Surveying and mapping method based on remote sensing big data analysis

Abstract

The invention discloses a surveying and mapping method based on remote sensing big data analysis, and relates to the technical field of remote sensing big data. During operation of the system, images and spectral data of a target water body area are collected through satellite remote sensing, unmanned aerial vehicle remote sensing or a ground sensor, the collected remote sensing data are preprocessed, and the target water body area is obtained through waveband combination or spectral line analysis; the method comprises the following steps: extracting characteristic parameters of a water body by utilizing spectral information in remote sensing data, carrying out multi-dimensional analysis on field data, calculating to obtain a water body turbidity coefficient Ct, an algal bloom coefficient Ca and an oil pollution coefficient Co, and analyzing the influence of potential pollution sources, agricultural runoff and industrial wastewater discharge on the water body by combining the remote sensing data and geographic information. And performing spatial-temporal change analysis on the water body pollution condition, identifying the trend of pollutant expansion or degradation, and based on the results of pollution assessment and spatial-temporal analysis, comparing the comprehensive water quality index WQI with a preset threshold to generate water quality level early warning information.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing big data, and specifically to a mapping method based on remote sensing big data analysis. Background Art

[0002] Remote sensing big data technology is an important means of collecting and processing information related to the Earth's surface and atmosphere through various remote sensing devices such as satellites, unmanned aerial vehicles, and ground sensors. In recent years, due to its characteristics such as wide spatial coverage, high temporal resolution, and automated data acquisition, remote sensing technology has been widely applied in the field of environmental monitoring. In terms of water body monitoring, remote sensing data can achieve water quality monitoring of water bodies such as lakes, rivers, and oceans through optical, thermal infrared, and radar technologies, covering comprehensive collection and analysis of parameters such as water body color, optical reflectance, and temperature, so as to evaluate the pollution status of water bodies, such as the frequency of occurrence of algal blooms, abnormal changes in turbidity, and the scope and concentration of oil pollution. This technology has demonstrated unique advantages in water quality dynamic monitoring and pollution early warning.

[0003] Existing water quality monitoring methods mainly rely on ground sampling and laboratory analysis. Although the data accuracy is high, they have disadvantages such as limited sampling point distribution, insufficient spatial coverage, and poor dynamics. At the same time, due to the low efficiency of manual sampling and the difficulty of real-time data update, they are not suitable for sudden pollution events or large-area water body monitoring. This limitation makes it difficult to detect and respond to abnormal situations of water pollution diffusion in a timely manner. For example, the outbreak of algal blooms often spreads rapidly in a short time due to excessive nitrogen and phosphorus concentrations, but traditional monitoring methods cannot capture its diffusion speed and coverage, thus increasing the risk of water body hypoxia and ecological deterioration. Similarly, for water quality changes caused by high turbidity or oil pollution events, if not evaluated and warned in a timely manner, it may cause irreversible damage to the aquatic biological habitat and drinking water resources. These abnormal effects not only affect the balance of the ecosystem, but also increase the difficulty and cost of pollution control, seriously restricting the sustainable utilization of water resources. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a mapping method based on remote sensing big data analysis, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A mapping method based on remote sensing big data analysis, including the following steps,

[0006] Step 1: Collect image and spectral data of the target water body area through satellite remote sensing, unmanned aerial vehicle remote sensing, or ground sensors, including data on the color, temperature, and optical reflectance of the water body;

[0007] Step 2: Perform radiometric correction, atmospheric correction, and geometric correction on the collected remote sensing data, remove noise, and ensure the accuracy and consistency of the data;

[0008] Step 3: Extract the characteristic parameters of water bodies, including algal blooms, turbidity, and oil pollution concentration, from the spectral information in the remote sensing data through band combination or spectral line analysis, extract, analyze, and model the characteristics of water bodies, and perform inversion and correction of water quality parameters in the remote sensing image through multiple regression analysis or machine learning algorithms. After performing multi-dimensional analysis on the on-site data, calculate and obtain: water body turbidity coefficient Ct, algal bloom coefficient Ca, and oil pollution coefficient Co;

[0009] Step 4: Combine remote sensing data with geographical information, including basin information and industrial emission areas, analyze the impact of potential pollution sources, agricultural runoff, and industrial wastewater emissions on water bodies, and use the change detection method of remote sensing images to identify the distribution of pollutants in water bodies, including detecting the diffusion of oil pollution and algal bloom pollutants;

[0010] Step 5: Conduct spatio-temporal variation analysis of water body pollution conditions, identify the trends of pollutant expansion or degradation, and pollution changes under different seasons or weather conditions;

[0011] Step 6: Based on the results of pollution assessment and spatio-temporal analysis, generate water quality level warning information by comparing the comprehensive water quality index WQI with a preset threshold, and provide data support for relevant management departments to formulate pollution control or prevention measures.

[0012] Preferably, Step 1 includes:

[0013] Collect image data of the target water body area through satellite remote sensing, UAV remote sensing, or ground sensor devices, covering the color, texture, and spatial distribution information of the water body, providing the visual characteristics of the water body, and being able to initially identify the appearance and pollution degree of the water body;

[0014] Collect the optical reflectance data of the water body through multi-spectral or hyperspectral remote sensing sensors, providing the reflection characteristic information of the water body surface and the underlying water body substances. The key spectral bands include green light, red light, and near-infrared;

[0015] Collect the temperature data of the water body through infrared remote sensing technology or water temperature sensors. The water temperature information has a direct impact on the identification of pollutants, oil pollution, and algal blooms because different pollutants have different effects on the water temperature, and the change in water temperature reflects potential pollution areas or the self-purification ability of the water body;

[0016] Collect the chlorophyll a concentration Chl-a, the maximum chlorophyll a concentration Chl-amax in the reference water area, the cyanobacteria biomass Cb, the maximum cyanobacteria biomass Cbmax in the reference water area, and the optical reflectance Rλ through a multispectral or hyperspectral remote sensing sensor;

[0017] Measure through a water quality sensor, a portable turbidimeter, and the flow monitoring equipment of a ground monitoring station to obtain the water turbidity Turbidity, the standard turbidity Turbidity of the reference area ref , the total suspended solids concentration TSS, and the total suspended solids concentration TSSref in the reference water area;

[0018] Use the synthetic aperture radar SAR remote sensing data Sentinel-1 and multispectral data in combination to obtain the spectral absorption characteristics, and use a ground oil pollution detector and an infrared spectrometer to obtain the oil film coverage area A oil , the maximum oil pollution coverage area A in the reference water area oilmax , the reflection intensity I of the oil film at a specific spectral wavelength λoil , the maximum reflection intensity I without an oil film in the reference area λmax ;

[0019] Obtain the water surface temperature WST of the water body and the water surface temperature WST of the oil-free sewage area through a thermal infrared remote sensing device and a thermal infrared sensor carried on MODIS or an unmanned aerial vehicle, and use a thermometer for auxiliary collection and calibration. ref , and use a thermometer for auxiliary collection and calibration.

