A method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing

Abstract

The present invention is a method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing, specifically relating to the technical field of environmental monitoring. It solves the technical problems that it is difficult to analyze various characteristic data of microplastics through image processing software, and it is also difficult to comprehensively construct a model to output the comprehensive pollution degree value of waters, and there is a lack of a technology for combining the model prediction value with GIS technology to identify the spatial distribution. The method includes the following steps: extracting 70% of the sample data in the target waters for preprocessing; screening out the samples with the microplastic abundance not less than the average abundance of microplastics in the target waters; extracting characteristic data from the remote sensing image, including the total color adsorption ability degree, the total shape coverage ability degree, and the total water turbidity degree; using the characteristic data to construct a model to obtain the predicted value of the comprehensive pollution degree of waters; using GIS technology to generate the spatial distribution of the predicted value of the comprehensive pollution degree, and using different colors to represent different pollution degrees.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring, and particularly relates to a method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing. Background Art

[0002] With the continuous increase in global plastic production, microplastics have become one of the main sources of water pollution. For this reason, a method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing has emerged. The present invention extracts various characteristic data through the comprehensive utilization of remote sensing technology, neural network models, and multi-dimensional data analysis methods to construct a prediction model for the comprehensive pollution degree of waters, realizing the efficient identification of the distribution of microplastic pollution in waters. After converting the model prediction value point data into surface data, it is imported into GIS software to generate the spatial distribution of the pollution degree prediction value.

[0003] Although the existing methods for identifying the spatial distribution of microplastic-polluted waters have achieved the identification of the spatial distribution of polluted waters to a certain extent, traditional water quality monitoring methods require sampling one by one, with low efficiency. It is difficult to extract features from microplastic images through image processing software, analyze by constructing corresponding characteristic degree data based on the features, and it is also difficult to comprehensively construct a model with the characteristic degree data to predict the comprehensive pollution degree value of waters. There is a lack of the spatial distribution obtained by importing the comprehensive pollution degree value of waters into GIS software and using different colors to represent different pollution degrees. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes a method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing, which is used to solve the following technical problems:

[0005] Although the existing methods for identifying the spatial distribution of microplastic-polluted waters have achieved the identification of the spatial distribution of polluted waters to a certain extent, traditional water quality monitoring methods require sampling one by one, with low efficiency. It is difficult to extract features from microplastic images through image processing software, analyze by constructing corresponding characteristic degree data based on the features, and it is also difficult to comprehensively construct a model with the characteristic degree data to predict the comprehensive pollution degree value of waters. There is a lack of the spatial distribution obtained by importing the comprehensive pollution degree value of waters into GIS software and using different colors to represent different pollution degrees.

[0006] To solve the above problems, the first aspect of the present invention provides a method for identifying the spatial distribution of microplastic-polluted waters based on remote sensing, including the following steps:

[0007] S1: Collect a number of water samples in the target water area, and extract 70% of the sample data for preprocessing;

[0008] S2: Detect the pre - processed water body samples, and screen out the water body samples with the micro - plastic abundance greater than or equal to the average value of the micro - plastic abundance in the target water area;

[0009] S3: Use remote sensing technology to obtain the remote sensing images of the screened water body samples. After extracting the boundaries of the water bodies through the Canny edge detection algorithm and performing pre - processing, extract and identify the characteristic data from the remote sensing images, including the total color adsorption ability degree, the total shape coverage ability degree, and the total water body turbidity degree;

[0010] S4: Use the collected characteristic data to build a model and train it. Deploy the trained model to the actual environment, extract features from new images and use the model for prediction to obtain the predicted value of the comprehensive water area pollution degree;

[0011] S5: Use GIS technology to visualize the spatial distribution of the predicted value of the comprehensive water area pollution degree obtained by the model on the map. According to the predicted value of the comprehensive water area pollution degree and different colors representing different pollution degrees, use GIS tools to analyze the spatial distribution of micro - plastic water area pollution and identify hot spots.

[0012] As a further scheme of the present invention: The step S1 includes the following steps:

[0013] According to the preset sampling point coordinates, measure the width of the target water area, arrange a number of sampling points at equal distances along the width direction of the water area, the sampling depth is between 0.5 - 1 meter of the depth of the target water area, collect a number of water body samples in the target water area, randomly select 70% of the collected water body samples as the treatment object, and perform pre - processing operations on the selected treatment object.

[0014] As a further scheme of the present invention: The pre - processing operation on the selected treatment object includes the following steps:

[0015] The pre - processing operation on the selected treatment object includes adding 30% hydrogen peroxide with a volume ratio of 10:1 to the sample, performing digestion at a constant temperature of 60°C for 12 hours; mixing the digested water body sample with a high - density saturated sodium chloride salt solution for density separation, stirring evenly and then standing for precipitation for 24 hours, and collecting the upper solution; performing a filtration operation on the upper solution, putting the obtained filter paper into a culture dish and drying it at 30°C for 24 hours.

