A method and system for identifying urban black and odorous water bodies based on remote sensing spectrum

Abstract

The present invention relates to the field of remote sensing spectral technology, and specifically to a method and system for identifying urban black and odorous water bodies based on remote sensing spectroscopy. The method comprises the following steps: based on remote sensing satellites or unmanned aerial vehicles, infrared spectrum and visible spectrum data are acquired, the data are processed, noise and outliers in the data are eliminated, and spectral feature extraction is performed to obtain a spectral feature data set. In the present invention, the infrared and visible spectrum data collected by remote sensing satellites or unmanned aerial vehicles are combined with the urban water body data of the geographic information system to improve the dimension and quality of the data, so that the monitoring of urban black and odorous water bodies is not limited to surface coverage, but also can accurately control the sensitivity of data analysis by dynamically adjusting the spectral band weights, adapt to changing environmental conditions, and improve the recognition accuracy of various polluted water bodies. By continuously updating and optimizing the processing flow, the continuity and accuracy of long-term monitoring are ensured, effectively supporting urban water quality management and decision-making processes.

Description

Technical Field

[0001] The invention relates to the technical field of remote sensing spectroscopy, and in particular to a method and system for identifying urban black and odorous water bodies based on remote sensing spectroscopy. Background Art

[0002] Remote sensing spectroscopy is a method of using a spectrometer to detect the ground or other targets from a long distance. It obtains chemical and physical information about surface materials by analyzing the spectral characteristics of light reflected or radiated from the surface. Remote sensing spectrometers are usually installed on satellites or aircraft and can cover wide areas, thereby effectively monitoring large-scale environmental and surface changes. They are widely used in environmental monitoring, agriculture, forestry, geological exploration, urban planning and other fields.

[0003] Among them, the urban black and odorous water body identification method of remote sensing spectroscopy focuses on using remote sensing spectroscopy technology to identify and monitor black and odorous water bodies in cities. Black and odorous water bodies are usually caused by serious deterioration of water quality during urban sewage discharge, industrial wastewater discharge or natural decay, and physical and chemical changes occur. The water bodies pose a threat to the environment and public health. Through remote sensing spectroscopy technology, these polluted water bodies can be quickly and accurately identified from the air, and their pollution level and distribution can be analyzed, thereby guiding urban environmental governance and water quality improvement measures.

[0004] Existing technologies lack real-time data updates and comprehensive data analysis capabilities in the continuous monitoring of urban water bodies, and are unable to promptly detect and address emerging or sudden water quality problems. In addition, existing technologies lack effective data integration capabilities when processing and analyzing collected spectral data, making it difficult to adapt to changing urban environmental conditions, resulting in limited accuracy and timeliness of monitoring results, slow response to urban water body monitoring and management, and increased environmental risks and governance costs. Summary of the invention

[0005] In order to solve the problems that the existing technology of continuous monitoring of urban water bodies lacks real-time data update and comprehensive data analysis capabilities, and cannot timely discover and deal with new or sudden water quality problems, in addition, the existing technology lacks effective data integration capabilities when processing and analyzing the collected spectral data, and is difficult to adapt to changing urban environmental conditions, resulting in limited accuracy and timeliness of monitoring results, slow response to urban water body monitoring and management, and increased environmental risks and governance costs, the embodiment of the present invention provides a method and system for identifying urban black and odorous water bodies based on remote sensing spectroscopy. The technical solution is as follows:

[0006] On the one hand, a method for identifying urban black and odorous water bodies based on remote sensing spectroscopy is provided, comprising the following steps:

[0007] S1: Based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are obtained, the data are processed to eliminate noise and outliers in the data, and spectral features are extracted to obtain spectral feature data sets;

[0008] S2: Based on the geographic information system, the geographical location and environmental characteristic data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed by the VGG model to obtain the pollution level prediction index;

[0009] S3: Based on the pollution level prediction index, the current environmental factors recorded in the geographic information are compared, the weight of each spectral band is dynamically adjusted, the analysis error is minimized, the recognition ability of urban water body characteristics under different environmental conditions is optimized, and the data processing flow is readjusted to obtain the optimized water body recognition configuration;

[0010] S4: Based on the optimized water body identification configuration, evaluate the water body status of multiple cities, identify the pollution hot spots and pollution change trends in urban water bodies, and compare historical data to verify the accuracy of the prediction results, and obtain a pollution trend analysis log;

[0011] S5: Based on the pollution trend analysis log, regularly update environmental monitoring data and feedback information, continuously adjust the remote sensing data processing process, optimize the monitoring and identification efficiency of urban water status, and obtain water monitoring optimization results.