[0020] Preferably, step two includes:

[0021] Correct the radiation error in the remote sensing image. By eliminating the errors caused by the sensor, solar radiation, and terrain factors, ensure that the radiation value of each pixel in the remote sensing image reflects the true ground object characteristics, improve the accuracy of the data, remove the influence of the atmosphere on the remote sensing image, including atmospheric scattering and absorption effects, and ensure that the spectral information of the data can accurately reflect the spectral characteristics of the ground substances. By performing geometric correction on the remote sensing data, eliminate the geometric distortion caused by the satellite or sensor position, tilt angle, and the earth's curvature factors. The geometric correction ensures that each pixel in the remote sensing image corresponds precisely to the geographic coordinate system.

[0022] Preferably, step three includes:

[0023] Extract the key characteristic parameters of the water body, including algal blooms, turbidity, and oil pollution concentration, through band combination or spectral line analysis, using the spectral information in the remote sensing data. By analyzing the spectral reflectance data of different bands, extract the spectral characteristics related to the water pollutant concentration and generate a preliminary estimated value of the water quality parameters;

[0024] Using the multiple regression analysis method, the spectral information in the remote sensing image is combined with the ground monitoring data to establish an inversion model. Through this model, the spectral characteristics in the remote sensing data are converted into water quality parameters, and after calculation, the turbidity coefficient Ct, algal bloom coefficient Ca, oil pollution coefficient Co, and comprehensive water quality index WQI of the water body are obtained, supplementing the deficiencies of the ground data;

[0025] Using machine learning algorithms, including support vector machines, random forests, and neural networks, to invert and correct the water quality parameters in the remote sensing image. Through the training dataset, the machine learning model can automatically identify the pollutant distribution in the water body.

[0026] Preferably, step three further includes:

[0027] The turbidity coefficient Ct of the water body is obtained by the following formula:

[0028]

[0029] In the formula, Turbidity represents the turbidity of the water body, Turbidity ref represents the standard turbidity of the reference area, TSS represents the total suspended solids concentration of the water body, TSS ref represents the total suspended solids concentration in the reference water area, and x1 and x2 respectively represent the weight values of each coefficient, and β1 and β2 respectively represent the fitting exponents, reflecting the influence of different types of suspended solids on turbidity.

[0030] Preferably, the algal bloom coefficient Ca is obtained by the following formula:

[0031]

[0032] In the formula, Chl-a represents the chlorophyll a concentration in the water body, Chl-a max represents the maximum chlorophyll a concentration in the reference water area, Cb represents the cyanobacteria biomass, Cb max represents the maximum cyanobacteria biomass in the reference water area, Rλ represents the optical reflectance, w1 and w2 respectively represent the weight values of each parameter, and α1 and α2 respectively represent the spectral response exponents, adjusting the sensitivity of the spectral reflectance characteristics to algae.

[0033] Preferably, the oil pollution coefficient Co is obtained by the following formula:

[0034]

[0035] In the formula, Aoil represents the area covered by the oil film, A oilmax represents the maximum coverage area of oil pollution in the reference water area, I λoil represents the reflection intensity of the oil film at a specific spectral wavelength, Iλmax represents the maximum reflection intensity without oil film in the reference area, WST represents the temperature of the water surface, and WST ref represents the surface temperature of the oil-free sewage area. v1, v2, and v3 respectively represent the weight values of each parameter, and γ1, γ2, and γ3 are exponential fitting coefficients to adjust the sensitivity of each parameter to oil pollution;

[0036] The comprehensive water quality index WQI is calculated and obtained through the following formula:

[0037]

[0038] In the formula, Ct represents the turbidity coefficient of the water body, Ca represents the algal bloom coefficient, Co represents the oil pollution coefficient, and n1, n2, and n3 represent the weight coefficients of each coefficient.

[0039] Preferably, step four includes:

[0040] Combining remote sensing data with geographic information system GIS technology to analyze the location of potential pollution sources and their impact on the water body. By analyzing basin information, industrial emission areas, and agricultural runoff geographical factors, identify pollution sources and evaluate the degree of their impact on water pollution;

[0041] Adopt the remote sensing image change detection method to monitor and identify the spatial distribution of water pollutants. By comparing remote sensing images of different periods, detect the diffusion situation and change trend of oil pollution and algal bloom pollutants, and provide support for pollutant control and treatment.

[0042] Preferably, step five includes:

[0043] Through the spatio-temporal sequence analysis of water pollution data, identify the trend of pollutant expansion or degradation. Combining historical data and real-time data, evaluate the dynamic changes of pollutants under different seasons and different meteorological conditions, and reveal the temporal and spatial characteristics of water quality changes;

[0044] By analyzing the seasonal changes in water pollution, identify the water quality fluctuations caused by seasonal changes, including precipitation and temperature changes. According to the seasonal change trend, provide targeted strategies for water quality treatment and optimize pollution control measures;

[0045] By establishing a dynamic model of pollutants and combining the physical processes of water body flow, sedimentation, and diffusion, simulate the migration and transformation of pollutants in the water body. Through these models, real-time predict the changes of pollutants in the water body and give early warnings of future pollution trends.