[0016] As a further scheme of the present invention: The step S2 includes the following steps:

[0017] The pretreated water samples were tested for microplastics using a microscope visual identification method, and the number, color, size and shape characteristics of the microplastics in each sample were recorded. Based on the test data, the average abundance of microplastics in all samples in the target waters was calculated, and the abundance of microplastics in each sample was compared with the average abundance of the target waters. Water samples with microplastic abundance greater than or equal to the average abundance of microplastics in the target waters were screened out and analyzed.

[0018] As a further solution of the present invention: Step S3 comprises the following steps:

[0019] Remote sensing technology is used to obtain remote sensing images of screened water samples. The boundaries of the water bodies are extracted using the Canny edge detection algorithm and then preprocessed, including denoising and image enhancement. Feature data are extracted and identified from the remote sensing images, including the total color adsorption capacity, the total shape coverage capacity and the total water turbidity.

[0020] As a further solution of the present invention: the total color adsorption capacity comprises the following steps:

[0021] Collect image datasets containing microplastics and other objects. The model uses a convolutional neural network to extract image features, including color, size, and shape. The Mask R-CNN mask region convolutional neural network uses a region proposal network to generate potential microplastic locations, classify and segment the locations, assign a category label to each potential microplastic location, and generate a corresponding mask. Use the mouse to draw a polygon to mark the edge of the target object, use the annotation tool to annotate the microplastics and other objects in the image, and save it as a .json file. Convert the .json format to a format that matches the Mask R-CNN mask region convolutional neural network training. The converted data package includes image files and corresponding annotation files. Use the converted data to train the Mask R-CNN mask region convolutional neural network, and use the trained model to distinguish microplastics from other objects in the image.

[0022] According to the color characteristics, the microplastics are divided into three categories, including black, blue and colorless microplastics. The images containing black, blue and colorless microplastics are annotated, and the annotated data set is used to train the classifier to automatically identify and classify microplastics. The object technology method is used to count the microplastics of each color category, and the proportion of the number of microplastics of each color to the total number of microplastics is calculated. The proportion value is used as the weight coefficient. According to the adsorption intensity coefficient set for microplastics of different colors based on the research data, the weight coefficient of each color of microplastics is combined with the adsorption intensity coefficient of the corresponding color, and the combined values ​​of the three colors are added to obtain the total color adsorption capacity of the water area;

[0023] Calculation formula for the total color adsorption capacity degree:

[0024]

[0025] Wherein, is the total color adsorption capacity degree, is the number of black microplastics, is the number of blue microplastics, is the number of colorless microplastics, is the total number of microplastics of the three colors, , and are the set adsorption intensity coefficients.

[0026] As a further solution of the present invention: The total shape coverage capacity degree includes the following steps:

[0027] Convert the collected image into a grayscale image, use the pattern recognition algorithm in the image analysis software to identify and classify the shapes of microplastics, detect the change in pixel intensity in the image based on the edge detection algorithm to determine the edge position, extract the edges of microplastics from the image, and apply the contour tracking algorithm to connect the edge points to form the object contour; Use the Fourier transform infrared microscope based on the focal plane array to image the microplastic particles to obtain a high-resolution two-dimensional image, use laser ranging to obtain the depth information of the microplastics, combine the depth information with the two-dimensional image, use the three-dimensional reconstruction algorithm to generate the three-dimensional model of the microplastics, and obtain the surface area data of each microplastic through the three-dimensional model; By analyzing the shape characteristics of microplastics in the three-dimensional model, classify the microplastics into different shape types, including fibrous, granular, and film-like, count the number of microplastics in each shape category, calculate the surface area of microplastics of different shapes, multiply the surface area of microplastics of each shape by the corresponding number to obtain the total surface area of the corresponding shape, calculate the proportion value of the total surface area of each shape to the comprehensive surface area of the three shapes, use the proportion value as the weight coefficient, set the coverage breadth coefficient for microplastics of each shape, multiply the weight coefficient by the coverage breadth coefficient, and then add the combined values of the three shapes to obtain the total shape coverage capacity degree of this water area;

[0028] Calculation formula for the total shape coverage capacity degree:

[0029]

[0030]

[0031] Wherein, is the comprehensive surface area of the three shapes, is the number of fibrous microplastics, is the surface area of fibrous microplastics, is the quantity of granular microplastics, is the surface area of granular microplastics, is the quantity of film - shaped microplastics, is the surface area of film - shaped microplastics, is the degree of total shape coverage ability, , and are the set coverage breadth coefficients.