[0012] Optionally, the spectral feature data set includes absorption peak, emission peak, and spectral width; the pollution level prediction indicators are specifically turbidity level, pH value, and dissolved oxygen content; the optimized water body identification configuration includes adjustment parameters, perception threshold, and data collection frequency; and the pollution trend analysis log includes historical comparison results, prediction deviation, and key variable identification results.

[0013] Optionally, based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are acquired, the data are processed, noise and outliers in the data are eliminated, and spectral features are extracted to obtain spectral feature data sets in the following specific steps:

[0014] S101: Based on the data collected by remote sensing satellites or drones, synchronize the infrared spectrum and visible spectrum data, record the time and location of data collection, and generate spectrum annotation data;

[0015] S102: performing frequency filtering on the spectral annotation data, removing noise signals with abnormally high frequencies, retaining data within a key spectral range, optimizing data quality, and generating a frequency-optimized spectrum;

[0016] S103: extracting key features from the frequency-optimized spectrum, identifying peaks and valleys within key spectral bands, and quantitatively analyzing their intensities and distributions to obtain a spectral feature data set.

[0017] Optionally, based on a geographic information system, the geographical location and environmental characteristic data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed by a VGG model to obtain the pollution level prediction index in the following steps:

[0018] S201: Based on the geographic information system, locate the space of urban water bodies, analyze the geographical and environmental characteristics around the water bodies, determine the key monitoring areas, and generate the spatial characteristics of the water bodies;

[0019] S202: Integrate the water body spatial feature and spectral feature data sets, match geographic and spectral data points by linear interpolation, and verify the consistency of the data to generate a data consistency set;

[0020] S203: Based on the data consistency set, the pollution level is quantitatively analyzed through the VGG model, the spectral anomaly index of multiple regions is calculated, and the potential types and concentrations of pollutants are analyzed to obtain pollution level prediction indicators.

[0021] Optionally, based on the pollution level prediction index, the current environmental factors recorded in the geographic information are compared, the weight of each spectral band is dynamically adjusted, the analysis error is minimized, the recognition capability of urban water body characteristics under different environmental conditions is optimized, and the data processing flow is readjusted to obtain the optimized water body recognition configuration. Specifically, the steps are as follows:

[0022] S301: Based on the pollution level prediction index, current environmental factor data is compared, and by extracting real-time meteorological and water quality data, deviations from historical geographic information are corrected to generate environmental correction data;

[0023] S302: dynamically adjusting the weights of the spectral bands based on the environmental correction data, reallocating the weight ratios according to the criticality of the spectral bands, reducing data errors, matching the reflectivity changes of the spectral bands, and generating a weight adjustment configuration;

[0024] S303: Based on the weight adjustment configuration, the data processing flow is optimized, the spectral feature extraction and geographic information integration sequence is reorganized, and the deviation of the data integration process is corrected to obtain an optimized water body identification configuration.

[0025] Optionally, the weights of the spectral bands are dynamically adjusted according to the formula:

[0026]

[0027] In the formula, represents the new weight value, represents the reflectance of the current spectral band, represents the reflectance of the reference spectral band, Represents the original weight.

[0028] Optionally, based on the optimized water body identification configuration, the water body status of multiple cities is evaluated, the pollution hot spots and pollution change trends in urban water bodies are identified, and the accuracy of the prediction results is verified by comparing historical data. The steps of obtaining the pollution trend analysis log are specifically as follows:

[0029] S401: Based on the optimized water body identification configuration, a multi-city water body status assessment is performed, and through regional division and pollution level determination, multi-region pollution indexes are analyzed, and key pollution areas are identified to generate a regional pollution overview;

[0030] S402: Based on the regional pollution overview, compare and analyze pollution data with historical data, identify pollution diffusion paths and change rates, determine key pollution variables, and generate pollution diffusion analysis records;

[0031] S403: Based on the pollution diffusion analysis record, the pollution area changes and key variable information are integrated to establish a pollution trend data table and predict pollution changes to obtain a pollution trend analysis log.

[0032] Optionally, the pollution data is compared and analyzed with historical data, according to the formula:

[0033]

[0034] Calculate the rate of change of pollutant concentration in water , where Represents the current concentration of water pollutants, represents the pollutant concentration during the same period in history, Represents the number of data points to compare.

