A method for predicting water body phosphate concentration based on multispectral images

Abstract

The present invention relates to the technical field of water quality data analysis, and specifically to a method for predicting the phosphate concentration in water bodies based on multi-spectral images. The key points of its technical solution include: data collection, image preprocessing, determination of absorption characteristics, selection of key bands and feature extraction, model establishment and training, and real-time prediction and optimization to improve the continuity and accuracy within the prediction area; by using a method that combines laboratory simulation with on-site data, the present invention directly utilizes the specific absorption characteristics of the complex formed by the reaction of phosphate with metal ions such as iron and aluminum in the red edge or near-infrared band to construct a high-precision and real-time online phosphate concentration prediction system. Through multiple links such as image preprocessing, selection of key bands, spectral feature extraction, establishment of a non-linear regression model, and optimization of spatio-temporal data, it successfully solves the defects of traditional remote sensing methods that rely on indirect indicators and are greatly affected by the environment, and significantly improves the accuracy and reliability of water quality monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality data analysis, and particularly to a method for predicting the concentration of phosphate in water bodies based on multi-spectral images. Background Art

[0002] Currently, the problem of water eutrophication is becoming increasingly serious. Among them, phosphate, as one of the main nutrient salts, its excessive presence often causes abnormal reproduction of algae and water bloom phenomena, thereby threatening the ecological balance and water quality safety. Traditional monitoring of phosphate in water bodies mainly relies on laboratory chemical analysis methods, such as spectrophotometry, ion chromatography, and electrochemical sensing technology. Although these methods are accurate, they have defects such as long sample collection, transportation, and detection cycles, and limited spatial coverage, making it difficult to meet the requirements of large-scale and real-time online monitoring. In recent years, remote sensing technology has been widely used in water quality monitoring, and the monitoring method based on multi-spectral images has attracted much attention due to its wide coverage and strong real-time performance.

[0003] However, due to the lack of obvious spectral response of phosphate itself, traditional multi-spectral remote sensing methods usually rely on indirect indicators (such as chlorophyll concentration, suspended solid concentration, etc.) for inference, resulting in low prediction accuracy and being greatly affected by the environment. The existing technology has not fully utilized the specific absorption characteristics shown by phosphate in water when reacting with metal ions such as iron and aluminum to form complexes in the red edge or near-infrared band as the basis for directly reflecting the change of phosphate concentration, thus limiting the application effect of remote sensing technology in water quality monitoring. To solve the above problems, we propose a method for predicting the concentration of phosphate in water bodies based on multi-spectral images. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a method for predicting the concentration of phosphate in water bodies based on multi-spectral images, which solves the problems raised in the background art.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions:

[0006] A method for predicting the concentration of phosphate in water bodies based on multi-spectral images, comprising:

[0007] S1. Data collection, which is used to collect multi-temporal multi-spectral image data of the target water body and on-site environmental parameters, where the environmental parameters include the pH value, temperature, dissolved oxygen content of the water body, and the concentration of metal ions such as iron and aluminum;

[0008] S2. Image preprocessing, which is used to perform atmospheric, geometric, and radiometric corrections on the collected images, and use the water body masking technology to segment the water body area of the image, so as to extract the spectral reflectance data of the effective water body area;

[0009] S3. Absorption characteristic determination is used to measure the absorption peak position, absorption depth, and bandwidth parameters of the complex formed by the reaction of metal ions such as iron and aluminum with phosphate in the red edge or near-infrared band under laboratory conditions by simulating the water environment and adjusting the metal ion concentration and pH value.

[0010] S4. Key band selection and feature extraction adaptively select the key bands corresponding to the absorption peaks of the complex according to the results of S3, extract the reflectance data of each key band from the image data extracted in S2, and use smoothing filtering to improve the signal-to-noise ratio of the data to construct the spectral feature vector of the water body area.

[0011] S5. Model establishment and training are used to establish a mathematical model between the phosphate concentration and the spectral features extracted in S4 by using the phosphate concentration data obtained from on-site sampling in combination with the metal ion concentration and pH value collected in S1 through the nonlinear least squares regression method, and optimize the model parameters by using cross-validation.

[0012] S6. Real-time prediction and optimization are used to input the spectral features extracted by S4 from the latest collected multi-spectral image data into the S5 model, calculate the phosphate concentration of each area of the water body in real time, and use Kriging interpolation and time series analysis to optimize the spatio-temporal coupling of the preliminary prediction results to improve the continuity and accuracy within the prediction area.