[0032] As a further solution of the present invention: the total water turbidity degree includes the following steps:

[0033] Import the collected image into the open - source ImageJ software, set the scale length and unit in the software, pre - process the image, including adjusting the contrast and brightness, manually mark the microplastic particles in the image using the Rectangle tool in the toolbar. For each marked particle, draw a straight line passing through the center of the particle using the function provided by the software, calculate and record the maximum size of each particle, classify the microplastics according to the measured particle size into nano - scale microplastics, micro - scale microplastics, and millimeter - scale microplastics, collect the particle size data of all particles, perform statistical analysis to obtain the average particle size of the microplastics, count the microplastics in each particle size interval, count the number of microplastics in each particle size interval, and combine the shape ratios of the three different - shaped microplastics to construct a weighted average particle size. According to the average particle size of each shape of microplastics and its ratio, obtain the total water turbidity degree of this water area;

[0034] Total water turbidity degree calculation formula:

[0035]

[0036] Wherein, is the total water turbidity degree, is the sum of the particle sizes of fibrous microplastics, is the th particle size of fibrous microplastics, is the quantity of fibrous microplastics, is the total quantity of the three - shaped microplastics, is the sum of the particle sizes of granular microplastics, is the th particle size of granular microplastics, is the quantity of granular microplastics, is the sum of the particle sizes of film - shaped microplastics, is the th particle size of film - shaped microplastics, is the quantity of film - shaped microplastics.

[0037] As a further solution of the present invention: Step S4 includes the following steps:

[0038] According to the feature data extracted from the image, including the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water body turbidity degree, after cleaning and standardizing the feature data, a machine learning model capable of predicting the comprehensive pollution degree of the water area is constructed. The collected feature data is used to train the model, and the trained model is deployed to the actual environment. Features are extracted from the new image and the model is used for prediction to obtain the predicted value of the comprehensive pollution degree of the water area.

[0039] As a further solution of the present invention: Step S5 includes the following steps:

[0040] After converting the model prediction value point data into surface data, it is imported into the GIS software to generate the spatial distribution of the pollution degree prediction value. It is set that when the predicted value of the comprehensive pollution degree of the water area ≤ 1, it is low pollution; when 1 < the predicted value of the comprehensive pollution degree of the water area ≤ 2, it is medium pollution; when 2 < the predicted value of the comprehensive pollution degree of the water area, it is heavy pollution. Different colors are used to represent different pollution degrees. Among them, green represents low pollution degree, yellow represents medium pollution degree, and red represents high pollution degree. Using the mapping function of the GIS software, annotations and legends are added; the spatial distribution of microplastic water pollution and hot spot areas are analyzed according to the GIS tools.

[0041] Advantages of the present invention:

[0042] The present invention obtains remote sensing images of selected water body samples through remote sensing technology, constructs a neural network model capable of distinguishing microplastics from other objects by extracting the characteristics of microplastics in the samples, combines various characteristics of microplastics with corresponding quantities and coefficients respectively to obtain the characteristic data of the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water body turbidity degree of the water area. Using hyperspectral remote sensing technology and machine learning algorithms improves the recognition efficiency and accuracy of microplastics, realizes large-scale monitoring of microplastic pollution in water bodies, and provides a scientific basis for comprehensively evaluating the water body pollution status through various characteristic data obtained by comprehensively analyzing various characteristics of microplastics;

[0043] The present invention preprocesses the feature data extracted from the image, including the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water body turbidity degree, constructs a machine learning model capable of predicting the comprehensive pollution degree of the water area and trains it. The data in the new image is predicted by the trained model to obtain the predicted value of the comprehensive pollution degree of the water area, realizing real-time acquisition of water quality monitoring data and improving the efficiency and accuracy of water quality monitoring;

[0044] By utilizing GIS technology, the present invention visualizes the predicted values of the comprehensive pollution degree of water areas obtained from the model on a map, and uses different colors to represent different pollution degrees according to the threshold range to which the predicted values of the comprehensive pollution degree of water areas belong, thereby achieving a more accurate identification of pollution areas of different degrees and their spatial distributions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a schematic flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0048] Please refer to Figure 1 As shown, the present invention is a method for identifying the spatial distribution of microplastic-polluted water areas based on remote sensing, including the following steps:

[0049] S1: Collect a number of water samples in the target water area, and extract 70% of the sample data for preprocessing;

[0050] S2: Detect the preprocessed water samples, and screen out the water samples with the microplastic abundance greater than or equal to the average abundance of microplastics in the target water area;

[0051] S3: Use remote sensing technology to obtain the remote sensing images of the screened water samples, extract the boundaries of the water bodies through the Canny edge detection algorithm and then perform preprocessing, and extract and identify the characteristic data from the remote sensing images, including the total color adsorption ability degree, the total shape coverage ability degree, and the total water body turbidity degree;

[0052] S4: Use the collected characteristic data to build a model and train it, deploy the trained model to the actual environment, extract features from new images and use the model for prediction to obtain the predicted value of the comprehensive pollution degree of the water area;

[0053] S5: Using GIS technology, visualize the predicted values of the comprehensive water pollution degree obtained from the model on the map for spatial distribution. According to the predicted values of the comprehensive water pollution degree and different colors representing different pollution degrees, use GIS tools to analyze the spatial distribution of microplastic water pollution and identify hotspots.