[0035] Optionally, based on the pollution trend analysis log, the environmental monitoring data and feedback information are regularly updated, the remote sensing data processing process is continuously adjusted, and the monitoring and identification efficiency of the urban water body status is optimized. The steps of obtaining the water body monitoring optimization result are specifically as follows:

[0036] S501: Based on the pollution trend analysis log, by synchronizing the newly collected remote sensing and geographic information data, checking the consistency with the existing data, and identifying environmental changes and abnormal points, an environmental synchronization record is generated;

[0037] S502: Based on the environmental synchronization record, adjust the remote sensing data processing process, update data screening and processing parameters, match new environmental data features, and obtain a remote sensing process adjustment record;

[0038] S503: Based on the remote sensing process adjustment records, the analysis depth of remote sensing data and the water body identification efficiency are optimized, and the continuity and effectiveness of the monitoring activities are verified to generate water body monitoring optimization results.

[0039] On the other hand, a system for identifying urban black and odorous water bodies based on remote sensing spectroscopy is provided, and the system is applied to a method for identifying urban black and odorous water bodies based on remote sensing spectroscopy, comprising:

[0040] The spectral data acquisition module collects infrared and visible spectrum data of urban water bodies based on remote sensing satellites or drones, performs noise reduction and outlier processing on the data, and extracts spectral features to obtain spectral feature data sets;

[0041] A geographic information integration module, based on a geographic information system, collects the location and environmental characteristics of urban water bodies, integrates them with the spectral feature data set, and analyzes the integrated data set through a VGG model to obtain a pollution level prediction index;

[0042] The pollution prediction and analysis module dynamically adjusts the weight of each spectral band based on the pollution level prediction index and the current environmental factors recorded in the geographic information, minimizes the analysis error, optimizes the recognition capability of urban water body characteristics under different environmental conditions, and obtains the optimized water body recognition configuration;

[0043] The pollution trend monitoring module, based on the optimized water body identification configuration, evaluates the pollution status of multiple urban water bodies, identifies pollution hot spots and pollution change trends, compares them with historical data, regularly updates monitoring data and feedback information, optimizes the remote sensing data processing process, and obtains water body monitoring optimization results.

[0044] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0045] The infrared and visible spectral data collected by remote sensing satellites or drones, combined with the urban water body data of the geographic information system, have improved the dimension and quality of the data, so that the monitoring of urban black and odorous water bodies is not limited to surface coverage, but can also accurately control the sensitivity of data analysis by dynamically adjusting the spectral band weights, adapt to changing environmental conditions, and improve the identification accuracy of various types of polluted water bodies. By continuously updating and optimizing the processing process, the continuity and accuracy of long-term monitoring are ensured, effectively supporting urban water quality management and decision-making processes, thereby promoting the efficiency and scientificity of urban water environment governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 It is a main step flow chart provided by an embodiment of the present invention;

[0048] Figure 2 is a flow chart of the steps of S1 of the present invention;

[0049] Figure 3 is a flow chart of the steps of S2 of the present invention;

[0050] Figure 4 is a flow chart of the steps of S3 of the present invention;

[0051] Figure 5 is a flow chart of the steps of S4 of the present invention;

[0052] Figure 6 is a flow chart of the steps of S5 of the present invention;

[0053] Figure 7 It is a system block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0055] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0056] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0057] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0058] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0059] The embodiment of the present invention provides a method for identifying urban black and odorous water bodies based on remote sensing spectroscopy. The method can be implemented by an urban black and odorous water body identification system based on remote sensing spectroscopy. The urban black and odorous water body identification system based on remote sensing spectroscopy can be a terminal or a server. Figure 1 The flowchart of the urban black and odorous water body identification method based on remote sensing spectrum is shown, and the processing flow of the method may include the following steps:

[0060] S1: Based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are obtained, the data are processed to eliminate noise and outliers in the data, and spectral features are extracted to obtain spectral feature data sets;

[0061] S2: Based on the geographic information system, the geographical location and environmental characteristics data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed through the VGG model to obtain the pollution level prediction index;

[0062] S3: Based on the pollution level prediction indicators, the current environmental factors recorded by geographic information are compared, the weight of each spectral band is dynamically adjusted to minimize the analysis error, optimize the recognition ability of urban water body characteristics under different environmental conditions, and readjust the data processing flow to obtain the optimized water body identification configuration;

[0063] S4: Based on the optimized water body identification configuration, the water body status of multiple cities is evaluated, the pollution hot spots and pollution change trends in urban water bodies are identified, and the accuracy of the prediction results is verified by comparing historical data to obtain a pollution trend analysis log;

[0064] S5: Based on the pollution trend analysis log, regularly update environmental monitoring data and feedback information, continuously adjust the remote sensing data processing process, optimize the monitoring and identification efficiency of urban water status, and obtain water monitoring optimization results.