[0046] Preferably, step six includes:

[0047] By comparing the comprehensive water quality index WQI with a preset pollution threshold, the severity of water body pollution is judged. When the water quality index exceeds the preset threshold, the system will automatically generate a water quality warning message to provide timely pollution warnings for the management department;

[0048] The turbidity coefficient Ct of the water body is compared with a preset standard threshold U:

[0049] When the turbidity coefficient Ct of the water body ≤ the preset standard threshold U, the water quality is good, the concentration of suspended solids in the water body is within the normal range, the ecosystem is not affected, and the agricultural runoff, industrial wastewater discharge, and surface scouring caused by rainfall within the basin are regularly monitored to avoid an increase in turbidity;

[0050] When the turbidity coefficient Ct of the water body > the preset standard threshold U, the turbidity of the water body exceeds the preset threshold, indicating that the turbidity of the water body has abnormally increased. High-concentration suspended particles will cause ecological problems, including reducing the photosynthesis efficiency of aquatic plants and endangering the fish habitat environment. At the same time, it indicates that surface runoff carries pollutants, including nutrients, pathogens, or toxic substances. Control the amount and timing of fertilization, build rainwater collection and purification systems to reduce the suspended particles brought into the water body during rainfall, and build sedimentation tanks or constructed wetlands in the water body to remove suspended particles by natural sedimentation and plant filtration;

[0051] The algal bloom coefficient Ca is compared with a preset standard threshold P:

[0052] When the algal bloom coefficient Ca ≤ the preset standard threshold P, there is no abnormal proliferation of algae in the water body, and the ecosystem is in a healthy state. Reduce the use of chemical fertilizers or build buffer zones, promote sewage treatment facilities in the coastal areas, avoid direct discharge of domestic sewage into the water body, maintain the natural fluidity of the water body, increase the river flow, and plant aquatic plants to competitively absorb nutrients to reduce the chance of algae reproduction;

[0053] When the algal bloom coefficient Ca > the preset standard threshold P, there is abnormal proliferation of algae in the water body, resulting in an ecological crisis of hypoxia and fish death in the water body and affecting the water body function. Carry out nitrogen and phosphorus interception measures for agricultural non-point source pollution, introduce eco-friendly algal control agents or closed floating islands into the water body to limit the growth of algae, and use aeration devices to increase the dissolved oxygen concentration of the water body;

[0054] The oil pollution coefficient Co is compared with a preset standard threshold R:

[0055] When the oil pollution coefficient Co ≤ the preset standard threshold R, the water body is not significantly polluted by oil, and the water ecosystem and water body use function are not significantly affected. Install remote sensing monitoring equipment to regularly track the distribution of oil films, and set up oil spill interception devices in the coastal areas or waterways to reduce the spread of oil pollution;

[0056] When the oil pollution coefficient Co > the preset standard threshold R, the oil pollution on the water surface is obvious, resulting in damage to the ecosystem, asphyxiation of aquatic organisms or damage to the ecological chain. At the same time, it affects the use function of the water body. Use oil-absorbing devices and oil spill cleanup ships to promptly remove the oil film on the water surface, and put in decomposable microorganisms or bioenzymes to accelerate the degradation of oil pollution, and repair the water ecosystem in the polluted area, including reconstructing wetlands, vegetation or putting in water purification plants.

[0057] The present invention provides a mapping method based on remote sensing big data analysis, which has the following beneficial effects:

[0058] (1) When the system runs, through satellite remote sensing, UAV remote sensing or ground sensors, images and spectral data of the target water body area are collected, and the collected remote sensing data is preprocessed. Through band combination or spectral line analysis, the characteristic parameters of the water body are extracted using the spectral information in the remote sensing data. After multi-dimensional analysis of the on-site data, the following are calculated and obtained: the water turbidity coefficient Ct, the algal bloom coefficient Ca, and the oil pollution coefficient Co. Combining remote sensing data with geographical information, analyze the impact of potential pollution sources, agricultural runoff and industrial wastewater discharge on the water body, conduct spatio-temporal change analysis of the water body pollution situation, identify the trend of pollutant expansion or degradation. Based on the results of pollution assessment and spatio-temporal analysis, by comparing the comprehensive water quality index WQI with the preset threshold, generate water quality level warning information.

[0059] (2) The mapping method based on remote sensing big data analysis realizes the comprehensive monitoring and assessment of water body pollution through a systematic process of six steps. From the first step to the third step, through the collection, calibration of multi-source data and the extraction of characteristic parameters of water quality parameters, the quantitative assessment of key indicators such as water turbidity, algal bloom and oil pollution is completed; in the fourth step, through the combination of remote sensing images and the geographical information system GIS, the source tracing analysis of pollution sources and the monitoring of pollutant diffusion are completed; the fifth step and the sixth step provide accurate pollution warning and governance decision support on the basis of spatio-temporal change analysis and water quality index calculation. This process not only completes the dynamic perception of water body pollution, but also provides a closed-loop management of the whole life cycle from data acquisition to decision assistance.

[0060] (3) Compared with traditional water quality monitoring technologies, this method has achieved significant improvements in aspects such as spatial coverage, time resolution, and dynamic assessment. Traditional technologies mainly rely on ground sampling and laboratory analysis. Although the data accuracy is high, they have the deficiencies of limited monitoring range and serious time lag, especially being ineffective in dealing with large-scale and sudden water pollution. This method realizes the efficient processing from spatial data collection to pollution analysis through remote sensing equipment, optimizes the inversion accuracy of water quality parameters using machine learning algorithms, and combines GIS technology to complete the comprehensive identification of pollution distribution and the prediction of change trends. The improved dynamic monitoring ability and data analysis automation greatly make up for the shortcomings of traditional means.