[0054] Specifically, collect a number of water samples within the target water area. Randomly select 70% of the collected water samples as the treatment objects and perform pretreatment operations on the selected treatment objects; add 30% hydrogen peroxide with a volume ratio of 10:1 to each water sample, place the mixture under a constant temperature condition of 60 °C for digestion for 12 hours, mix the digested water samples with a high-density saturated sodium chloride salt solution for density separation, stir evenly and then let it stand for precipitation for 24 hours, collect the upper solution, filter the upper solution, put the obtained filter paper into a culture dish, and dry it at 30 °C for 24 hours; detect microplastics in the pretreated water samples by microscopic vision recognition method, record the quantity, color, size and shape characteristics of microplastics in each sample, calculate the average abundance of microplastics in all samples in the target water area, compare the microplastic abundance of each sample with the average abundance in the target water area, and screen out the water samples with microplastic abundance not less than the average microplastic abundance in the target water area; use a satellite remote sensing platform to obtain remote sensing images of the target water area, apply the Canny edge detection algorithm to process the remote sensing images to extract the boundaries of the water bodies, perform pretreatment on the extracted water body boundaries, including denoising and image enhancement processing, extract and identify feature data from the pretreated remote sensing images, obtain the pollution adsorption degree through the pollution adsorption degree of microplastics of different colors, obtain the pollution coverage degree through the surface area of microplastics of different shapes, and obtain the total water turbidity degree of the water area through microplastics of different particle sizes; after cleaning and standardizing a variety of feature data, convert the feature data of different dimensions to a unified scale, use the total color adsorption ability degree, the total shape coverage ability degree and the total water turbidity degree as the model input, and the comprehensive water pollution degree as the model output to construct a machine learning model capable of predicting the comprehensive water pollution degree of this water area, use the collected feature data to train the model, deploy the trained model to a new actual environment, perform the same pretreatment and feature extraction on the newly obtained remote sensing images, use the feature data of the new images as the input for the deployed model to obtain the predicted values of the comprehensive water pollution degree; convert the model predicted value point data into surface data and then import it into GIS software to generate the spatial distribution of the pollution degree prediction values, and use different colors to represent different pollution degrees obtained according to the threshold range where the predicted values of the comprehensive water pollution degree are located.

[0055] In one embodiment of the present invention, the step S1 includes the following steps:

[0056] According to the preset sampling point coordinates, measure the width of the target water area, arrange a number of sampling points at equal distances along the width direction of the water area, with the sampling depth between 0.5 and 1 meter of the depth of the target water area, collect a number of water samples in the target water area, randomly select 70% of the collected water samples as the treatment objects, and perform preprocessing operations on the selected treatment objects.

[0057] Specifically, measure the width of the target water area, arrange a number of sampling points at equal distances along the width direction of the water area, set the sampling depth between 0.5 and 1 meter of the depth of the target water area, collect a number of water samples in the target water area, randomly select 70% of the collected water samples as the treatment objects, and perform preprocessing operations on the selected treatment objects.

[0058] In one embodiment of the present invention, the preprocessing operation on the selected treatment objects includes the following steps:

[0059] The preprocessing operation on the selected treatment objects includes adding 30% hydrogen peroxide with a volume ratio of 10:1 to the samples, and performing digestion at a constant temperature of 60°C for 12 hours; mixing the digested water samples with a high-density saturated sodium chloride salt solution for density separation, stirring evenly and then standing for precipitation for 24 hours, and collecting the upper layer solution; performing a filtration operation on the upper layer solution, putting the obtained filter paper into a culture dish and drying it at 30°C for 24 hours.

[0060] Specifically, add 30% hydrogen peroxide with a volume ratio of 10:1 to each water sample, place the mixture at a constant temperature of 60°C for digestion for 12 hours, mix the digested water samples with a high-density saturated sodium chloride salt solution for density separation, stir evenly and then stand for precipitation for 24 hours, collect the upper layer solution, perform a filtration operation on the upper layer solution, put the obtained filter paper into a culture dish, and dry it at 30°C for 24 hours to ensure that the samples undergo appropriate chemical treatment and physical separation processes for analysis and research.