[0065] The spectral feature data set includes absorption peak, emission peak, and spectral width. The pollution level prediction indicators are specifically turbidity level, pH value, and dissolved oxygen content. The optimized water body identification configuration includes adjustment parameters, perception threshold, and data collection frequency. The pollution trend analysis log includes historical comparison results, prediction deviation, and key variable identification results.

[0066] like Figure 2 As shown, based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are obtained, the data are processed, noise and outliers in the data are eliminated, and spectral features are extracted to obtain spectral feature data sets. The specific steps are as follows:

[0067] S101: Based on the data collected by remote sensing satellites or drones, synchronize the infrared spectrum and visible spectrum data, record the time and location of data collection, and generate spectrum annotation data;

[0068] The infrared spectrum and visible spectrum data are calibrated synchronously, and the time and place of collection are recorded at the same time. By setting the reference standard during collection, for example, the wavelength range of the infrared spectrum is set to 800-2500nm, and the visible spectrum range is set to 400-700nm, the recorded time format is the UTC time standard, and the location is marked in the WGS84 coordinate format. The spectral data is calibrated using a reference white board to eliminate the deviation caused by changes in the light source intensity. The benchmark white reflectance is set to 99% and corrected. The processed spectral data and the time and place information are uniformly encoded and stored through the spectral annotation module to form a structured spectral annotation data file.

[0069] S102: Perform frequency filtering on the spectral annotation data, remove noise signals with abnormally high frequencies, retain data within a key spectral range, optimize data quality, and generate a frequency-optimized spectrum;

[0070] A digital filter is used to remove noise signals with abnormally high frequencies. First, the frequency range of the noise signal is analyzed according to the spectral distribution of the spectral signal, and the filter range is set to 1Hz to 100Hz. The Butterworth low-pass filter is selected and the cutoff frequency is set to 80Hz. The signal is spectrally decomposed through fast Fourier transform (FFT), and the frequency components exceeding the set range are reset to zero. The signal is then reconstructed into time domain data through inverse Fourier transform, and the mean square error of the reconstructed signal is calculated to ensure signal quality optimization, and a frequency-optimized spectral data file is generated.

[0071] S103: extract key features from the frequency-optimized spectrum, identify peaks and valleys in key spectral bands, and quantitatively analyze their intensity and distribution to obtain a spectral feature data set;

[0072] First, determine the key spectral band range. For example, based on the reflectance spectrum of water body characteristics, select 420-460nm and 900-950nm as the key analysis range, segment the spectral data, and use the convolution method to identify the peaks and valleys in each segment. Quantitative data is obtained by calculating its spectral intensity and position distribution. The spectral intensity is calculated by summing the spectral reflectance within a specific wavelength range, and the relative position distribution of valleys and peaks is analyzed by the difference method. Finally, the processed data are summarized to form a spectral feature data set, which includes peak intensity, valley depth, and distribution information within the key spectral band.

[0073] like Figure 3As shown in the figure, based on the geographic information system, the geographical location and environmental characteristic data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed by the VGG model to obtain the pollution level prediction index. The specific steps are as follows:

[0074] S201: Based on the geographic information system, locate the space of urban water bodies, analyze the geographical and environmental characteristics around the water bodies, determine the key monitoring areas, and generate the spatial characteristics of the water bodies;

[0075] Locate the space of urban water bodies, use the urban water body vector data layer in the geographic information system, and combine it with the digital elevation model (DEM) to determine the water body distribution area. Through terrain analysis, identify the geographical features around the water body, including slope and elevation changes. Further call the land use layer to extract the types of human activities around the water body, such as industrial areas, living areas and farmland distribution. Combine meteorological data to analyze environmental parameters such as rainfall and evaporation near the water body. Use buffer analysis to generate monitoring areas within a certain range from the water body boundary. Combine weight factors such as water body area and human activity intensity to prioritize the monitoring areas, and finally generate a spatial dataset annotated with the spatial distribution and environmental characteristics of water bodies.

[0076] S202: Integrate the water body spatial characteristics and spectral characteristics datasets, match the geographic and spectral data points through linear interpolation, and verify the consistency of the data to generate a data consistency set;

[0077] The spatial coordinates recorded in the water body spatial characteristics are compared and matched with the sampling position coordinates in the spectral data. The linear interpolation method is used to interpolate the spatial coordinates and the spectral data coordinates. The nearest neighbor interpolation is used to determine the connection relationship between the matching points. The error analysis module is called to calculate the matching error, and the point pairs whose errors exceed the set threshold are eliminated. The cleaned matching data are regenerated through the data screening module. After verifying the consistency of the spectral data and the spatial feature data, a unified geographic spectral data pair is formed.