[0061] (4) Through the collaborative optimization of six steps, this method has achieved multi-faceted improvements in water pollution monitoring and treatment effects. First, in terms of pollution identification, the accuracy and real-time performance have been significantly enhanced, and it can capture the dynamic changes of key issues such as algal blooms, turbidity, and oil pollution. Second, in terms of pollution assessment, the introduction of the comprehensive water quality index WQI provides a quantitative water quality health evaluation standard and a decision-making basis for water resource management departments. Finally, in terms of treatment efficiency, through the prediction of pollution diffusion trends and precise early warnings, the early intervention and the optimal allocation of treatment resources are realized. Generally speaking, this method not only improves the scientific and intelligent level of water quality monitoring but also provides strong technical support for the sustainable management of water ecosystems. Description of the Drawings

[0062] Figure 1 It is a schematic diagram of the steps of a mapping method based on remote sensing big data analysis according to the present invention. Detailed Embodiments

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment 1

[0065] The present invention provides a mapping method based on remote sensing big data analysis. Please refer to Figure 1 , including the following steps,

[0066] Step 1: Collect image and spectral data of the target water body area through satellite remote sensing, unmanned aerial vehicle remote sensing, or ground sensors, including data on the color, temperature, and optical reflectivity of the water body;

[0067] Step 2: Perform radiometric correction, atmospheric correction, and geometric correction on the collected remote sensing data, remove noise, and ensure the accuracy and consistency of the data;

[0068] Step 3: Through band combination or spectral analysis, use the spectral information in the remote sensing data to extract the characteristic parameters of the water body, including algal blooms, turbidity, and oil pollution concentration. Extract, analyze, and model the characteristics of the water body, and perform inversion and correction of the water quality parameters in the remote sensing image through multiple regression analysis or machine learning algorithms. After performing multi-dimensional analysis on the on-site data, calculate and obtain: the water turbidity coefficient Ct, the algal bloom coefficient Ca, and the oil pollution coefficient Co;

[0069] Step 4: Combine the remote sensing data with geographical information, including basin information and industrial emission areas, analyze the impact of potential pollution sources, agricultural runoff, and industrial wastewater emissions on the water body, and use the change detection method of remote sensing images to identify the distribution of pollutants in the water body, including detecting the spread of oil pollution and algal bloom pollutants;

[0070] Step 5: Conduct spatio-temporal variation analysis of the water body pollution situation, identify the trends of pollutant expansion or degradation, and the pollution changes under different seasons or weather conditions;

[0071] Step 6: Based on the results of pollution assessment and spatio-temporal analysis, generate water quality grade warning information by comparing the comprehensive water quality index WQI with the preset threshold, and provide data support for relevant management departments to formulate pollution control or prevention measures.

[0072] In this embodiment, through satellite remote sensing, UAV remote sensing, or ground sensors, collect the image and spectral data of the target water body area, preprocess the collected remote sensing data, through band combination or spectral analysis, use the spectral information in the remote sensing data to extract the characteristic parameters of the water body, calculate and obtain the water turbidity coefficient Ct, the algal bloom coefficient Ca, and the oil pollution coefficient Co after performing multi-dimensional analysis on the on-site data, combine the remote sensing data with geographical information, analyze the impact of potential pollution sources, agricultural runoff, and industrial wastewater emissions on the water body, conduct spatio-temporal variation analysis of the water body pollution situation, identify the trends of pollutant expansion or degradation, and the pollution changes under different seasons or weather conditions, and based on the results of pollution assessment and spatio-temporal analysis, generate water quality grade warning information by comparing the comprehensive water quality index WQI with the preset threshold, and provide data support for relevant management departments to formulate pollution control or prevention measures.

[0073] Embodiment 2

[0074] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: Step 1 includes:

[0075] Collect image data of the target water body area through satellite remote sensing, UAV remote sensing or ground sensor devices, covering the color, texture and spatial distribution information of the water body, providing the visual characteristics of the water body, and being able to initially identify the appearance and pollution degree of the water body;

[0076] Collect the optical reflectance data of the water body through multi-spectral or hyperspectral remote sensing sensors, providing the reflectance characteristic information of the water body surface and the underlying water body substances. The key spectral bands include green light, red light and near-infrared;

[0077] Collect the temperature data of the water body through infrared remote sensing technology or water temperature sensors. The water temperature information has a direct impact on the identification of pollutants, oil spills and algal blooms, because different pollutants have different effects on the water temperature, and the change of water temperature reflects the potential pollution area or the self-purification ability of the water body;

[0078] Collect chlorophyll a concentration Chl-a, the maximum concentration of chlorophyll a in the reference water area Chl-amax, cyanobacteria biomass Cb, the maximum value of cyanobacteria biomass in the reference water area Cbmax, and optical reflectance Rλ through multi-spectral or hyperspectral remote sensing sensors;

[0079] Measure through water quality sensors, portable turbidity meters and flow monitoring devices of ground monitoring stations to obtain water body turbidity Turbidity, standard turbidity Turbidity of the reference area ref , total suspended solids concentration TSS and total suspended solids concentration TSSref in the reference water area;

[0080] Use synthetic aperture radar SAR remote sensing data Sentinel-1 and multi-spectral data to combine to obtain spectral absorption characteristics, and use ground oil spill detectors and infrared spectrometers to obtain the oil film coverage area A oil , the maximum oil spill coverage area A in the reference water area oilmax , the reflection intensity I of the oil film at a specific spectral wavelength λoil , the maximum reflection intensity I without oil film in the reference area λmax ;

[0081] Obtain the surface water temperature WST of the water body and the surface water temperature WST of the oil-free sewage area through thermal infrared remote sensing equipment and thermal infrared sensors carried on MODIS or UAVs ref , and use a thermometer for auxiliary collection and calibration.

[0082] Step two includes:

[0083] Radiometric errors in remote sensing images are corrected. By eliminating errors caused by sensors, solar radiation, and terrain factors, it ensures that the radiometric values of each pixel in the remote sensing image reflect the true ground object characteristics, improves the precision of the data, and removes the influence of the atmosphere on the remote sensing image, including atmospheric scattering and absorption effects, ensuring that the spectral information of the data can accurately reflect the spectral characteristics of ground substances. By performing geometric correction on the remote sensing data, geometric distortions caused by satellite or sensor position, tilt angle, and Earth curvature factors are eliminated. Geometric correction ensures that each pixel in the remote sensing image corresponds precisely to the geographic coordinate system.