[0061] In one embodiment of the present invention, step S2 includes the following steps:

[0062] Perform microplastic detection on the preprocessed water samples by microscopic vision recognition method, record the number, color, size and shape characteristics of microplastics in each sample, calculate the average abundance of microplastics in all samples of the target water area according to the detection data, compare the microplastic abundance of each sample with the average abundance of the target water area, screen out the water samples with microplastic abundance greater than or equal to the average abundance of microplastics in the target water area, and analyze the screened water samples.

[0063] Specifically, all pre-treated water body samples are prepared, and each sample has undergone density separation, filtration, and drying treatment steps to facilitate the observation and identification of microplastic particles under a microscope. A high-resolution microscope is used to observe each water body sample, and the color, size, and shape characteristics of the microplastics in each sample are recorded. According to the observed data, the average abundance of microplastics in all samples of the target water area is calculated, and the average abundance is 6 pieces / L. The plastic abundance of each sample is compared with the average abundance of the target water area, and the water body samples with microplastic abundance greater than or equal to the average microplastic abundance of the target water area are screened out, and the screened samples are analyzed.

[0064] In one embodiment of the present invention, the step S3 includes the following steps:

[0065] Use remote sensing technology to obtain the remote sensing image of the screened water body sample. After extracting the boundary of the water body through the Canny edge detection algorithm, preprocessing is performed, including denoising and image enhancement processing. Feature data, including the total color adsorption ability degree, the total shape coverage ability degree, and the total water body turbidity degree, are extracted and identified from the remote sensing image.

[0066] Specifically, use a satellite remote sensing platform to obtain the remote sensing image of the target water area, apply the Canny edge detection algorithm to process the remote sensing image to extract the boundary of the water body, perform preprocessing on the extracted water body boundary, including denoising and image enhancement processing, extract and identify feature data from the preprocessed remote sensing image, obtain the pollution adsorption degree of microplastics of different colors, obtain the pollution coverage degree through the surface area of microplastics of different shapes, and obtain the total water body turbidity degree of the water area through microplastics of different particle sizes.

[0067] In one embodiment of the present invention, the total color adsorption ability degree includes the following steps:

[0068] Collect an image data set containing microplastics and other objects. The model extracts the features of the image through a convolutional neural network, including color, size, and shape; the Mask R-CNN mask region convolutional neural network uses a region proposal network to generate potential microplastic positions, classifies and segments the positions, assigns a class label to each potential microplastic position and generates a corresponding mask; use the mouse to draw a polygon to mark the edge of the target object, use the annotation tool to annotate the microplastics and other objects in the image, and save it as a.json format file; convert the.json format to the format matching the training of the Mask R-CNN mask region convolutional neural network. The converted data packet includes image files and corresponding annotation files, and use the converted data to train the Mask R-CNN mask region convolutional neural network to distinguish microplastics and other objects in the image through the trained model;

[0069] According to the color characteristics, the microplastics are divided into three categories, including black, blue and colorless microplastics. The images containing black, blue and colorless microplastics are annotated, and the annotated data set is used to train the classifier to automatically identify and classify microplastics. The object technology method is used to count the microplastics of each color category, and the proportion of the number of microplastics of each color to the total number of microplastics is calculated. The proportion value is used as the weight coefficient. According to the adsorption intensity coefficient set for microplastics of different colors based on the research data, the weight coefficient of each color of microplastics is combined with the adsorption intensity coefficient of the corresponding color, and the combined values ​​of the three colors are added to obtain the total color adsorption capacity of the water area;

[0070] The total color adsorption capacity calculation formula is:

[0071]

[0072] in, is the degree of total color adsorption capacity, The amount of black microplastics, The amount of blue microplastics, is the amount of colorless microplastics, is the total amount of microplastics of three colors, , and is the set adsorption intensity coefficient.

[0073] In one embodiment of the present invention, the overall shape coverage capability comprises the following steps:

[0074] Convert the collected image into a grayscale image, use the pattern recognition algorithm in the image analysis software to identify and classify the shapes of microplastics, detect the change in pixel intensity in the image based on the edge detection algorithm to determine the edge position, extract the edges of microplastics from the image, and apply the contour tracking algorithm to connect the edge points to form an object contour; use the Fourier transform infrared microscope based on a focal plane array to image the microplastic particles to obtain a high-resolution two-dimensional image, use laser ranging to obtain the depth information of the microplastics, combine the depth information with the two-dimensional image, and use a three-dimensional reconstruction algorithm to generate a three-dimensional model of the microplastics, and obtain the surface area data of each microplastic through the three-dimensional model; by analyzing the shape characteristics of the microplastics in the three-dimensional model, classify the microplastics into different shape types, including fibrous, granular, and film-like, count the number of microplastics in each shape category, calculate the surface area of the microplastics in different shapes, multiply the surface area of each shape of microplastics by the corresponding quantity to obtain the total surface area of the corresponding shape, calculate the proportion value of the total surface area of each shape to the combined surface area of the three shapes, use the proportion value as the weight coefficient, the coverage breadth coefficient set for each shape of microplastics, multiply the weight coefficient by the coverage breadth coefficient, and then add the combined values of the three shapes to obtain the total shape coverage ability degree of the water area;

[0075] Formula for calculating the total shape coverage ability degree:

[0076]

[0077]

[0078] Wherein, is the combined surface area of the three shapes, is the number of fibrous microplastics, is the surface area of fibrous microplastics, is the number of granular microplastics, is the surface area of granular microplastics, is the number of film-like microplastics, is the surface area of film-like microplastics, is the total shape coverage ability degree, 、 and are the set coverage breadth coefficients.