[0078] S203: Based on the data consistency set, the pollution level is quantitatively analyzed through the VGG model, the spectral anomaly index of multiple regions is calculated, and the potential type and concentration of pollutants are analyzed to obtain the pollution level prediction index;

[0079] The pollution level is quantitatively analyzed using the VGG model. First, the spectral data of each area in the consistency data set are normalized, and the spectral reflectance of the specific pollution characteristic band is extracted. Each monitoring area is scored by calculating the spectral anomaly index. The anomaly index is calculated based on the reflectance deviation of each band. The pollutant feature database is called to match the spectral anomalies in the area with the known pollutant types. The pollutant concentration is estimated in combination with the chemical analysis data. The pollution score and pollutant concentration distribution of each area are integrated to generate a pollution level prediction indicator for each monitoring area.

[0080] like Figure 4 As shown in the figure, based on the pollution level prediction index, the current environmental factors recorded by geographic information are compared, the weight of each spectral band is dynamically adjusted, the analysis error is minimized, the recognition ability of urban water body characteristics under different environmental conditions is optimized, and the data processing flow is readjusted. The specific steps to obtain the optimized water body identification configuration are as follows:

[0081] S301: Based on the pollution level prediction index, the current environmental factor data is compared, and the deviation from the historical geographic information is corrected by extracting the real-time meteorological and water quality data to generate environmental correction data;

[0082] Compare the current environmental factor data, extract the real-time meteorological data of the current time period, including temperature, humidity and rainfall, call the surface water quality monitoring system to obtain the real-time water quality data of the current water body, such as dissolved oxygen, ammonia nitrogen and chemical oxygen demand, compare and analyze the real-time meteorological data with the data of the corresponding time period in the historical geographic information, correct the deviation by calculating the difference between the current data and the historical data, apply the linear deviation model to adjust the error value in the historical record, and integrate the corrected data to generate a standardized environmental correction data set.

[0083] S302: dynamically adjusting the weights of the spectral bands based on the environmental correction data, reallocating the weight ratios according to the criticality of the spectral bands, reducing data errors, matching the reflectivity changes of the spectral bands, and generating weight adjustment configurations;

[0084] Dynamically adjust the weights of the spectral bands according to the formula:

[0085]

[0086] In the formula, represents the new weight value, represents the reflectance of the current spectral band, represents the reflectance of the reference spectral band, represents the original weight;

[0087] To update the spectral band weights to match the current spectral data characteristics, first compare the current spectral band reflectance with a set reference reflectance. If the current reflectance is 0.5, the reference reflectance is set to 0.45, and the original weight is 1.0, then calculate the new weight according to the formula:

[0088]

[0089] This result shows that according to the current environmental changes, the original weights have been increased by about 11%, helping to reduce errors in data processing and more accurately match the actual reflectance changes of spectral bands.

[0090] S303: Based on the weight adjustment configuration, the data processing flow is optimized, the spectral feature extraction and geographic information integration sequence is reorganized, and the deviation of the data integration process is corrected to obtain an optimized water body identification configuration;

[0091] Optimize the data processing process, reorder the order of spectral feature extraction and geographic information integration, analyze the average time consumption of each feature processing step, process the time-consuming steps in advance to optimize the overall processing efficiency, and reduce errors by recalculating interpolation weights and adjusting matching accuracy for data points with large deviations during the data integration process. Finally, the optimized data processing process will generate a new water body identification profile for further application and analysis.

[0092] like Figure 5 As shown in the figure, based on the optimized water body identification configuration, the water body status of multiple cities is evaluated, the pollution hot spots and pollution change trends in urban water bodies are identified, and the accuracy of the prediction results is verified by comparing historical data. The specific steps for obtaining the pollution trend analysis log are as follows:

[0093] S401: Based on the optimized water body identification configuration, multi-city water body status assessment is carried out, multi-region pollution index is analyzed through regional division and pollution level determination, key pollution areas are identified, and regional pollution overview is generated;

[0094] The water area of ​​each city is divided into several standard cells, and the area of ​​each cell is fixed at 1 square kilometer. The water body reflectivity and pollutant concentration data are called to calculate the pollution level of each cell one by one. The pollution level is divided into light, moderate and heavy pollution according to the classification standard. The comprehensive pollution index of each area is calculated based on the cell pollution index. The areas with pollution index higher than the set threshold are marked as key pollution areas. The pollution index and marking information of all areas are summarized to generate an overview of the overall regional pollution.