[0084] In this embodiment, by implementing Step 1 and Step 2, the comprehensiveness, accuracy, and practicality of water body monitoring data are significantly improved. First, the multi-source data acquisition in Step 1 ensures the acquisition of multi-dimensional information of the water body, including parameters such as the color, texture, optical reflectance, and temperature of the water body, comprehensively covering the key characteristics of water body pollution. At the same time, through multi-spectral and hyperspectral remote sensing technologies, combined with the monitoring of specific indicators such as chlorophyll a concentration, turbidity, and oil film coverage area, the distribution and concentration of algal blooms, suspended particles, and oil pollution in the water body can be accurately identified. In addition, Step 2 effectively eliminates radiometric errors, atmospheric interference, and geometric distortions in the collected data through radiometric correction, atmospheric correction, and geometric correction, ensuring that the spectral characteristics of the remote sensing image truly reflect ground object information. The combination of the two steps not only improves the quality and credibility of the data but also provides high-precision and high-resolution basic data for subsequent water quality analysis and pollution assessment, greatly enhancing the efficiency and scientific nature of water quality monitoring and early warning.

[0085] Embodiment 3

[0086] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: Step 3 includes:

[0087] By band combination or spectral line analysis, key characteristic parameters of the water body are extracted using the spectral information in the remote sensing data, including algal blooms, turbidity, and oil pollution concentration. By analyzing the spectral reflectance data of different bands, spectral characteristics related to the concentration of water body pollutants are extracted to generate preliminary estimated values of water quality parameters;

[0088] Using the multiple regression analysis method, the spectral information in the remote sensing image is combined with ground monitoring data to establish an inversion model. Through this model, the spectral characteristics in the remote sensing data are converted into water quality parameters, and after calculation, the turbidity coefficient Ct, algal bloom coefficient Ca, oil pollution coefficient Co, and comprehensive water quality index WQI of the water body are obtained, supplementing the deficiencies of ground data;

[0089] Machine learning algorithms, including support vector machines, random forests, and neural networks, are used to invert and correct water quality parameters in remote sensing images. Through a training dataset, the machine learning model can automatically identify the pollutant distribution in water bodies.

[0090] Step three also includes:

[0091] The turbidity coefficient Ct of the water body is calculated by the following formula:

[0092]

[0093] In the formula, Turbidity represents the turbidity of the water body, Turbidity ref represents the standard turbidity of the reference area, TSS represents the total suspended solids concentration of the water body, TSS ref represents the total suspended solids concentration in the reference water area, x1 and x2 respectively represent the weight values of each coefficient, and β1 and β2 respectively represent the fitting exponents, reflecting the influence of different types of suspended solids on turbidity.

[0094] The algal bloom coefficient Ca is calculated by the following formula:

[0095]

[0096] In the formula, Chl-a represents the chlorophyll a concentration in the water body, Chl-a max represents the maximum chlorophyll a concentration in the reference water area, Cb represents the cyanobacteria biomass, Cb max represents the maximum cyanobacteria biomass in the reference water area, Rλ represents the optical reflectance, w1 and w2 respectively represent the weight values of each parameter, and α1 and α2 respectively represent the spectral response indices, adjusting the sensitivity of the spectral reflectance characteristics to algae.

[0097] The oil pollution coefficient Co is calculated by the following formula:

[0098]

[0099] In the formula, Aoil represents the area covered by the oil film, A oilmax represents the maximum coverage area of oil pollution in the reference water area, I λoil represents the reflection intensity of the oil film at a specific spectral wavelength, I λmax represents the maximum reflection intensity without an oil film in the reference area, WST represents the water surface temperature, WST ref represents the surface temperature of the oil-free sewage water area, v1, v2, and v3 respectively represent the weight values of each parameter, and γ1, γ2, and γ3 are exponential fitting coefficients, adjusting the sensitivity of each parameter to oil pollution;

[0100] The comprehensive water quality index WQI is calculated through the following formula:

[0101]

[0102] In the formula, Ct represents the turbidity coefficient of the water body, Ca represents the algal bloom coefficient, Co represents the oil pollution coefficient, and n1, n2, and n3 represent the weight coefficients of each coefficient.

[0103] In this embodiment, through the implementation of Step 3, the method effectively improves the quantification ability of water body pollution characteristics and the accuracy of water quality analysis. First, by combining band combinations or spectral line analysis to extract key spectral features and using multiple regression analysis methods, an accurate conversion from remote sensing data to water quality parameters is achieved, generating the turbidity coefficient Ct, algal bloom coefficient Ca, and oil pollution coefficient Co of the water body, and further calculating the comprehensive water quality index WQI, providing a multi-dimensional quantitative assessment of the water body pollution status. At the same time, machine learning algorithms (such as support vector machines, random forests, and neural networks) are used to make the inversion of water quality parameters in remote sensing images more efficient and intelligent through learning and optimization of training data, ensuring the accuracy of pollutant distribution identification. The analysis process of water quality parameters is refined by using formula calculation methods. For example, the calculation of the turbidity coefficient Ct and the algal bloom coefficient Ca not only considers key indicators (such as turbidity, chlorophyll a concentration, cyanobacteria biomass, etc.), but also combines spectral reflection characteristics and weight allocation to fully reflect the impact of different pollutants on water body health. The oil pollution coefficient Co comprehensively evaluates the coverage and pollution degree of oil pollution on the water body by integrating multi-factor parameters such as oil film area, spectral absorption characteristics, and water temperature. The quantification of these coefficients provides a scientific basis for the calculation of the comprehensive water quality index WQI.

[0104] Embodiment 4

[0105] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: Step 4 includes:

[0106] Combining remote sensing data with geographic information system GIS technology, analyze the location of potential pollution sources and their impact on the water body. By analyzing basin information, industrial emission areas, and agricultural runoff geographical factors, identify pollution sources and evaluate their impact degree on water body pollution;

[0107] Adopt the remote sensing image change detection method to monitor and identify the spatial distribution of water body pollutants. By comparing remote sensing images of different periods, detect the diffusion situation and change trend of oil pollution and algal bloom pollutants, providing support for pollutant control and treatment.

[0108] Step 5 includes:

[0109] Through the spatio-temporal sequence analysis of water pollution data, identify the trends of pollutant expansion or degradation, combine historical data and real-time data, evaluate the dynamic changes of pollutants under different seasons and meteorological conditions, and reveal the temporal and spatial characteristics of water quality changes;

[0110] By analyzing the seasonal changes in water pollution, identify the water quality fluctuations caused by seasonal changes, including precipitation and temperature changes. According to the seasonal change trends, provide targeted strategies for water quality governance and optimize pollution control measures;

[0111] By establishing a dynamic model of pollutants, combining the physical processes of water body flow, sedimentation and diffusion, simulate the migration and transformation of pollutants in the water body. Through these models, predict the changes of pollutants in the water body in real time and give early warnings of future pollution trends.