[0079] In one embodiment of the present invention, the total water turbidity degree includes the following steps:

[0080] Import the collected images into the open-source ImageJ software. Set the scale bar length and unit in the software, and preprocess the images, including adjusting the contrast and brightness. Manually mark the microplastic particles in the images using the Rectangle tool in the toolbar. For each marked particle, draw a straight line passing through the center of the particle using the functions provided by the software. Calculate and record the maximum size of each particle. Classify the microplastics according to the measured particle sizes into nanoscale microplastics, microscale microplastics, and millimeter-scale microplastics. Collect the particle size data of all particles, perform statistical analysis to obtain the average particle size of the microplastics, count the microplastics in each particle size range, and statistically analyze the number of microplastics in each particle size range. Combine the shape ratios of the microplastics in three different shapes to construct a weighted average particle size. Based on the average particle size of each shape of microplastics and its ratio, obtain the turbidity of the total water body in this water area;

[0081] Formula for calculating the turbidity of the total water body:

[0082]

[0083] Where, is the turbidity of the total water body, is the sum of the particle sizes of fibrous microplastics, is the th particle size of fibrous microplastics, is the number of fibrous microplastics, is the total number of microplastics in three shapes, is the sum of the particle sizes of granular microplastics, is the th particle size of granular microplastics, is the number of granular microplastics, is the sum of the particle sizes of film-like microplastics, is the th particle size of film-like microplastics, is the number of film-like microplastics.

[0084] Specifically, an image dataset containing microplastics and other objects is collected. The model extracts the features of the images through a convolutional neural network, including color, size, and shape data. The Mask R-CNN (Region-based Convolutional Neural Network) generates potential microplastic locations through the Region Proposal Network and then performs classification and segmentation. A class label is assigned to each potential microplastic location and a corresponding mask is generated. The edges of the target objects are marked by drawing polygons with a mouse, and the microplastics and other objects in the images are marked using the marking tool and saved as a.json format file. The.json format is converted into a format matching the training of the Mask R-CNN. The converted data packet includes image files and corresponding annotation files. The Mask R-CNN is trained using the converted data, and the trained model is used to distinguish microplastics and other objects in the images. After extracting the color, shape, and size features of the microplastics, the features are calculated through various methods and algorithms to obtain the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water turbidity degree respectively, providing a basis for constructing the model.

[0085] In one embodiment of the present invention, step S4 includes the following steps:

[0086] According to the feature data extracted from the images, including the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water turbidity degree, after cleaning and standardizing the feature data, a machine learning model capable of predicting the comprehensive pollution degree of the water area is constructed. The collected feature data is used to train the model, and the trained model is deployed to the actual environment. Features are extracted from the new images and the model is used for prediction to obtain the predicted value of the comprehensive pollution degree of the water area.

[0087] Specifically, through various feature data extracted from the images, including the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water turbidity degree, after cleaning and standardizing the various feature data, the feature data with different dimensions is converted to a unified scale. Then, the total color adsorption capacity degree, the total shape coverage capacity degree, and the total water turbidity degree are used as the model inputs, and the comprehensive pollution degree of the water area is used as the model output. A machine learning model capable of predicting the comprehensive pollution degree of the water area is constructed. The collected feature data is used to train the model, and the trained model is deployed to the new actual environment. The same preprocessing and feature extraction are performed on the newly acquired remote sensing images, and the feature data of the new images is used as the input for the deployed model to obtain the predicted value of the comprehensive pollution degree of the water area.

[0088] In one embodiment of the present invention, step S5 includes the following steps:

[0089] After converting the model prediction value point data into surface data, import it into GIS software to generate the spatial distribution of the pollution degree prediction value. Set the prediction value of the comprehensive water pollution degree ≤ 1 as low pollution, 1 < the prediction value of the comprehensive water pollution degree ≤ 2 as medium pollution, and the prediction value of the comprehensive water pollution degree > 2 as heavy pollution. Use different colors to represent different pollution degrees. Among them, green represents low pollution degree, yellow represents medium pollution degree, and red represents high pollution degree. Use the mapping function of GIS software to add annotations and legends. Analyze the spatial distribution of microplastic water pollution and identify hot spots according to GIS tools.