[0095] S402: Based on the regional pollution overview, compare and analyze pollution data with historical data, identify pollution diffusion paths and change rates, determine key pollution variables, and generate pollution diffusion analysis records;

[0096] Compare and analyze pollution data with historical data, according to the formula:

[0097]

[0098] Calculate the rate of change of pollutant concentration in water , where represents the current concentration of water pollutants (such as lead or nitrate concentrations), represents the pollutant concentration during the same period in history, Represents the number of data points for comparison;

[0099] In order to quantify the change in the concentration of water pollutants, it is necessary to calculate the difference between the current and historical data and find the average. The current measured lead concentration in the water is 0.10mg / L, 0.12mg / L and 0.15mg / L, and the historical data for the same period is 0.08mg / L, 0.09mg / L and 0.12mg / L, that is:

[0100] mg / L;

[0101] mg / L;

[0102] , calculated according to the formula:

[0103]

[0104]

[0105] The results show that during the analyzed period, the average lead concentration in water bodies for each data point increased by 0.027 mg / L compared with historical data, indicating that the concentration of lead in water bodies has a tendency to increase, providing data support for identifying pollution diffusion paths and key pollution variables.

[0106] S403: Based on the pollution diffusion analysis record, the pollution area changes and key variable information are integrated to establish a pollution trend data table and predict pollution changes to obtain a pollution trend analysis log;

[0107] Extract time series data for each key pollution area, calculate the change rate of pollution variables in each time period, analyze the trend of the change rate over time, mark the time point when the change rate exceeds the set threshold as the key event node, integrate the pollution type and concentration of the event node into a trend data table, predict the pollution change trend in a specific time period in the future through curve fitting method, and generate a pollution trend analysis log by summarizing the trend data and analysis records.

[0108] like Figure 6 As shown in the figure, based on the pollution trend analysis log, the environmental monitoring data and feedback information are regularly updated, the remote sensing data processing process is continuously adjusted, and the monitoring and identification efficiency of urban water status is optimized. The specific steps to obtain the water monitoring optimization results are as follows:

[0109] S501: Based on the pollution trend analysis log, by synchronizing the newly collected remote sensing and geographic information data, checking the consistency with the existing data, and identifying environmental changes and anomalies, an environmental synchronization record is generated;

[0110] By synchronizing newly collected remote sensing and geographic information data, extracting key band information in remote sensing images, including infrared and visible light bands, matching spectral data with existing water body distribution data in the geographic information system, and comparing the differences between water body boundaries in remote sensing data and boundaries recorded in geographic information, marking abnormal areas caused by environmental changes or data errors, calling environmental monitoring equipment to extract real-time meteorological data and pollutant concentration information related to abnormal areas, and verifying abnormal points one by one, eliminating abnormal points that cannot be matched or whose errors exceed the set threshold, and integrating the proofread data to generate environmental synchronization records.

[0111] S502: Based on the environmental synchronization record, adjust the remote sensing data processing process, update the data screening and processing parameters, match the new environmental data characteristics, and obtain the remote sensing process adjustment record;

[0112] By analyzing the spectral data deviation in the synchronous records, resetting the threshold range for spectral data screening, extracting the reflectivity of the pollution characteristic band and analyzing its changing trend, the screening module in the data processing flow is updated to a dynamic threshold-based mode, and adjusting the spectral weight parameters of image processing according to the real-time collected environmental data. The reference value in the boundary extraction algorithm is optimized, and the boundary data of the geographic information system is compared with the adjusted spectral reflectivity. A new data screening and processing parameter configuration file is generated, and the remote sensing process adjustment record is generated after integrating the adjustment content.

[0113] S503: Based on the remote sensing process adjustment records, optimize the analysis depth of remote sensing data and the efficiency of water body identification, verify the continuity and effectiveness of monitoring activities, and generate water body monitoring optimization results;

[0114] The optimized spectral weight parameters are applied to the full-band spectral data analysis, the pollution characteristic areas in the spectral data are re-divided, and each area is graded and extracted. The processing time of each module in the extraction process is analyzed and the module calling order is optimized. By introducing a parallel computing structure to the pollution index calculation module, the calculation speed of the regional pollution level is improved, the data continuity and the execution stability of each step in the monitoring activities are verified, and the execution results of each verification are recorded and integrated into the water body monitoring optimization results.