[0112] In this embodiment, by implementing Step 4 and Step 5, the method significantly improves the spatial distribution analysis and dynamic change monitoring capabilities of water pollution. In Step 4, by combining remote sensing data with Geographic Information System (GIS) technology, the location of potential pollution sources and their impacts on water bodies can be accurately located. Especially for the analysis of industrial emission areas, agricultural runoff and watershed information, not only the types of pollution sources are identified, but also the degree of their contributions to water bodies is quantified. At the same time, through remote sensing image change detection technology, by comparing and analyzing image data at different times, the diffusion of pollutants such as oil pollution and algal blooms is effectively monitored, providing a scientific basis for the formulation of pollution control and treatment plans. Step 5 further deepens the dimension of spatio-temporal dynamic analysis. By combining historical data and real-time data, identify the trends of pollutant expansion or degradation. Especially in the impact of seasonal changes (such as precipitation, temperature changes, etc.) on water quality, reveal the temporal and spatial variation laws of pollutants. By establishing a dynamic model of pollutants and combining the physical processes of water body flow, sedimentation and diffusion, the simulation of pollutant migration and accurate early warning of future trends are realized. Such a dynamic model can not only predict the expansion range of pollution in real time, but also provide forward-looking decision-making support for early treatment.

[0113] Example 5

[0114] This embodiment is an explanatory description carried out in Example 1. Please refer to Figure 1 , specifically: Step 6 includes:

[0115] By comparing the comprehensive water quality index WQI with a preset pollution threshold, judge the severity of water pollution. When the water quality index exceeds the preset threshold, the system will automatically generate water quality warning information to provide timely pollution warnings for the management department;

[0116] Compare the turbidity coefficient Ct of the water body with a preset standard threshold U:

[0117] When the turbidity coefficient Ct of the water body ≤ the preset standard threshold U, the water quality is good, the concentration of suspended solids in the water body is within the normal range, the ecosystem is not affected, regularly monitor agricultural runoff, industrial wastewater discharge, and surface scouring caused by rainfall within the basin area to avoid an increase in turbidity;

[0118] When the turbidity coefficient Ct of the water body > the preset standard threshold U, the turbidity of the water body exceeds the preset threshold, indicating that the turbidity of the water body has abnormally increased. High-concentration suspended particles will cause ecological problems, including reducing the photosynthesis efficiency of aquatic plants and endangering the fish habitat environment. At the same time, it indicates that surface runoff carries pollutants, including nutrients, pathogens, or toxic substances. Control the amount and timing of fertilization, construct rainwater collection and purification systems to reduce the suspended particles brought into the water body during rainfall, build sedimentation tanks or constructed wetlands in the water body, and use natural sedimentation and plant filtration to remove suspended particles;

[0119] Compare the algal bloom coefficient Ca with the preset standard threshold P:

[0120] When the algal bloom coefficient Ca ≤ the preset standard threshold P, there is no abnormal proliferation of algae in the water body, and the ecosystem is in a healthy state. Reduce the use of chemical fertilizers or construct buffer zones, promote sewage treatment facilities in the coastal areas, avoid direct discharge of domestic sewage into the water body, maintain the natural fluidity of the water body, increase the river flow, and plant aquatic plants to competitively absorb nutrients to reduce the chance of algae reproduction;

[0121] When the algal bloom coefficient Ca > the preset standard threshold P, there is abnormal proliferation of algae in the water body, resulting in an ecological crisis of hypoxia and fish death in the water body and affecting the water body function. Carry out nitrogen and phosphorus interception measures for agricultural non-point source pollution, introduce eco-friendly algal control agents or enclosed floating islands into the water body to limit the growth of algae, and use aeration devices to increase the dissolved oxygen concentration of the water body;

[0122] Compare the oil pollution coefficient Co with the preset standard threshold R:

[0123] When the oil pollution coefficient Co ≤ the preset standard threshold R, the water body is not significantly polluted by oil, and the water ecosystem and water body use function are not significantly affected. Install remote sensing monitoring equipment to regularly track the distribution of oil films, and set up oil spill interception devices in the coastal area or waterway to reduce the spread of oil pollution;

[0124] When the oil pollution coefficient Co > the preset standard threshold R, the oil pollution on the water surface is obvious, resulting in damage to the ecosystem, asphyxiation of aquatic organisms or damage to the ecological chain. At the same time, it affects the use function of the water body. Use oil-absorbing devices and oil spill cleanup ships to promptly remove the oil film on the water surface, and put in decomposable microorganisms or biological enzymes to accelerate the degradation of oil pollution, and repair the water ecosystem in the polluted area, including reconstructing wetlands, vegetation or putting in water-purifying plants.

[0125] In this embodiment, by implementing Step Six, the method realizes the quantitative assessment and intelligent early warning of water pollution, greatly improving the scientificity and timeliness of water pollution management. By comparing the comprehensive water quality index WQI with the preset threshold, the severity of water pollution can be accurately judged. When the pollution exceeds the threshold, the system automatically generates early warning information, providing technical support for rapid response for the management department. When further refined to specific pollution types, the hierarchical assessment and comparison of the turbidity coefficient Ct, algal bloom coefficient Ca, and oil pollution coefficient Co of the water body can respectively identify the different impacts of suspended particles, algal blooms, and oil pollution, and give targeted treatment suggestions. When the pollution index is at a low-risk level, the preventive measures proposed by the system (such as regular monitoring, optimizing agricultural and industrial emissions management, etc.) can effectively avoid water quality deterioration; while at a high-risk level, the emergency response strategies for different pollution types (such as algae control measures, sedimentation tank or wetland construction, oil spill cleanup and ecological restoration, etc.) can quickly reduce the pollution level and alleviate the ecological crisis. Especially by combining remote sensing monitoring equipment with the dynamic early warning function, the system has the ability to continuously track pollution changes, ensuring the reasonable allocation of treatment resources.