[0090] Specifically, obtain the prediction value of the comprehensive water pollution degree through the model, sort the prediction values according to the longitude and latitude coordinates to ensure that there is a corresponding pollution prediction value at each location. Convert the point data into surface data through the tools in GIS software, import the pollution degree data predicted by the model into GIS software to generate the spatial distribution, and select colors according to the range of the prediction values to represent different levels of pollution degrees. Green represents low pollution degree, yellow represents medium pollution degree, and red represents high pollution degree.

[0091] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing, characterized in that: The following steps are involved: S1: Collect several water samples in the target waters and extract 70% of the sample data for preprocessing; S2: Detect the pre-treated water samples and screen out water samples whose microplastic abundance is greater than or equal to the average abundance of microplastics in the target waters; S3: remote sensing technology is used to obtain remote sensing images of the screened water samples, and the boundaries of the water bodies are extracted by the Canny edge detection algorithm and then preprocessed to extract and identify feature data from the remote sensing images, including the total color adsorption capacity, the total shape coverage capacity and the total water turbidity; S4: Use the collected feature data to build a model and train it, deploy the trained model to the actual environment, extract features from new images and use the model to predict, and obtain the predicted value of the comprehensive pollution degree of the water area; S5: Use GIS technology to visualize the spatial distribution of the predicted values ​​of the comprehensive pollution degree of waters obtained by the model on the map. According to the predicted values ​​of the comprehensive pollution degree of waters and different colors to represent different pollution degrees, use GIS tools to analyze the spatial distribution of microplastic water pollution and identify hot spots; The total color adsorption capacity is obtained by the following formula: in, is the degree of total color adsorption capacity, The amount of black microplastics, The amount of blue microplastics, is the amount of colorless microplastics, is the total amount of microplastics of three colors, , and is the set adsorption intensity coefficient; The total shape coverage degree is obtained by the following formula: in, is the combined surface area of ​​the three shapes, is the amount of fibrous microplastics, is the surface area of ​​fibrous microplastics, is the amount of granular microplastics, is the surface area of ​​granular microplastics, is the amount of film-like microplastics, is the surface area of ​​film-like microplastics, is the total shape coverage capability, , and is the set coverage breadth coefficient; The total water turbidity is obtained by the following formula: in, is the overall water turbidity level, is the particle size and For the The particle size of fibrous microplastics is is the amount of fibrous microplastics, is the total number of microplastics in three shapes, is the particle size and For the The particle size of microplastic particles is is the amount of granular microplastics, is the particle size and For the The particle size of film-like microplastics is is the amount of film-like microplastics.

2. According to the method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing in claim 1, it is characterized in that: The step S1 comprises the following steps: According to the preset sampling point coordinates, the width of the target water area is measured, and several sampling points are arranged at equal distances along the width of the water area. The sampling depth is between 0.5 and 1 meter of the depth of the target water area. Several water samples are collected in the target water area, and 70% of the collected water samples are randomly selected as processing objects, and pre-processing operations are performed on the selected processing objects.

3. According to claim 2, a method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing is characterized in that: The preprocessing operation on the extracted processing object includes the following steps: The extracted treatment objects were subjected to pretreatment operations, including adding 30% hydrogen peroxide with a volume ratio of 10:1 to the samples, and digesting them at a constant temperature of 60°C for 12 hours; mixing the digested water samples with a high-density saturated sodium chloride salt solution for density separation, stirring them evenly and letting them stand for 24 hours to collect the upper solution; filtering the upper solution, and placing the obtained filter paper in a culture dish and drying it at 30°C for 24 hours.

4. According to the method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing in claim 1, it is characterized in that: The step S2 comprises the following steps: The pretreated water samples were tested for microplastics using a microscope visual identification method, and the number, color, size and shape characteristics of the microplastics in each sample were recorded. Based on the test data, the average abundance of microplastics in all samples in the target waters was calculated, and the abundance of microplastics in each sample was compared with the average abundance of the target waters. Water samples with microplastic abundance greater than or equal to the average abundance of microplastics in the target waters were screened out and analyzed.

5. According to the method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing in claim 1, it is characterized in that: The step S3 comprises the following steps: Remote sensing technology is used to obtain remote sensing images of screened water samples. The boundaries of the water bodies are extracted using the Canny edge detection algorithm and then preprocessed, including denoising and image enhancement. Feature data are extracted and identified from the remote sensing images, including the total color adsorption capacity, the total shape coverage capacity and the total water turbidity.

