Sewage pipe network leakage detection method based on radar satellite

Abstract

The invention discloses a sewage pipe network leakage detection method based on a radar satellite, and the method comprises the following steps: S1, obtaining radar satellite image data according to a monitoring region, a monitoring range and monitoring time, and carrying out the preprocessing of the data; s2, based on a water cloud model, fitting is carried out by combining surface soil water content data or actually measured data of a ground station, and surface water content inversion is completed; s3, performing global statistics on monitoring area data based on an inversion result, determining a leakage monitoring threshold value, and extracting leakage risk points in a gridding manner; and S4, extracting suspected leakage points in combination with earth surface coverage and POI auxiliary information gridding. According to the method, the radar satellite image data of the monitored area is obtained, the area with the high water content is found through inversion of the surface water content, the sewage pipe network leakage risk point is extracted in a large range through the area with the high water content in combination with the surface coverage data and the POI data, and the advantage of wide satellite coverage range is fully played; and the suspected leakage point location of the sewage pipe network can be found more efficiently.

Description

Technical Field

[0001] This invention relates to the field of groundwater monitoring technology, and in particular to a method for detecting leakage in sewage pipe networks based on radar satellites. Background Technology

[0002] Wastewater pipe networks are an important component of urban infrastructure. Their main function is to collect and transport domestic sewage, industrial wastewater, and surface runoff that may occur during rainy days, so as to effectively transfer these water bodies to sewage treatment plants for treatment, thereby protecting the environment and public health. Wastewater pipe network leakage refers to the phenomenon where some sewage is lost into the soil or groundwater during transportation due to pipe ruptures, leaky joints, or seepage in the pipe walls. There are various causes of wastewater pipe network leakage, such as aging pipe materials, geological changes such as earthquakes and land subsidence, and root intrusion.

[0003] Leaks in sewage pipe networks can lead to environmental pollution, economic losses, infrastructure damage, road subsidence, foul odors, and health problems. To reduce the risks and impacts of sewage pipe network leaks, regular inspections and maintenance of the network are usually necessary. However, existing technologies lack efficient methods for detecting sewage pipe network leaks, making it difficult to identify and repair potential problems in a timely manner. Summary of the Invention

[0004] This invention discloses a method for detecting leakage in sewage pipe networks based on radar satellites, aiming to solve the technical problems in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for detecting leakage in sewage pipe networks based on radar satellites includes the following specific steps:

[0007] S1: Obtain radar satellite imagery data based on the monitoring area, monitoring range, and monitoring time, and perform preprocessing;

[0008] (1) Based on the monitoring area and monitoring time, query the coverage of L-band and C-band ALOS-2 satellite data to obtain radar satellite image data;

[0009] (2) After acquiring the raw radar satellite data, the raw data is preprocessed;

[0010] S2: Based on the water cloud model, the surface soil moisture content data from ground stations or measured surface moisture content data are fitted to complete the surface moisture content inversion of the monitoring area.

[0011] (1) Calculate the vegetation canopy water content NDWI using optical satellite remote sensing images;

[0012] (2) Construct a water cloud model to remove the influence of vegetation canopy water content on radar satellite backscattering and obtain surface soil backscattering data;

[0013] (3) Organize the measured soil moisture content data at a depth of 50cm from the ground stations in the monitoring area, and establish a fitting model by combining the measured soil moisture content data from the ground stations with the backscattering data of the surface soil.

[0014] (4) The surface soil moisture content data in the monitoring area was retrieved based on the fitted model and compared with the measured data to verify the accuracy of the fitting results;

[0015] S3: Based on the surface water content inversion results, perform global statistics on the monitoring area data, analyze the overall differences in surface water content in the area, determine the leakage monitoring threshold, and extract leakage risk points in a grid-like manner;

[0016] (1) Conduct an overall analysis of the radar satellite soil moisture content inversion results of the monitoring area, draw a numerical distribution map of surface soil moisture content in the monitoring area, calculate the maximum, minimum, median and mode, analyze the differences in surface soil moisture content in the monitoring area, and determine the threshold range of the high-value area of ​​surface soil moisture content in the monitoring area.