[0126] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A mapping method based on remote sensing big data analysis, characterized in that: It includes the following steps: Step 1: Collect images and spectral data of the target water body area through satellite remote sensing, UAV remote sensing or ground sensors, including data on the color, temperature and optical reflectivity of the water body; Step 2: Perform radiometric correction, atmospheric correction and geometric correction on the collected remote sensing data to remove noise and ensure the accuracy and consistency of the data; Step 3: Extract characteristic parameters of the water body, including algal blooms, turbidity and oil pollution concentration, from the spectral information in the remote sensing data through band combination or spectral line analysis, extract, analyze and model the characteristics of the water body, invert and correct the water quality parameters in the remote sensing image through multiple regression analysis or machine learning algorithms, and calculate and obtain through multi-dimensional analysis of on-site data: water body turbidity coefficient Ct, algal bloom coefficient Ca and oil pollution coefficient Co; Step 4: Combine remote sensing data with geographical information, including basin information and industrial emission areas, analyze the impact of potential pollution sources, agricultural runoff and industrial wastewater discharges on the water body, and use the change detection method of remote sensing images to identify the distribution of pollutants in the water body, including detecting the spread of oil pollution and algal bloom pollutants; Step 5: Conduct spatio-temporal variation analysis of the water body pollution situation to identify the trends of pollutant expansion or degradation, as well as pollution changes under different seasons or weather conditions; Step 6: Based on the results of pollution assessment and spatio-temporal analysis, generate water quality grade warning information by comparing the comprehensive water quality index WQI with a preset threshold, and provide data support for relevant management departments to formulate pollution control or prevention measures.

2. The mapping method based on remote sensing big data analysis according to claim 1, wherein: Step 1 includes: Collect image data of the target water body area through satellite remote sensing, UAV remote sensing or ground sensor equipment, covering information on the color, texture and spatial distribution of the water body, providing visual characteristics of the water body, and being able to initially identify the appearance and pollution degree of the water body; Collect optical reflectivity data of the water body through multi-spectral or hyperspectral remote sensing sensors, providing reflection characteristic information of the water body surface and its underlying water body substances, and the key spectral bands include green light, red light and near-infrared; Collect temperature data of the water body through infrared remote sensing technology or water temperature sensors. The water temperature information has a direct impact on the identification of pollutants, oil pollution and algal blooms, because different pollutants have different effects on the water temperature, and the change of water temperature reflects potential pollution areas or the self-purification ability of the water body; Collect chlorophyll a concentration Chl-a, maximum chlorophyll a concentration Chl-amax in the reference water area, cyanobacteria biomass Cb, maximum value of cyanobacteria biomass Cbmax in the reference water area, and optical reflectivity Rλ through multi-spectral or hyperspectral remote sensing sensors; Measured by a water quality sensor, a portable turbidimeter, and a flow monitoring device at a ground monitoring station to obtain the water turbidity, the standard turbidity of the reference area, the total suspended solids concentration (TSS), and the total suspended solids concentration in the reference water area (TSSref). ref and the total suspended solids concentration (TSS) and the total suspended solids concentration in the reference water area (TSSref); Obtain the spectral absorption characteristics by combining Sentinel-1 synthetic aperture radar (SAR) remote sensing data and multispectral data, and use a ground oil detector and an infrared spectrometer to obtain the oil film coverage area A oil 、The maximum coverage area A of oil pollution in the reference water area oilmax 、The reflection intensity I of the oil film at a specific spectral wavelength λoil 、The maximum reflection intensity I without an oil film in the reference area λmax ; Obtain the water surface temperature WST of the water body and the water surface temperature WST of the oil-free sewage area through a thermal infrared remote sensing device and a thermal infrared sensor carried on MODIS or an unmanned aerial vehicle ref , and use a thermometer for auxiliary collection and calibration.

3. A mapping method based on remote sensing big data analysis according to claim 1, characterized in that: Step 2 includes: Correct the radiation errors in remote sensing images. By eliminating the errors caused by sensors, solar radiation, and terrain factors, ensure that the radiation value of each pixel in the remote sensing image reflects the true ground features, improve the accuracy of the data, and remove the influence of the atmosphere on the remote sensing image, including atmospheric scattering and absorption effects, to ensure that the spectral information of the data can accurately reflect the spectral characteristics of ground substances. Through geometric correction of the remote sensing data, eliminate the geometric distortions caused by the position and tilt angle of the satellite or sensor and the factor of the earth's curvature. Geometric correction ensures that each pixel in the remote sensing image corresponds precisely to the geographic coordinate system.

4. A mapping method based on remote sensing big data analysis according to claim 1, characterized in that: Step three includes: Extract the key characteristic parameters of water bodies, including algal blooms, turbidity, and oil pollution concentration, using the spectral information in the remote sensing data through band combination or spectral line analysis. By analyzing the spectral reflectance data of different bands, extract the spectral characteristics related to the concentration of water pollutants and generate a preliminary estimate of the water quality parameters. Use the multiple regression analysis method to combine the spectral information in the remote sensing image with the ground monitoring data to establish an inversion model. Through this model, convert the spectral characteristics in the remote sensing data into water quality parameters, and calculate to obtain: the turbidity coefficient Ct of the water body, the algal bloom coefficient Ca, the oil pollution coefficient Co, and the comprehensive water quality index WQI, to supplement the deficiency of the ground data. Adopt machine learning algorithms, including support vector machines, random forests, and neural networks, to invert and correct the water quality parameters in the remote sensing image. Through the training dataset, the machine learning model can automatically identify the distribution of water pollutants.

5. A mapping method based on remote sensing big data analysis according to claim 4, characterized in that: Step three also includes: The turbidity coefficient Ct of the water body is calculated and obtained through the following formula: In the formula, Turbidity represents the turbidity of the water body, Turbidity ref represents the standard turbidity of the reference area, TSS represents the total suspended solids concentration of the water body, TSS ref represents the total suspended solids concentration in the reference water area, x1 and x2 respectively represent the weight values of each coefficient, and β1 and β2 respectively represent the fitting exponents, reflecting the influence of different types of suspended solids on turbidity.

