ecosystem types, and water resource distribution in local areas within a specific period, and to conduct spatial analysis and visualization.

[0112] Micro-scale analysis: Extract high-resolution remote sensing data and combine it with on-site field surveys to conduct field sampling and analysis of ecological data, verify the results of remote sensing analysis, draw distribution maps of ecological changes, and identify hot spots.

[0113] (6) Steps for constructing ecological impact indicators: Extract key ecological indicators: According to the characteristics of the power transmission and transformation project, relevant remote sensing indexes and ecological factors are selected. Using GIS software and PCA method, key ecological indicators such as vegetation greenness, soil moisture, drought index, and surface heat are extracted from the fusion database.

[0114] PCA analysis: The PCA method was used to reduce the dimensionality of the extracted ecological impact indicators, generate new variables, and retain the main information.

[0115] (7) Steps for constructing the remote sensing ecological index model: RSEI model construction: Using the PCA analysis results, the RSEI model is constructed to integrate multiple ecological indicators into one indicator to quantify the impact of power transmission and transformation projects on the ecological environment.

[0116] Model validation: Random forest algorithm is used to classify and detect changes in remote sensing data to verify the accuracy of the RSEI model.

[0117] Sensitivity analysis: The variance decomposition method is used to conduct sensitivity analysis to determine the contribution of each indicator to the RSEI value.

[0118] (8) Steps for determining the spatial and temporal boundaries of ecological impacts: Visualization of RSEI values: Use GIS software to visualize RSEI values, determine the spatial and temporal boundaries of the ecological impact of power transmission and transformation projects, and identify key affected areas.

[0119] (9) Steps for establishing a dynamic monitoring and early warning system platform: Regular data updates: Regularly acquire new satellite images, drone photography, and surface monitoring multi-source data to update the database.

[0120] Ecological status analysis: Use the RSEI model to analyze the ecological status and its changing trends.

[0121] Automatic warning: Automatically issue warning signals based on preset thresholds.

[0122] (10) Long-term monitoring and evaluation steps: Annual or seasonal analysis: Conduct annual or seasonal analysis to track the dynamic process of ecological change.

[0123] Time series analysis: Analyze the changing trend of RSEI value over time and evaluate the cumulative impact of power transmission and transformation projects on the ecological environment.

[0124] Model optimization: Optimize the model according to actual conditions to improve the accuracy and applicability of the model.

[0125] Through the above steps, the present invention can provide a clear and systematic process for the ecological impact assessment of power transmission and transformation projects, ensuring the accuracy and practicality of the assessment results. At the same time, through the establishment of dynamic monitoring and automatic early warning systems, ecological problems can be discovered and responded to in a timely manner, contributing to environmental protection and sustainable development.

[0126] Example 4 A load balancing system supporting QUIC multipath transmission based on VPP, comprising: Data acquisition module: According to the planning scheme, multi-source data from the space segment, sky segment, and surface segment are collected, and the collected data are pre-processed and integrated using data processing tools to build an air-space-ground multi-source remote sensing information differentiation storage database.

[0127] Spatiotemporal analysis module: Spatiotemporal analysis is performed through the multi-source remote sensing data set of the air-space-ground multi-source remote sensing information differentiation storage database to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all directions, local areas, and spatial units.

[0128] Integrated analysis module: Based on the characteristics of power transmission and transformation projects and regional ecosystems, key ecological indicators are extracted from the database, and integrated analysis is performed to build an ecological impact indicator system.

[0129] Index quantification module: Through the constructed ecological impact index system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into the RSEI value, and the impact of the power transmission and transformation project on the ecological environment is quantified according to the RSEI value.

[0130] Boundary determination module: The RSEI value is visualized through geographic information system software to determine the spatiotemporal boundaries of the ecological impact of the power transmission and transformation project and identify the key affected areas.

[0131] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining the spatiotemporal boundaries of ecological impacts of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information, characterized in that: The following steps are involved: Through geographic information system software, determine the planning scheme of power transmission and transformation projects, including specific geographical scope, time period, line direction and site location, identify the ecological and environmental areas that may be involved in the project, and clarify the data types that need to be collected and the key ecological factors to be monitored; According to the planning scheme, multi-source data from space, sky and surface are collected, and data processing tools are used to pre-process and integrate the collected data to build a differentiated storage database for multi-source remote sensing information from space, sky and ground. Through the multi-source remote sensing data set of the air-space-ground multi-source remote sensing information differentiation storage database, the spatiotemporal analysis is carried out to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all directions, local areas and spatial units; According to the characteristics of power transmission and transformation projects and regional ecosystems, key ecological indicators are extracted from the database, integrated and analyzed, and an ecological impact indicator system is constructed; Through the constructed ecological impact index system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into the RSEI value, and the impact of power transmission and transformation projects on the ecological environment is quantified according to the RSEI value; The RSEI values ​​are visualized through geographic information system software to determine the spatiotemporal boundaries of the ecological impact of power transmission and transformation projects and identify the key affected areas.

2. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 1 is characterized in that: The data types of the multi-source data include satellite remote sensing data in the space segment, drone monitoring data in the sky segment, and ground monitoring station data in the surface segment; the data collection method is as follows: Space segment satellite remote sensing data: Remote sensing data is regularly received into the database through satellite data receiving equipment or satellite data center platform, including optical images, radar data, thermal imaging data, and multi-spectral data, which are obtained through data subscription or direct purchase of services; Sky segment drone monitoring data: obtain aerial monitoring data of designated areas through drone platforms, including videos, thermal images and high-resolution images; Surface ground monitoring station data: Meteorological stations, water quality monitoring stations and environmental sensors are deployed in designated areas to collect temperature, humidity, precipitation and water quality environmental parameters, and the data are transmitted to the database using wireless communication technology.

