Environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellite

Abstract

The invention discloses an environmental pollutant remote sensing monitoring system based on a multi-source remote sensing satellite, and the system comprises an air pollution data collection unit which is used for collecting air pollution related data through multiple ways; the air pollution data preprocessing unit is used for performing format conversion, radiation correction and geometric correction on the acquired air pollution related data; the air pollution data fusion unit is used for fusing air pollution related data acquired in multiple ways by adopting principal component analysis and a wavelet transform method; the air pollution data analysis unit is used for constructing a pollution component inversion model and analyzing the pollutant concentration by performing feature extraction and screening on the data; and the analysis result evaluation unit is used for evaluating the data acquisition accuracy and the analysis process effectiveness. The problems that an existing environmental pollutant monitoring system lacks customized design and cannot accurately capture environmental parameter changes are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring, and in particular relates to an environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites. Background Art

[0002] As environmental issues become increasingly complex, traditional ground-based monitoring stations have limited coverage, poor real-time performance, and inefficient and costly manual sampling and analysis, making them unable to meet the needs of large-scale, dynamic environmental monitoring. Existing general-purpose remote sensing products, due to a lack of customized design, are unable to accurately capture changes in environmental parameters when addressing specific environmental issues such as air pollution and water quality monitoring. Furthermore, environmental remote sensing data is multi-source, heterogeneous, and massively complex. Traditional data processing methods face technical bottlenecks in data fusion, feature extraction, and quantitative inversion, making it difficult to achieve high-precision, specialized monitoring and analysis. Summary of the Invention

[0003] In response to the problem that existing environmental pollutant monitoring systems lack customized design and cannot accurately capture changes in environmental parameters, the present invention provides an environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites.

[0004] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:

[0005] An environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites, comprising an air pollution data acquisition unit, an air pollution data preprocessing unit, an air pollution data fusion unit, an air pollution data analysis unit and an analysis result evaluation unit;

[0006] Air pollution data collection unit, used to collect air pollution related data through multiple channels;

[0007] Air pollution data preprocessing unit, used for format conversion, radiation correction and geometric correction of collected air pollution related data;

[0008] The air pollution data fusion unit uses principal component analysis (PCA) and wavelet transform to fuse air pollution-related data collected from multiple channels;

[0009] Air pollution data analysis unit builds a pollution component inversion model and analyzes pollutant concentrations by extracting and screening data features;

[0010] The analysis result evaluation unit is used to evaluate the accuracy of data collection and the effectiveness of the analysis process.

[0011] Furthermore, the collection of air pollution-related data includes multi-source satellite remote sensing data, ground remote sensing monitoring data, and drone remote sensing data;

[0012] Multi-source satellite remote sensing data, which is obtained by accessing existing satellite platforms;

[0013] Ground remote sensing monitoring data: Build ground remote sensing monitoring stations in air pollution-sensitive areas and collect corresponding ground remote sensing data through high-precision spectrum analyzers and meteorological sensors at the ground remote sensing monitoring stations;

[0014] Drone remote sensing data, remote sensing data of small areas and rapid patrol remote sensing data of large areas through different types of drones.

[0015] Furthermore, the air pollution data fusion unit fuses multi-source remote sensing data from satellites and drones, integrating high spatial resolution and high spectral resolution to enhance data availability.

[0016] Match ground sensor data with remote sensing images in time and space to provide multi-dimensional information for subsequent air pollution data analysis.

[0017] Furthermore, the air pollution data analysis unit collects a large amount of historical remote sensing data and synchronized ground-measured pollutant concentration data to form a training data set; by extracting and screening the data features, the spectral features are used as model input and the pollutant concentration is used as output to train and optimize the model.

[0018] Based on hyperspectral remote sensing data, the concentration distribution of atmospheric pollutants is inverted using spectral absorption characteristics, using algorithms such as least squares and neural networks. For example, by using the absorption characteristics of sulfur dioxide in the 300-330nm band, a concentration inversion model is established to draw a spatial distribution map of pollutant concentrations.

[0019] Furthermore, the air pollution data analysis unit also simulates pollution transmission, obtains real-time meteorological data on wind direction, wind speed, temperature and humidity, and combines the meteorological data interface with the atmospheric diffusion model to realize pollution transmission simulation.