[0013] By adopting the above technical solution, the multi-spectral image data collected in the S1 step includes visible light, red edge, and near-infrared band data, and the on-site environmental parameters are collected in real time by a portable water quality monitoring instrument to ensure data synchronization and accuracy.

[0014] By adopting the above technical solution, the image preprocessing adopted in the S2 step includes:

[0015] Using an atmospheric correction algorithm to eliminate atmospheric scattering interference;

[0016] Adopting geometric correction technology to eliminate image distortion;

[0017] Applying a water body masking algorithm based on threshold segmentation or edge detection to accurately distinguish the water body area from land and clouds.

[0018] By adopting the above technical solution, in the S3 step, by performing spectral scanning under the conditions of controlling temperature, pH value, and metal ion concentration, the absorption peak position of the complex (such as wavelength λ≈680–720nm), absorption depth, and bandwidth parameters are determined, and the quantitative relationship between them and the changes in metal ion concentration and pH value is recorded.

[0019] By adopting the above technical solution, the spectral feature vectors extracted in the step S4 are subjected to smoothing filtering and then normalized to eliminate the reflectance deviation caused by environmental light changes, ensuring that the extracted features reflect the complex absorption characteristics.

[0020] By adopting the above technical solution, the calibration model established in the step S5 is a non-linear least squares regression model, where the model parameters are determined by cross-validation, and the metal ion concentration and pH value are used as covariates in the model to improve the prediction accuracy.

[0021] By adopting the above technical solution, the spatio-temporal optimization adopted in the step S6 includes:

[0022] Interpolating the spatial distribution data by using the Kriging interpolation method to ensure the continuity of the predicted values in each region of the water body;

[0023] Combining time series analysis to smooth and correct the trend of multi-temporal data to eliminate the influence of short-term fluctuations on the prediction accuracy.

[0024] By adopting the above technical solution, the predicted results of the water body phosphate concentration after the S6 optimization are output in the form of spatio-temporal distribution maps and statistical charts, and data visualization is realized through the GIS system.

[0025] In summary, the present invention mainly has the following beneficial effects:

[0026] 1. By simulating the water body environment under laboratory conditions, adjusting the concentrations of metal ions such as iron and aluminum and the pH value, accurately measuring the absorption peak position, absorption depth and bandwidth parameters of the phosphate complex formed by the reaction of phosphate with these metal ions in the red edge or near-infrared band, and establishing the quantitative relationship between them and the phosphate concentration, the absorption characteristics of the complex in a specific band are directly utilized, making up for the defect that the traditional remote sensing technology cannot directly reflect the change of phosphate concentration.

[0027] 2. By adaptively selecting the key bands corresponding to the laboratory measurement results, extracting the spectral data directly reflecting the complex absorption characteristics from the multi-spectral images, combining atmospheric, geometric and radiometric corrections and water body masking techniques to ensure the accuracy and regional continuity of the extracted data, and then establishing an accurate phosphate concentration prediction model, the real-time and direct monitoring of the water body phosphate concentration is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic flow chart of the method for predicting the water body phosphate concentration of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0030] The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of protection of the present invention. The conditions in the embodiments can be further adjusted according to specific conditions. Any simple improvement to the method of the present invention under the premise of the concept of the present invention belongs to the scope of protection required by the present invention.

[0031] Embodiment 1

[0032] Reference Figure 1 , a method for predicting the phosphate concentration in water based on multispectral images. In this embodiment, a certain reservoir is used as the target water body. By combining laboratory and field data, the feasibility of the technology for predicting the phosphate concentration in water based on multispectral images is verified. The specific steps are as follows:

[0033] S1. Data collection: After selecting the target reservoir area on-site, a high-resolution multispectral remote sensing instrument is used to collect image data of this area. The collected images cover three bands: visible light, red edge, and near-infrared, which can capture the reflection characteristics of the water body under different spectra. At the same time, a portable water quality monitoring instrument is used to record the environmental parameters of the water body in real time, including pH value, temperature, dissolved oxygen, and the concentrations of metal ions such as iron and aluminum, ensuring the synchronization of the image data and the on-site water quality parameters in terms of time and space, providing a reliable basis for subsequent analysis.

[0034] S2. Image preprocessing: The collected original image data needs to be preprocessed to eliminate the interference caused by the environment and the instrument. First, the atmospheric correction technology is used for the image data to remove the atmospheric scattering and absorption effects and restore the true reflectance of the water body. Subsequently, the geometric correction technology is used to eliminate the image distortion caused by sensor movement and terrain undulation. Finally, an automated segmentation algorithm is used to generate a water body mask to accurately distinguish the water body area from the land and clouds, so as to only extract the reflectance data within the water body area for subsequent processing.