[0115] like Figure 7 As shown, a system for identifying urban black and smelly water bodies based on remote sensing spectroscopy includes:

[0116] The spectral data acquisition module collects infrared and visible spectrum data of urban water bodies based on remote sensing satellites or drones, performs noise reduction and outlier processing on the data, and extracts spectral features to obtain spectral feature data sets;

[0117] The geographic information integration module collects the location and environmental characteristics of urban water bodies based on the geographic information system, integrates them with the spectral feature data set, and analyzes the integrated data set through the VGG model to obtain the pollution level prediction index;

[0118] The pollution prediction and analysis module dynamically adjusts the weight of each spectral band based on the pollution level prediction index and the current environmental factors recorded in the geographic information, minimizes the analysis error, optimizes the recognition ability of urban water body characteristics under different environmental conditions, and obtains the optimized water body recognition configuration;

[0119] The pollution trend monitoring module, based on the optimized water body identification configuration, evaluates the pollution status of multiple urban water bodies, identifies pollution hotspots and pollution change trends, compares them with historical data, regularly updates monitoring data and feedback information, optimizes the remote sensing data processing process, and obtains water body monitoring optimization results.

[0120] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying urban black and odorous water bodies based on remote sensing spectroscopy, characterized in that: The method comprises: Based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are obtained, the data are processed to eliminate noise and outliers in the data, and spectral features are extracted to obtain spectral feature data sets; Based on the geographic information system, the geographical location and environmental characteristic data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed by the VGG model to obtain the pollution level prediction index; Based on the pollution level prediction index, the current environmental factors recorded in the geographic information are compared, the weight of each spectral band is dynamically adjusted to minimize the analysis error, optimize the recognition ability of urban water body characteristics under different environmental conditions, and readjust the data processing flow to obtain an optimized water body recognition configuration; Based on the optimized water body identification configuration, the water body status of multiple cities is evaluated, the pollution hot spots and pollution change trends in urban water bodies are identified, and the accuracy of the prediction results is verified by comparing historical data to obtain a pollution trend analysis log; Based on the pollution trend analysis log, the environmental monitoring data and feedback information are regularly updated, the remote sensing data processing flow is continuously adjusted, the monitoring and identification efficiency of the urban water body status is optimized, and the water body monitoring optimization result is obtained.

2. The method for identifying urban black and odorous water bodies based on remote sensing spectroscopy according to claim 1 is characterized in that: The spectral feature data set includes absorption peak, emission peak, and spectral width. The pollution level prediction indicators are specifically turbidity level, pH value, and dissolved oxygen content. The optimized water body identification configuration includes adjustment parameters, perception threshold, and data collection frequency. The pollution trend analysis log includes historical comparison results, prediction deviation, and key variable identification results.

3. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 1 is characterized in that: Based on remote sensing satellites or drones, infrared spectrum and visible spectrum data are obtained, the data are processed, noise and outliers in the data are eliminated, and spectral features are extracted. The specific steps to obtain the spectral feature data set are as follows: Based on the data collected by remote sensing satellites or drones, the infrared spectrum and visible spectrum data are synchronously calibrated, and the time and location of data collection are recorded to generate spectrum annotation data; Performing frequency filtering on the spectral annotation data to remove noise signals with abnormally high frequencies, retaining data within a critical spectral range, optimizing data quality, and generating a frequency-optimized spectrum; Key features are extracted from the frequency-optimized spectrum, peaks and valleys within key spectral bands are identified, and their intensities and distributions are quantitatively analyzed to obtain a spectral feature data set.

4. The method for identifying urban black and odorous water bodies based on remote sensing spectroscopy according to claim 1 is characterized in that: Based on the geographic information system, the geographical location and environmental characteristic data of urban water bodies are collected, integrated with the spectral characteristic data set, and the integrated data set is analyzed by the VGG model to obtain the pollution level prediction index. The specific steps are as follows: Based on the geographic information system, locate the space of urban water bodies, analyze the geographical and environmental characteristics around the water bodies, determine the key monitoring areas, and generate the spatial characteristics of the water bodies; Integrate the water body spatial characteristics and spectral characteristics data sets, match geographic and spectral data points by linear interpolation, and verify the consistency of the data to generate a data consistency set; Based on the data consistency set, the pollution level is quantitatively analyzed through the VGG model, the spectral anomaly index of multiple regions is calculated, and the potential types and concentrations of pollutants are analyzed to obtain pollution level prediction indicators.

5. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 1 is characterized in that: Based on the pollution level prediction index, the current environmental factors recorded in the geographic information are compared, the weight of each spectral band is dynamically adjusted, the analysis error is minimized, the recognition ability of urban water body characteristics under different environmental conditions is optimized, and the data processing flow is readjusted to obtain the optimized water body identification configuration steps as follows: Based on the pollution level prediction index, current environmental factor data are compared, and environmental correction data are generated by extracting real-time meteorological and water quality data and correcting deviations from historical geographic information; Based on the environmental correction data, dynamically adjust the weights of the spectral bands, redistribute the weight ratios according to the criticality of the spectral bands, reduce data errors, and match the reflectivity changes of the spectral bands to generate a weight adjustment configuration; Based on the weight adjustment configuration, the data processing flow is optimized, the spectral feature extraction and geographic information integration sequence is reorganized, and the deviation of the data integration process is corrected to obtain an optimized water body identification configuration.

6. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 5 is characterized in that: Dynamically adjust the weights of the spectral bands according to the formula: ； In the formula, represents the new weight value, represents the reflectance of the current spectral band, represents the reflectance of the reference spectral band, Represents the original weight.

7. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 1 is characterized in that: Based on the optimized water body identification configuration, the water body status of multiple cities is evaluated, the pollution hot spots and pollution change trends in urban water bodies are identified, and the accuracy of the prediction results is verified by comparing historical data. The specific steps for obtaining the pollution trend analysis log are as follows: Based on the optimized water body identification configuration, multi-city water body status assessment is performed, multi-region pollution index is analyzed through regional division and pollution level determination, key pollution areas are identified, and regional pollution overview is generated; Based on the regional pollution overview, compare and analyze pollution data with historical data, identify pollution diffusion paths and change rates, determine key pollution variables, and generate pollution diffusion analysis records; Based on the pollution diffusion analysis record, the pollution area changes and key variable information are integrated, a pollution trend data table is established and pollution changes are predicted to obtain a pollution trend analysis log.

8. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 7 is characterized in that: Compare and analyze the pollution data with historical data, according to the formula: ； Calculate the rate of change of pollutant concentration in water , where Represents the current concentration of water pollutants, represents the pollutant concentration during the same period in history, Represents the number of data points to compare.

9. The method for identifying urban black and odorous water bodies based on remote sensing spectrum according to claim 1 is characterized in that: Based on the pollution trend analysis log, the environmental monitoring data and feedback information are regularly updated, the remote sensing data processing process is continuously adjusted, and the monitoring and identification efficiency of the urban water body status is optimized. The specific steps for obtaining the water body monitoring optimization results are as follows: Based on the pollution trend analysis log, by synchronizing newly collected remote sensing and geographic information data, checking consistency with existing data, and identifying environmental changes and anomalies, an environmental synchronization record is generated; Based on the environmental synchronization record, adjust the remote sensing data processing process, update data screening and processing parameters, match new environmental data features, and obtain remote sensing process adjustment records; Based on the remote sensing process adjustment records, the analysis depth of remote sensing data and the water body identification efficiency are optimized, and the continuity and effectiveness of monitoring activities are verified to generate water body monitoring optimization results.

10. A system for identifying urban black and odorous water bodies based on remote sensing spectroscopy, wherein the system for identifying urban black and odorous water bodies based on remote sensing spectroscopy is used to implement the method for identifying urban black and odorous water bodies based on remote sensing spectroscopy as claimed in any one of claims 1 to 9, characterized in that: The system comprises: The spectral data acquisition module collects infrared and visible spectrum data of urban water bodies based on remote sensing satellites or drones, performs noise reduction and outlier processing on the data, and extracts spectral features to obtain spectral feature data sets; A geographic information integration module, based on a geographic information system, collects the location and environmental characteristics of urban water bodies, integrates them with the spectral feature data set, and analyzes the integrated data set through a VGG model to obtain a pollution level prediction index; The pollution prediction and analysis module dynamically adjusts the weight of each spectral band based on the pollution level prediction index and the current environmental factors recorded in the geographic information, minimizes the analysis error, optimizes the recognition capability of urban water body characteristics under different environmental conditions, and obtains the optimized water body recognition configuration; The pollution trend monitoring module, based on the optimized water body identification configuration, evaluates the pollution status of multiple urban water bodies, identifies pollution hot spots and pollution change trends, compares them with historical data, regularly updates monitoring data and feedback information, optimizes the remote sensing data processing process, and obtains water body monitoring optimization results.

Images