[0020] Furthermore, data collection accuracy assessment includes multi-source data consistency verification, data integrity check, and sensor accuracy calibration;

[0021] Verify the consistency of multi-source data, comparing the monitoring results of satellite remote sensing data, ground monitoring station data and drone data in the same monitoring area and at the same time point;

[0022] Data integrity check: Count the proportion of missing data during the data collection process, and check the data collection links that do not meet the standards by setting data integrity thresholds; for example, the effective data collection rate is required to be no less than 95%.

[0023] Sensor accuracy calibration: Regularly calibrate the sensors at the ground monitoring station in the laboratory, compare the measured values ​​of the sensors under standard environment with the standard values, and calculate the measurement error.

[0024] Furthermore, the effectiveness evaluation of the analytical process includes the assessment of the accuracy of pollution composition inversion, the accuracy of pollution transport simulation and traceability, and the reliability of time series analysis;

[0025] Pollutant component inversion accuracy assessment uses an independent validation data set to evaluate the accuracy of the inversion model. In air pollution monitoring, the pollutant concentrations inverted by the model are compared with the actual concentrations measured on the ground, and the mean absolute error (MAE) and relative error indicators are calculated. If the MAE is lower than the set threshold and the relative error is controlled within a reasonable range, it means that the inversion model has high accuracy. For water quality parameter inversion, the inversion effect of the model on parameters such as chlorophyll and suspended matter is also evaluated by comparing the inverted values ​​with the measured values.

[0026] Pollution transmission simulation and traceability accuracy assessment: compare the pollution transmission simulation results with the actual monitored pollution diffusion. In the air pollution scenario, observe whether the simulated pollution transmission path is consistent with the actual monitored pollution distribution. Quantitative assessment is performed by calculating indicators such as the spatial overlap between the simulation results and the actual data. If the matching degree is higher than 80%, it indicates that the analysis process has a high accuracy in traceability.

[0027] Time series analysis reliability assessment: Analyze the time series trends of long-term monitoring data to verify whether the analysis process can accurately reflect the evolution of environmental issues. For example, observe the changing trends of air pollution concentrations in different seasons and years, and conduct correlation analysis with actual environmental governance measures and changes in meteorological conditions to determine whether the analysis process can reasonably explain environmental changes; and evaluate the reliability of the analysis process in long-term monitoring.

[0028] Furthermore, it also includes a visualization unit, which includes visualization of the spatial distribution of pollutant concentrations, dynamic visualization of pollution transmission, and data comparison and trend visualization;

[0029] The spatial distribution of pollutant concentrations is visualized using a geographic information system (GIS) to present inverted pollutant concentration data in the form of thematic maps. Different colors and tones are used to represent different concentration levels, such as red for high-concentration pollution areas and blue for clean areas, to intuitively display the spatial distribution of air pollution in cities and regions. Users can also zoom and pan the map to view detailed pollution distribution at different scales.

[0030] Dynamic visualization of pollution transmission: Based on the results of pollution transmission simulations, dynamic animations are created to illustrate the diffusion of pollutants. Using time as the axis, the distribution of pollutants at different moments is presented frame by frame. Combined with meteorological information such as wind direction and speed, arrows and other symbols are used to visually indicate the direction and speed of pollution transmission. For example, the animation clearly shows how industrial pollutants spread through the atmosphere and their impact on surrounding areas.

[0031] Data comparison and trend visualization: Use line charts, bar charts, and other charts to compare changes in pollutant concentrations over different time periods and regions. For example, compare PM2.5 concentrations in different administrative districts of a city on a monthly basis, using a bar chart to visually demonstrate regional pollution differences. Use a line chart to display the annual Air Quality Index (AQI) trend for a specific region, facilitating analysis of pollution control effectiveness.