[0017] (2) Divide the monitoring area into a grid of 1km×1km;

[0018] (3) Extract points in grid-by-grid areas with high soil moisture content and identify them as potential leakage risk points;

[0019] S4: Combine land cover and POI auxiliary information to grid-extract suspected leakage points;

[0020] (1) Use sub-meter high spatial resolution satellite imagery to classify land use types in the monitoring area, obtain information on surface vegetation, water bodies, buildings and other areas, and form surface cover data;

[0021] (2) Using Gaode Map, Baidu Map and Tencent Map, and employing fuzzy search, we query the POIs of polluting enterprises within the monitoring area and collect the geographical coordinates and name information of the POIs;

[0022] (3) Summarize the POI information searched within the monitoring area, convert the Mars coordinate system (GCJ02) of the POI points to the CGS2000 coordinate system, and form the distribution data of suspected polluting enterprises;

[0023] (4) Collect distribution data of each community, urban village and municipal sewage pipeline within the monitoring area;

[0024] (5) Overlay the potential leakage risk points extracted in S3 with the surface cover data, suspected sewage discharge enterprise distribution data and sewage pipeline distribution data to screen out the suspected sewage pipeline leakage points with high confidence.

[0025] In a preferred embodiment, in step (1) of S1, the L-band radar has a longer wavelength and better penetration capability, which can penetrate vegetation to detect the soil moisture and structure of the lower layer, and the results of soil moisture inversion in vegetation-covered areas are better; the C-band radar has higher resolution and lower penetration capability, and is more suitable for detailed detection of surface features and reflecting ground or near-ground information, and the results of soil moisture inversion in bare soil areas are better.

[0026] In a preferred embodiment, in step (1) of S1, if the monitoring time is a historical time, the archived data is queried and the data with the most recent time interval is selected as the basic data; if the monitoring time is a future time, a shooting plan is formulated in the monitoring area based on the satellite transit situation to obtain transit data.

[0027] In a preferred embodiment, in step (2) of S1, data preprocessing includes radiometric calibration, multiview processing, filtering, DB image conversion, geocoding, and georegistration operations.

[0028] In a preferred embodiment, in step (2) of S2, the water cloud model divides the backscattering of the vegetation canopy into two parts: one part is the volume scattering caused by the vegetation canopy itself, and the other part is the surface scattering caused by the surface soil.

[0029] In a preferred embodiment, in step (3) of S2, the process of fitting the model involves selecting one or more hypothesis functions and using an optimization algorithm to find the optimal parameter values, thereby minimizing the difference between the model predictions and the actual data.

[0030] In a preferred embodiment, in step (4) of S2, if the accuracy of the fitting result is low, the established fitting model is modified.

[0031] In a preferred embodiment, in step (2) of S4, the polluting enterprises include urban domestic sewage treatment plants, centralized industrial wastewater treatment plants, heavy metal enterprises, petrochemical enterprises, pesticide enterprises, plastic enterprises, organic chemical enterprises, chemical fiber enterprises, electronic and electrical enterprises, waste disposal enterprises, coking, electroplating, and leather enterprises.

[0032] In a preferred embodiment, in step (5) of S4, potential risk points such as water areas, community green spaces, park wetlands, storage land types, and non-sewage pipeline areas are eliminated during the screening process.

[0033] As can be seen from the above, this invention establishes a method for detecting leakage in a wide-area underground sewage pipe network. By acquiring multi-sensor radar satellite image data of the monitoring area, and performing surface water content inversion after image preprocessing, areas with high surface water content are identified. By combining high surface water content areas with surface cover data and POI data, leakage risk points of underground sewage pipe networks are extracted over a large area, giving full play to the advantage of the wide coverage of satellites and more efficiently discovering suspected sewage pipe network leakage points. Attached Figure Description

[0034] Figure 1 This diagram illustrates the specific steps of a radar satellite-based method for detecting leaks in sewage pipe networks, as proposed in this invention.