3. The method for determining the spatiotemporal boundary of ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 1 is characterized in that: The preprocessing and integration methods include format conversion, georeferencing, image processing, image fusion, and multi-source data integration; Format conversion: Use data processing tools to read multi-source remote sensing data, extract source coordinate information, determine the coordinate reference system of each data set, and convert multi-source format data into a common geographic information system format; Georeferencing: Georeferencing is performed through the Geospatial Data Abstraction Library to align multi-source data to the same coordinate system; Image processing: Use the open source computer vision library platform to process images, select the reference image, correct the multi-source remote sensing data to the reference image through control points, and use the camera calibration and distortion correction algorithm on the OpenCV platform to correct the geometric distortion of satellite images and aerial images to eliminate image geometric distortion; Image fusion: Use the image fusion algorithm in the OpenCV platform to fuse data from different sources and resolutions into a single high-resolution dataset; Fuse low-resolution multispectral images with high-resolution panchromatic images to generate high-resolution images; Multi-source data integration: Integrate the fused remote sensing data with related data to build an air-space-ground multi-source remote sensing information differentiated storage database.

4. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 1 is characterized in that: Spatiotemporal analysis of multi-source remote sensing data sets including macro, meso and micro scales through air-space-ground multi-source remote sensing information differentiated storage database; Macro scale: Use GIS software to analyze the trends of vegetation coverage, land use, biomass, and surface temperature within the entire impact area, use time series data to evaluate regional environmental changes, and determine the overall trend of the ecological impact of the power transmission and transformation project on the entire region; predict the annual trend changes in vegetation coverage, land use, and biomass during the construction and operation of the power transmission and transformation project; Mesoscale: cluster analysis methods are used to analyze vegetation coverage, land use changes, ecosystem types, and water resource distribution in local areas within a specific period; Use the silhouette coefficient to determine the optimal number of clusters and combine the clustering results with the geographic information system; compare the clustering results of different time periods to analyze the changing trends of vegetation coverage and land use changes; Micro scale: extract high-resolution remote sensing data from the database and combine it with field survey data to conduct field sampling and analysis of ecological data, verify remote sensing analysis results, and analyze changes in the ecological environment in local areas.

5. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 1 is characterized in that: The key ecological indicators include vegetation greenness, soil moisture, drought index, and surface temperature.

6. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 5 is characterized in that: The steps for constructing the remote sensing ecosystem index model are as follows: The vegetation greenness, soil moisture, drought index, and surface temperature indicators were normalized. The Min-Max normalization method was used to convert each indicator to a unified scale of [0,1] and synthesize a new layer as the basic data of the RSEI model. The normalized index layer is processed by the PCA method to generate the principal component; the RSEI value is calculated by the first principal component; The model was trained using ecological impact indicators and ground environmental monitoring data to analyze ecological change trends at different time points. The remote sensing data was classified and change detected using the random forest algorithm to verify the accuracy of the RSEI model, and the cross-validation method was used to improve the accuracy of the model output values. Variance decomposition method was used to conduct sensitivity analysis to determine the contribution of each indicator to the RSEI value.

7. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 6 is characterized in that: The normalization formula is as follows: ， In the formula, is the normalized value, is the original value, is the minimum value of the indicator, is the maximum value of the indicator; The RSEI value is calculated by the first principal component as follows: The normalized index layer was imported into GIS software, and PCA analysis was performed using spatial analysis tools. Normalization is performed to generate RSEI. The specific formula is as follows: ， in, is the minimum value of the first principal component, is the maximum value of the first principal component.

8. The method for determining the spatiotemporal boundary of the ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to any one of claims 1 to 7, characterized in that: The impact of power transmission and transformation projects on the ecological environment is quantified based on the RSEI value as follows: the impact degree is divided into severe impact, relatively severe impact, moderate impact, slight impact, and relatively slight impact according to the RSEI value. The corresponding RSEI value ranges are: severe impact [0.0-0.2) , relatively severe impact [0.2-0.4) , moderate impact [0.4-0.6) , slight impact [0.6-0.8) , and relatively slight impact [0.8-1.0) .

9. The method for determining the spatiotemporal boundary of ecological impact of power transmission and transformation projects based on deep fusion interpretation of multi-source remote sensing information according to claim 1 is characterized in that: It also includes establishing a regular monitoring and automatic early warning system platform, regularly acquiring new satellite images, drone photography, and surface monitoring multi-source data, updating the database, and using the RSEI model to process remote sensing data, analyze the ecological status and its changing trends, and promptly discover and warn of ecological risks.

10. A load balancing system supporting QUIC multipath transmission based on VPP, characterized in that: include: Data acquisition module: According to the planning scheme, collect multi-source data from the space segment, sky segment, and surface segment, use data processing tools to pre-process and integrate the collected data, and build a space-space-ground multi-source remote sensing information differentiation storage database; Spatiotemporal analysis module: Spatiotemporal analysis is performed through the multi-source remote sensing data set of the air-space-ground multi-source remote sensing information differentiation storage database to evaluate the spatiotemporal impact of the power transmission and transformation project on the regional ecology in all directions, local areas, and spatial units; Integrated analysis module: extract key ecological indicators from the database according to the characteristics of power transmission and transformation projects and regional ecosystems, conduct integrated analysis, and build an ecological impact indicator system; Index quantification module: Through the constructed ecological impact index system, a remote sensing ecosystem index model is constructed, multiple ecological indicators are integrated into the RSEI value, and the impact of power transmission and transformation projects on the ecological environment is quantified according to the RSEI value; Boundary determination module: The RSEI value is visualized through geographic information system software to determine the spatiotemporal boundaries of the ecological impact of the power transmission and transformation project and identify the key affected areas.

Images