[0032] Furthermore, it also includes a dynamic monitoring and early warning unit, which establishes a long-term remote sensing image database, compares data from different periods, and uses change detection algorithms (such as the difference method and the post-classification comparison method) to identify areas of environmental change;

[0033] Set pollution thresholds. When monitoring data exceeds the threshold, early warning information is automatically generated and promptly fed back to relevant departments, providing decision-making support for environmental governance.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] We develop customized remote sensing solutions for specific environmental issues, such as air pollution and water quality monitoring. By designing dedicated data collection processes and integrating multi-source remote sensing methods (satellites, drones, etc.), we accurately acquire environmental data in target areas, improving monitoring timeliness and spatial coverage. We also build dedicated analysis processes and apply advanced algorithms to achieve high-precision inversion of environmental parameters and dynamic change analysis. This addresses the challenges of insufficient traditional monitoring coverage and the lack of targeted general remote sensing, providing accurate and efficient data support for environmental quality assessment, pollution source tracing, and trend forecasting, facilitating environmental science decision-making and pollution control. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a block diagram of the overall structure of an environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and drawings. The contents mentioned in the embodiments are not intended to limit the present invention.

[0038] like Figure 1As shown, this embodiment provides an environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites, including an air pollution data acquisition unit, an air pollution data preprocessing unit, an air pollution data fusion unit, an air pollution data analysis unit, and an analysis result evaluation unit;

[0039] Air pollution data collection unit, used to collect air pollution related data through multiple channels;

[0040] Air pollution data preprocessing unit, used for format conversion, radiation correction and geometric correction of collected air pollution related data;

[0041] The air pollution data fusion unit uses principal component analysis (PCA) and wavelet transform to fuse air pollution-related data collected from multiple channels;

[0042] Air pollution data analysis unit builds a pollution component inversion model and analyzes pollutant concentrations by extracting and screening data features;

[0043] The analysis result evaluation unit is used to evaluate the accuracy of data collection and the effectiveness of the analysis process.

[0044] Collecting air pollution-related data includes multi-source satellite remote sensing data, ground remote sensing monitoring data, and drone remote sensing data;

[0045] Multi-source satellite remote sensing data, which is obtained by accessing existing satellite platforms;

[0046] Ground remote sensing monitoring data: Build ground remote sensing monitoring stations in air pollution-sensitive areas and collect corresponding ground remote sensing data through high-precision spectrum analyzers and meteorological sensors at the ground remote sensing monitoring stations;

[0047] Drone remote sensing data, remote sensing data of small areas and rapid patrol remote sensing data of large areas through different types of drones.

[0048] The air pollution data fusion unit fuses multi-source remote sensing data from satellites and drones, integrating high spatial resolution and high spectral resolution to enhance data availability.

[0049] Match ground sensor data with remote sensing images in time and space to provide multi-dimensional information for subsequent air pollution data analysis.

[0050] The air pollution data analysis unit collects a large amount of historical remote sensing data and synchronized ground-measured pollutant concentration data to form a training data set; by extracting and screening the data features, the spectral features are used as the model input and the pollutant concentration is used as the output to train and optimize the model.

[0051] Based on hyperspectral remote sensing data, the concentration distribution of atmospheric pollutants is inverted using spectral absorption characteristics, using algorithms such as least squares and neural networks. For example, by using the absorption characteristics of sulfur dioxide in the 300-330nm band, a concentration inversion model is established to draw a spatial distribution map of pollutant concentrations.

[0052] The air pollution data analysis unit also simulates pollution transmission, obtains real-time meteorological data on wind direction, wind speed, temperature and humidity, and combines the meteorological data interface with the atmospheric diffusion model to realize pollution transmission simulation.

[0053] Data collection accuracy assessment includes multi-source data consistency verification, data integrity check, and sensor accuracy calibration;

[0054] Verify the consistency of multi-source data, comparing the monitoring results of satellite remote sensing data, ground monitoring station data and drone data in the same monitoring area and at the same time point;

[0055] Data integrity check: Count the proportion of missing data during the data collection process, and check the data collection links that do not meet the standards by setting data integrity thresholds; for example, the effective data collection rate is required to be no less than 95%.

[0056] Sensor accuracy calibration: Regularly calibrate the sensors at the ground monitoring station in the laboratory, compare the measured values ​​of the sensors under standard environment with the standard values, and calculate the measurement error.

[0057] The effectiveness evaluation of the analytical process includes the evaluation of the accuracy of pollution composition inversion, the accuracy of pollution transmission simulation and tracing, and the reliability of time series analysis;

[0058] Pollutant component inversion accuracy assessment uses an independent validation data set to evaluate the accuracy of the inversion model. In air pollution monitoring, the pollutant concentrations inverted by the model are compared with the actual concentrations measured on the ground, and the mean absolute error (MAE) and relative error indicators are calculated. If the MAE is lower than the set threshold and the relative error is controlled within a reasonable range, it means that the inversion model has high accuracy. For water quality parameter inversion, the inversion effect of the model on parameters such as chlorophyll and suspended matter is also evaluated by comparing the inverted values ​​with the measured values.