[0035] Figure 2 This is a schematic diagram showing the general steps of a radar satellite-based method for detecting leakage in sewage pipe networks proposed in this invention. Detailed Implementation

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0037] Reference Figure 1-2 A method for detecting leakage in sewage pipe networks based on radar satellites includes the following specific steps:

[0038] S1: Obtain radar satellite imagery data based on the monitoring area, monitoring range, and monitoring time, and perform preprocessing;

[0039] (1) Based on the monitoring area and monitoring time, query the coverage of L-band and C-band ALOS-2 satellite data to obtain radar satellite image data;

[0040] (2) After acquiring the raw radar satellite data, the raw data is preprocessed;

[0041] S2: Based on the water cloud model, the surface soil moisture content data from ground stations or measured surface moisture content data are fitted to complete the surface moisture content inversion of the monitoring area.

[0042] (1) Calculate the vegetation canopy water content NDWI using optical satellite remote sensing images;

[0043] (2) Construct a water cloud model to remove the influence of vegetation canopy water content on radar satellite backscattering and obtain surface soil backscattering data;

[0044] (3) Organize the measured soil moisture content data at a depth of 50cm from the ground stations in the monitoring area, and establish a fitting model by combining the measured soil moisture content data from the ground stations with the backscattering data of the surface soil.

[0045] (4) The surface soil moisture content data in the monitoring area was retrieved based on the fitted model and compared with the measured data to verify the accuracy of the fitting results;

[0046] S3: Based on the surface water content inversion results, perform global statistics on the monitoring area data, analyze the overall differences in surface water content in the area, determine the leakage monitoring threshold, and extract leakage risk points in a grid-like manner;

[0047] (1) Conduct an overall analysis of the radar satellite soil moisture content inversion results of the monitoring area, draw a numerical distribution map of surface soil moisture content in the monitoring area, calculate the maximum, minimum, median and mode, analyze the differences in surface soil moisture content in the monitoring area, and determine the threshold range of the high-value area of ​​surface soil moisture content in the monitoring area.

[0048] (2) Divide the monitoring area into a grid of 1km×1km;

[0049] (3) Extract points in grid-by-grid areas with high soil moisture content and identify them as potential leakage risk points;

[0050] S4: Combine land cover and POI auxiliary information to grid-extract suspected leakage points;

[0051] (1) Use sub-meter high spatial resolution satellite imagery to classify land use types in the monitoring area, obtain information on surface vegetation, water bodies, buildings and other areas, and form surface cover data;

[0052] (2) Using Gaode Map, Baidu Map and Tencent Map, and employing fuzzy search, we query the POIs of polluting enterprises within the monitoring area and collect the geographical coordinates and name information of the POIs;

[0053] (3) Summarize the POI information searched within the monitoring area, convert the Mars coordinate system (GCJ02) of the POI points to the CGS2000 coordinate system, and form the distribution data of suspected polluting enterprises;

[0054] (4) Collect distribution data of each community, urban village and municipal sewage pipeline within the monitoring area;

[0055] (5) Overlay the potential leakage risk points extracted in S3 with the surface cover data, suspected sewage discharge enterprise distribution data and sewage pipeline distribution data to screen out the suspected sewage pipeline leakage points with high confidence.

[0056] In a preferred embodiment, in S1, the L-band radar in step (1) has a longer wavelength and better penetration capability, which can penetrate vegetation to detect the soil moisture and structure of the lower layer, and has better results for soil moisture inversion in vegetation-covered areas; the C-band radar has higher resolution and lower penetration capability, and is more suitable for detailed detection of surface features and reflecting ground or near-ground information, and has better results for soil moisture inversion in bare soil areas.

[0057] In a preferred embodiment, in step (1), if the monitoring time is a historical time, the archived data is queried and the data with the closest time interval is selected as the basic data; if the monitoring time is a future time, a shooting plan is formulated in the monitoring area based on the satellite transit situation, and transit data is obtained.