6. The method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing according to claim 5 is characterized in that: The total color adsorption capacity degree comprises the following steps: Collect image datasets containing microplastics and other objects. The model uses a convolutional neural network to extract image features, including color, size, and shape. The Mask R-CNN mask region convolutional neural network uses a region proposal network to generate potential microplastic locations, classify and segment the locations, assign a category label to each potential microplastic location, and generate a corresponding mask. Use the mouse to draw a polygon to mark the edge of the target object, use the annotation tool to annotate the microplastics and other objects in the image, and save it as a .json file. Convert the .json format to a format that matches the Mask R-CNN mask region convolutional neural network training. The converted data package includes image files and corresponding annotation files. Use the converted data to train the Mask R-CNN mask region convolutional neural network, and use the trained model to distinguish microplastics from other objects in the image. Based on color characteristics, microplastics are divided into three categories, including black, blue and colorless microplastics. Images containing black, blue and colorless microplastics are annotated, and the annotated data set is used to train the classifier to automatically identify and classify microplastics. The microplastics in each color category are counted using object technology methods, and the proportion of the number of microplastics of each color to the total number of microplastics is calculated. The proportion value is used as the weight coefficient, and the adsorption intensity coefficient of each color of microplastics is set according to the research data. After the weight coefficient of each color of microplastics is combined with the adsorption intensity coefficient of the corresponding color, the combined values ​​of the three colors are added to obtain the total color adsorption capacity of the water area.

7. The method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing according to claim 5 is characterized in that: The overall shape coverage capability degree comprises the following steps: The collected images are converted into grayscale images, and the pattern recognition algorithm in the image analysis software is used to identify and classify the shapes of microplastics. The edge detection algorithm detects the changes in pixel intensity in the image to determine the edge position, extracts the edges of microplastics from the image, and uses the contour tracking algorithm to connect the edge points to form the object contour; a Fourier transform infrared microscope based on a focal plane array is used to image the microplastic particles to obtain high-resolution two-dimensional images, and laser ranging is used to obtain the depth information of the microplastics. The depth information is combined with the two-dimensional image, and a three-dimensional reconstruction algorithm is used to generate a three-dimensional model of the microplastics. The surface of each microplastic is obtained through the three-dimensional model. area data; by analyzing the shape characteristics of microplastics in the three-dimensional model, microplastics are divided into different shape types, including fibrous, granular and film-like, the number of microplastics in each shape category is counted, the surface area of ​​microplastics of different shapes is calculated, the surface area of ​​microplastics of each shape is multiplied by the corresponding number to obtain the total surface area of ​​the corresponding shape, the proportion of the total surface area of ​​each shape to the combined surface area of ​​the three shapes is calculated, the proportion value is used as the weight coefficient, and the coverage breadth coefficient is set for each shape of microplastics. After multiplying the weight coefficient by the coverage breadth coefficient, the joint values ​​of the three shapes are added to obtain the total shape coverage capacity of the water area.

8. The method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing according to claim 5 is characterized in that: The total water turbidity degree comprises the following steps: Import the collected images into ImageJ open source software, set the scale length and unit in the software, preprocess the images, including adjusting the contrast and brightness, and use the Rectangle tool in the toolbar to manually mark the microplastic particles in the image. For each marked particle, use the function provided by the software to draw a straight line through the center of the particle, calculate and record the maximum size of each particle, and classify the microplastics according to the measured particle size, including nano-scale microplastics, micron-scale microplastics, and millimeter-scale microplastics. Collect the particle size data of all particles, perform statistical analysis to obtain the average particle size of the microplastics, count the microplastics in each particle size range, count the number of microplastics in each particle size range, and jointly construct a weighted average particle size based on the shape ratio of three different shapes of microplastics. According to the average particle size of each shape of microplastics and its ratio, the total water turbidity of the water area is obtained.

9. The method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing according to claim 1, characterized in that: The step S4 comprises the following steps: Based on the feature data extracted from the image, including the total color adsorption capacity, the total shape covering capacity and the total water turbidity, a machine learning model that can predict the comprehensive pollution level of the water area is constructed after cleaning and standardization operations. The model is trained using the collected feature data, and the trained model is deployed in the actual environment. Features are extracted from new images and predicted using the model to obtain the predicted value of the comprehensive pollution level of the water area.

10. The method for identifying the spatial distribution of microplastic-contaminated waters based on remote sensing according to claim 1, characterized in that: The step S5 comprises the following steps: The model prediction value point data is converted into surface data and imported into GIS software to generate the spatial distribution of the pollution degree prediction value; the water area comprehensive pollution degree prediction value is set as low pollution when ≤1, medium pollution when 1<water area comprehensive pollution degree prediction value ≤2, and heavy pollution when 2<water area comprehensive pollution degree prediction value. Different colors are used to represent different pollution degrees, among which green represents low pollution degree, yellow represents medium pollution degree, and red represents high pollution degree. The mapping function of GIS software is used to add annotations and legends; the spatial distribution of microplastic water pollution is analyzed and hot spots are identified based on GIS tools.

Images