[0059] Pollution transmission simulation and traceability accuracy assessment: compare the pollution transmission simulation results with the actual monitored pollution diffusion. In the air pollution scenario, observe whether the simulated pollution transmission path is consistent with the actual monitored pollution distribution. Quantitative assessment is performed by calculating indicators such as the spatial overlap between the simulation results and the actual data. If the matching degree is higher than 80%, it indicates that the analysis process has a high accuracy in traceability.

[0060] Time series analysis reliability assessment: Analyze the time series trends of long-term monitoring data to verify whether the analysis process can accurately reflect the evolution of environmental issues. For example, observe the changing trends of air pollution concentrations in different seasons and years, and conduct correlation analysis with actual environmental governance measures and changes in meteorological conditions to determine whether the analysis process can reasonably explain environmental changes; and evaluate the reliability of the analysis process in long-term monitoring.

[0061] It also includes a visualization unit, which includes visualization of the spatial distribution of pollutant concentrations, visualization of pollution transmission dynamics, and visualization of data comparison and trends;

[0062] The spatial distribution of pollutant concentrations is visualized using a geographic information system (GIS) to present inverted pollutant concentration data in the form of thematic maps. Different colors and tones are used to represent different concentration levels, such as red for high-concentration pollution areas and blue for clean areas, to intuitively display the spatial distribution of air pollution in cities and regions. Users can also zoom and pan the map to view detailed pollution distribution at different scales.

[0063] Dynamic visualization of pollution transmission: Based on the results of pollution transmission simulations, dynamic animations are created to illustrate the diffusion of pollutants. Using time as the axis, the distribution of pollutants at different moments is presented frame by frame. Combined with meteorological information such as wind direction and speed, arrows and other symbols are used to visually indicate the direction and speed of pollution transmission. For example, the animation clearly shows how industrial pollutants spread through the atmosphere and their impact on surrounding areas.

[0064] Data comparison and trend visualization: Use line charts, bar charts, and other charts to compare changes in pollutant concentrations over different time periods and regions. For example, compare PM2.5 concentrations in different administrative districts of a city on a monthly basis, using a bar chart to visually demonstrate regional pollution differences. Use a line chart to display the annual Air Quality Index (AQI) trend for a specific region, facilitating analysis of pollution control effectiveness.

[0065] It also includes a dynamic monitoring and early warning unit, which establishes a long-term remote sensing image database, compares data from different periods, and uses change detection algorithms (such as difference method and post-classification comparison method) to identify areas of environmental change;

[0066] Set pollution thresholds. When monitoring data exceeds the threshold, early warning information is automatically generated and promptly fed back to relevant departments, providing decision-making support for environmental governance.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] We develop customized remote sensing solutions for specific environmental issues, such as air pollution and water quality monitoring. By designing dedicated data collection processes and integrating multi-source remote sensing methods (satellites, drones, etc.), we accurately acquire environmental data in target areas, improving monitoring timeliness and spatial coverage. We also build dedicated analysis processes and apply advanced algorithms to achieve high-precision inversion of environmental parameters and dynamic change analysis. This addresses the challenges of insufficient traditional monitoring coverage and the lack of targeted general remote sensing, providing accurate and efficient data support for environmental quality assessment, pollution source tracing, and trend forecasting, facilitating environmental science decision-making and pollution control.

[0069] The above describes in detail the environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites provided by this application. The description of the specific embodiments is intended only to facilitate understanding of the method and core concepts of this application. It should be noted that those skilled in the art may make various improvements and modifications to this application without departing from the principles of this application, and such improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A remote sensing monitoring system for environmental pollutants based on multi-source remote sensing satellites, characterized in that: It includes an air pollution data acquisition unit, an air pollution data preprocessing unit, an air pollution data fusion unit, an air pollution data analysis unit and an analysis result evaluation unit; Air pollution data collection unit, used to collect air pollution related data through multiple channels; Air pollution data preprocessing unit, used for format conversion, radiation correction and geometric correction of collected air pollution related data; The air pollution data fusion unit uses principal component analysis and wavelet transform to fuse air pollution-related data collected from multiple channels; Air pollution data analysis unit builds a pollution component inversion model and analyzes pollutant concentrations by extracting and screening data features; The analysis result evaluation unit is used to evaluate the accuracy of data collection and the effectiveness of the analysis process.

2. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 1 is characterized in that: Collecting air pollution-related data includes multi-source satellite remote sensing data, ground remote sensing monitoring data, and drone remote sensing data; Multi-source satellite remote sensing data, which is obtained by accessing existing satellite platforms; Ground remote sensing monitoring data: Build ground remote sensing monitoring stations in air pollution-sensitive areas and collect corresponding ground remote sensing data through high-precision spectrum analyzers and meteorological sensors at the ground remote sensing monitoring stations; Drone remote sensing data, remote sensing data of small areas and rapid patrol remote sensing data of large areas through different types of drones.

3. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 2 is characterized in that: The air pollution data fusion unit fuses multi-source remote sensing data from satellites and drones, integrating high spatial resolution and high spectral resolution; Match ground sensor data with remote sensing images in time and space to provide multi-dimensional information for subsequent air pollution data analysis.

4. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 3 is characterized in that: The air pollution data analysis unit collects a large amount of historical remote sensing data and synchronized ground-measured pollutant concentration data to form a training data set; by extracting and screening the data features, the spectral features are used as the model input and the pollutant concentration is used as the output to train and optimize the model.

5. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 4 is characterized in that: The air pollution data analysis unit also simulates pollution transmission, obtains real-time meteorological data on wind direction, wind speed, temperature and humidity, and combines the meteorological data interface with the atmospheric diffusion model to realize pollution transmission simulation.

6. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 5 is characterized in that: Data collection accuracy assessment includes multi-source data consistency verification, data integrity check, and sensor accuracy calibration; Verify the consistency of multi-source data, comparing the monitoring results of satellite remote sensing data, ground monitoring station data and drone data in the same monitoring area and at the same time point; Data integrity check: calculate the proportion of missing data during the data collection process and set data integrity thresholds to check for data collection links that do not meet the standards; Sensor accuracy calibration: Regularly calibrate the sensors at the ground monitoring station in the laboratory, compare the measured values ​​of the sensors under standard environment with the standard values, and calculate the measurement error.

7. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 6 is characterized in that: The effectiveness evaluation of the analytical process includes the evaluation of the accuracy of pollution composition inversion, the accuracy of pollution transmission simulation and tracing, and the reliability of time series analysis; Pollutant composition inversion accuracy assessment: using an independent validation dataset to evaluate the accuracy of the inversion model. In air pollution monitoring, the pollutant concentrations inverted by the model are compared with the actual concentrations measured on the ground, and the mean absolute error and relative error indicators are calculated; Pollution transmission simulation and traceability accuracy assessment: Compare the pollution transmission simulation results with the actual monitored pollution diffusion. In air pollution scenarios, observe whether the simulated pollution transmission path is consistent with the actual monitored pollution distribution. Quantitative assessment is performed by calculating indicators such as the spatial overlap between the simulation results and the actual data. Reliability assessment of time series analysis: analyzing the time series trend of long-term monitoring data to verify whether the analysis process can accurately reflect the evolution of environmental problems.

8. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 1 is characterized in that: It also includes a visualization unit, which includes visualization of the spatial distribution of pollutant concentrations, visualization of pollution transmission dynamics, and visualization of data comparison and trends; Visualize the spatial distribution of pollutant concentrations and present the inverted pollutant concentration data in the form of thematic maps using geographic information systems; Dynamic visualization of pollution transmission: Based on the pollution transmission simulation results, dynamic animation is produced to show the diffusion process of pollutants; Data comparison and trend visualization, using line charts, bar charts and other charts to compare changes in pollutant concentrations in different time periods and different regions.

9. The environmental pollutant remote sensing monitoring system based on multi-source remote sensing satellites according to claim 1, characterized in that: It also includes a dynamic monitoring and early warning unit, which establishes a long-term remote sensing image database, compares data from different periods, and uses change detection algorithms to identify areas of environmental change; Set a pollution threshold. When the monitoring data exceeds the threshold, early warning information will be automatically generated and fed back to relevant departments in a timely manner.

Images