[0058] In a preferred embodiment, in step (2) of S1, data preprocessing includes radiometric calibration, multiview processing, filtering, DB image conversion, geocoding, and georegistration operations.

[0059] In a preferred embodiment, in step (2), the water cloud model divides the backscattering of the vegetation canopy into two parts: one part is the volume scattering caused by the vegetation canopy itself, and the other part is the surface scattering caused by the surface soil.

[0060] In a preferred embodiment, in S2, the process of fitting the model in step (3) involves selecting one or more hypothesis functions and using an optimization algorithm to find the optimal parameter values, thereby minimizing the difference between the model predictions and the actual data.

[0061] In a preferred embodiment, in step (4) of S2, if the accuracy of the fitting result is low, the established fitting model is modified.

[0062] In a preferred embodiment, in S4, the polluting enterprises in step (2) include urban domestic sewage treatment plants, centralized industrial wastewater treatment plants, heavy metal enterprises, petrochemical enterprises, pesticide enterprises, plastic enterprises, organic chemical enterprises, chemical fiber enterprises, electronic and electrical enterprises, waste disposal enterprises, coking, electroplating, and leather enterprises.

[0063] Heavy metal enterprises mainly include non-ferrous metal smelting, electroplating, waste battery recycling, and non-ferrous metal mining and beneficiation; petrochemical enterprises mainly include oil extraction, refining, fertilizers, synthetic materials, and pharmaceuticals; pesticide enterprises mainly include pesticide production, pesticide formulation processing, and pesticide application; plastic enterprises mainly include plastic product manufacturing and plastic recycling; organic chemical enterprises mainly include organic chemical production, dyes, pigments, coatings, and adhesives; chemical fiber enterprises mainly include chemical fiber manufacturing, dyeing and finishing, and printing and dyeing; electronics and electrical appliance enterprises mainly include electronic component manufacturing, electronic equipment manufacturing, and electronic waste dismantling; and waste disposal enterprises mainly include landfills, waste incineration power plants, and hazardous waste treatment plants.

[0064] In a preferred embodiment, in step (5), potential risk points such as water areas, community green spaces, park wetlands, storage land types, and non-sewage pipeline areas are eliminated during the screening process in step (5).

[0065] By acquiring multi-sensor radar satellite imagery data of the monitoring area, surface water content is retrieved after image preprocessing. Areas with high surface water content are identified. By combining high surface water content areas with surface cover data and POI data, risk points of underground sewage pipe network leakage are extracted over a wide range. This fully leverages the advantage of the wide coverage of satellites and more efficiently identifies suspected sewage pipe network leakage points.

[0066] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. The substitutions may be replacements of some structures, devices, or method steps, or they may be complete technical solutions. Equivalent substitutions or modifications made to the technical solutions and inventive concepts of the present invention should all be covered within the scope of protection of the present invention.