6. A mapping method based on remote sensing big data analysis according to claim 4, characterized in that: The algal bloom coefficient Ca is calculated and obtained through the following formula: where Chl-a represents the chlorophyll a concentration in water, and Chl-a max represents the maximum chlorophyll a concentration in the reference water area, Cb represents the cyanobacteria biomass, and Cb max represents the maximum cyanobacteria biomass in the reference water area, Rλ represents the optical reflectance, w1 and w2 respectively represent the weight values of each parameter, and α1 and α2 respectively represent the spectral response indices, adjusting the sensitivity of the spectral reflectance characteristics to algae.

7. A mapping method based on remote sensing big data analysis according to claim 4, characterized in that: The oil pollution coefficient Co is calculated and obtained through the following formula: Where, Aoil represents the area covered by the oil film, and A oilmax represents the maximum coverage area of the oil pollution in the reference water area, and I λoil represents the reflection intensity of the oil film at a specific spectral wavelength, and I λmax represents the maximum reflection intensity without an oil film in the reference area. WST represents the temperature of the water surface, and WST ref represents the surface temperature of the oil-free sewage water area. v1, v2, and v3 respectively represent the weight values of each parameter, and γ1, γ2, and γ3 are exponential fitting coefficients to adjust the sensitivity of each parameter to the oil pollution; The comprehensive water quality index WQI is calculated and obtained through the following formula: In the formula, Ct represents the turbidity coefficient of the water body, Ca represents the algal bloom coefficient, Co represents the oil pollution coefficient, and n1, n2, and n3 represent the weight coefficients of each coefficient.

8. A mapping method based on remote sensing big data analysis according to claim 1, characterized in that: Step four includes: Combine the remote sensing data with the geographic information system GIS technology to analyze the location of potential pollution sources and their impact on water bodies. By analyzing factors such as watershed information, industrial emission areas, and agricultural runoff geography, identify pollution sources and evaluate the degree of their impact on water pollution. Adopt the remote sensing image change detection method to monitor and identify the spatial distribution of water pollutants. By comparing remote sensing images of different periods, detect the diffusion and change trends of oil pollution and algal bloom pollutants, and provide support for pollutant control and treatment.

9. A mapping method based on remote sensing big data analysis according to claim 1, characterized in that: Step five includes: Through the spatio-temporal sequence analysis of water pollution data, identify the trend of pollutant expansion or degradation, combine historical data and real-time data, evaluate the dynamic changes of pollutants under different seasons and different meteorological conditions, and reveal the temporal and spatial characteristics of water quality changes. By analyzing the seasonal changes in the water pollution situation, identify the water quality fluctuations caused by seasonal changes, including precipitation and temperature changes. According to the seasonal change trend, provide targeted strategies for water quality treatment and optimize pollution control measures. By establishing a dynamic model of pollutants and combining the physical processes of water flow, sedimentation, and diffusion in the water body, the migration and transformation of pollutants in the water body are simulated. Through these models, the changes of pollutants in the water body are predicted in real time, and early warnings are issued for future pollution trends.

10. A mapping method based on remote sensing big data analysis according to claim 1, characterized in that: Step six includes: By comparing the comprehensive water quality index WQI with a preset pollution threshold, the severity of water body pollution is judged. When the water quality index exceeds the preset threshold, the system will automatically generate water quality early warning information to provide timely pollution warnings for the management department; The turbidity coefficient Ct of the water body is compared with a preset standard threshold U: When the turbidity coefficient Ct of the water body ≤ the preset standard threshold U, the water quality is good, the concentration of suspended solids in the water body is within the normal range, the ecosystem is not affected, and the agricultural runoff, industrial wastewater discharge, and surface scouring caused by rainfall within the basin are monitored regularly to avoid an increase in turbidity; When the turbidity coefficient Ct of the water body > the preset standard threshold U, the turbidity of the water body exceeds the preset threshold, indicating that the turbidity of the water body has increased abnormally. High-concentration suspended particles will cause ecological problems, including reducing the photosynthesis efficiency of aquatic plants and endangering the fish habitat. At the same time, it indicates that surface runoff carries pollutants, including nutrients, pathogens, or toxic substances. Control the amount and timing of fertilization, build rainwater collection and purification systems to reduce the suspended particles brought into the water body during rainfall, and build sedimentation ponds or constructed wetlands in the water body to remove suspended particles through natural sedimentation and plant filtration; The algal bloom coefficient Ca is compared with a preset standard threshold P: When the algal bloom coefficient Ca ≤ the preset standard threshold P, no abnormal proliferation of algae occurs in the water body, and the ecosystem is in a healthy state. Reduce the use of chemical fertilizers or build buffer zones, promote sewage treatment facilities in the coastal areas, avoid direct discharge of domestic sewage into the water body, maintain the natural fluidity of the water body, increase the river runoff, and plant aquatic plants to competitively absorb nutrients to reduce the chance of algae reproduction; When the algal bloom coefficient Ca > the preset standard threshold P, abnormal proliferation of algae occurs in the water body, leading to an ecological crisis of hypoxia and fish death in the water body and affecting the water body function. Implement nitrogen and phosphorus interception measures for agricultural non-point source pollution, introduce eco-friendly algal control agents or closed floating islands into the water body to limit the growth of algae, and use aeration devices to increase the dissolved oxygen concentration in the water body; The oil pollution coefficient Co is compared with a preset standard threshold R: When the oil pollution coefficient Co ≤ the preset standard threshold R, the water body is not significantly polluted by oil, and the water ecosystem and water body use function are not significantly affected. Install remote sensing monitoring equipment to regularly track the distribution of oil films, and set up oil spill interception devices in the coastal areas or waterways to reduce the spread of oil pollution; When the oil pollution coefficient Co > the preset standard threshold R, the water surface is significantly covered with oil, resulting in damage to the ecosystem, asphyxiation of aquatic organisms, or disruption of the ecological chain, and at the same time affecting the use function of the water body. Use oil absorption devices and oil spill cleaning ships to promptly remove the oil film on the water surface, put in decomposable microorganisms or bioenzymes to accelerate the degradation of oil pollution, and repair the water ecosystem in the polluted area, including reconstructing wetlands, vegetation, or putting in water purification plants.

Images