Claims

1. A method for detecting leakage in sewage pipe networks based on radar satellites, characterized in that, The specific steps include the following: S1: Obtain radar satellite imagery data based on the monitoring area, monitoring range, and monitoring time, and perform preprocessing; (1) Based on the monitoring area and monitoring time, query the coverage of L-band and C-band ALOS-2 satellite data to obtain radar satellite image data; (2) After acquiring the raw radar satellite data, the raw data is preprocessed; S2: Based on the water cloud model, the surface soil moisture content data from ground stations or measured surface moisture content data are fitted to complete the surface moisture content inversion of the monitoring area. (1) Calculate the vegetation canopy water content NDWI using optical satellite remote sensing images; (2) Construct a water cloud model to remove the influence of vegetation canopy water content on radar satellite backscattering and obtain surface soil backscattering data; (3) Organize the measured soil moisture content data at a depth of 50cm from the ground stations in the monitoring area, and establish a fitting model by combining the measured soil moisture content data from the ground stations with the backscattering data of the surface soil. (4) The surface soil moisture content data in the monitoring area was retrieved based on the fitted model and compared with the measured data to verify the accuracy of the fitting results; S3: Based on the surface water content inversion results, perform global statistics on the monitoring area data, analyze the overall differences in surface water content in the area, determine the leakage monitoring threshold, and extract leakage risk points in a grid-like manner; (1) Conduct an overall analysis of the radar satellite soil moisture content inversion results of the monitoring area, draw a numerical distribution map of surface soil moisture content in the monitoring area, calculate the maximum, minimum, median and mode, analyze the differences in surface soil moisture content in the monitoring area, and determine the threshold range of the high-value area of ​​surface soil moisture content in the monitoring area. (2) Divide the monitoring area into a grid of 1km×1km; (3) Extract points in grid-by-grid areas with high soil moisture content and identify them as potential leakage risk points; S4: Combine land cover and POI auxiliary information to grid-extract suspected leakage points; (1) Use sub-meter high spatial resolution satellite imagery to classify land use types in the monitoring area, obtain information on surface vegetation, water bodies, buildings and other areas, and form surface cover data; (2) Using Gaode Map, Baidu Map and Tencent Map, and employing fuzzy search, we query the POIs of polluting enterprises within the monitoring area and collect the geographical coordinates and name information of the POIs; (3) Summarize the POI information searched within the monitoring area, convert the Mars coordinate system (GCJ02) of the POI points to the CGS2000 coordinate system, and form the distribution data of suspected polluting enterprises; (4) Collect distribution data of each community, urban village and municipal sewage pipeline within the monitoring area; (5) Overlay the potential leakage risk points extracted in S3 with the surface cover data, suspected sewage discharge enterprise distribution data and sewage pipeline distribution data to screen out the suspected sewage pipeline leakage points with high confidence.

2. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 1, characterized in that, In step (1), the L-band radar has a longer wavelength and better penetration capability, which can penetrate vegetation to detect the soil moisture and structure of the lower layer, and the results of soil moisture inversion in vegetation-covered areas are better; the C-band radar has higher resolution and lower penetration capability, and is more suitable for detailed detection of surface features and reflecting ground or near-ground information, and the results of soil moisture inversion in bare soil areas are better.

3. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 2, characterized in that, In step (1), if the monitoring time is a historical time, the archived data is queried and the data with the closest time interval is selected as the basic data; if the monitoring time is a future time, a shooting plan is formulated in the monitoring area based on the satellite's transit situation, and transit data is obtained.

4. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 3, characterized in that, In step (2) of S1, data preprocessing includes radiometric calibration, multi-view processing, filtering, DB image conversion, geocoding, and georegistration.

5. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 1, characterized in that, In S2, the water cloud model in step (2) divides the backscattering of the vegetation canopy into two parts: one part is the volume scattering caused by the vegetation canopy itself, and the other part is the surface scattering caused by the surface soil.

6. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 5, characterized in that, In step (3) of S2, the process of fitting the model involves selecting one or more hypothesis functions and using optimization algorithms to find the optimal parameter values, thereby minimizing the difference between the model predictions and the actual data.

7. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 6, characterized in that, In step S2, if the accuracy of the fitting result is low in step (4), the established fitting model is corrected.

8. The method for detecting leakage in sewage pipe networks based on radar satellites according to claim 1, characterized in that, In step (2) of S4, the polluting enterprises include urban domestic sewage treatment plants, centralized industrial wastewater treatment plants, heavy metal enterprises, petrochemical enterprises, pesticide enterprises, plastic enterprises, organic chemical enterprises, chemical fiber enterprises, electronic and electrical enterprises, waste disposal enterprises, coking, electroplating, and leather enterprises.

9. A method for detecting leakage in a sewage pipe network based on radar satellites according to claim 8, characterized in that, In step (5) of S4, potential risk points such as water areas, community green spaces, park wetlands, storage land types, and non-sewage pipeline areas are eliminated during the screening process.

Images