[0035] S3. Absorption characteristic determination: Under laboratory conditions, a simulated water environment is set up. By adjusting the temperature, pH value, and the concentrations of metal ions such as iron and aluminum, the absorption characteristics of the complex formed by the reaction of phosphate with metal ions are studied. The simulated water body is scanned using a spectrometer, with a focus on the absorption characteristics in the red edge or near-infrared band (such as the 680–720 nm region). The absorption peak position, absorption depth, and bandwidth parameters of the complex are obtained through experiments, and the relationships between these parameters and the metal ion concentration and pH value are recorded, providing a scientific basis for the selection of key bands.

[0036] S4. Key band selection and feature extraction: Based on the absorption characteristics measured in the laboratory, the key bands related to the absorption of the complex in the red edge or near-infrared region are determined. Using the preprocessed image data, the reflectance information of these key bands is extracted to construct a vector representing the spectral characteristics of the water body. To improve the reliability of the data, the reflectance data of each band are first smoothed to reduce noise interference; then normalization processing is carried out to eliminate the deviation caused by different environmental lighting conditions, so that the extracted features can truly reflect the absorption characteristics of the complex.

[0037] S5. Model establishment and training: Using the actual phosphate concentration data collected on-site, as well as the spectral features and environmental parameters (such as iron ion concentration and pH value) extracted from the images, a non-linear regression model is constructed. This model continuously adjusts the model parameters by minimizing the error between the predicted value and the actual value. To ensure that the model has strong generalization ability and robustness, the cross-validation method is used to optimize the model parameters. Through this process, a mathematical model that can reflect the relationship between the phosphate concentration in the water body, the key spectral features, and the environmental parameters is constructed.

[0038] S6. Real-time prediction and optimization: After the model is established, using the latest collected multi-spectral images and on-site environmental data, the phosphate concentration in each region of the water body is predicted in real time through the trained model. To ensure the spatial continuity and accuracy of the prediction results, the Kriging interpolation method is used to optimize the predicted values in each region. At the same time, combined with time series analysis, the multi-temporal data are smoothed and trend corrected to effectively eliminate the interference caused by short-term environmental fluctuations, thereby obtaining more stable and reliable spatio-temporal prediction results;

[0039] Then, the spatio-temporally optimized prediction results are integrated and displayed through the GIS system to generate intuitive spatio-temporal distribution maps and statistical charts. Users can intuitively understand the dynamic changes in the phosphate concentration in each region of the water body through these visual graphs, which is convenient for the timely implementation of water quality management and early warning measures.

[0040] In this embodiment, a method combining laboratory simulation with on-site data is used. By directly utilizing the specific absorption characteristics of the complex formed by the reaction of phosphate with metal ions such as iron and aluminum in the red edge or near-infrared band, a high-precision, real-time on-line phosphate concentration prediction system is constructed. Through multiple steps such as image preprocessing, key band selection, spectral feature extraction, non-linear regression model establishment, and spatio-temporal data optimization, the defects of traditional remote sensing methods relying on indirect indicators and being greatly interfered by the environment are successfully solved, and the accuracy and reliability of water quality monitoring are significantly improved.

[0041] Example 2

[0042] In this embodiment, to verify the superiority of the method of the present invention, we carried out a comparative experiment in the same water body area. The improved method of the present invention and the conventional remote sensing method based on multi-spectral images were respectively used to predict the phosphate concentration in the water body, and a comparative analysis was carried out with the water sample detection data collected on-site.

[0043] Experimental design

[0044] Data collection: In the same reservoir area, image data was collected using the same multi-spectral remote sensing instrument. The collected data all included visible light, red edge, and near-infrared bands. At the same time on-site, a portable water quality monitoring instrument was used to record the environmental parameters of the water body (pH value, temperature, dissolved oxygen, and the concentrations of metal ions such as iron and aluminum), and water samples were collected for laboratory phosphate concentration detection as the true value.

[0045] Conventional method: A regression model was mainly established using the indicators that indirectly reflect the water body condition in the image (such as chlorophyll concentration and suspended solid concentration) to predict the phosphate concentration. Since phosphate itself lacks an obvious spectral response, this method has a large prediction error under different lighting and environmental interferences.

[0046] Method of Example 1: By simulating the water body environment in the laboratory and adjusting the concentrations of metal ions such as iron and aluminum and the pH value, the specific absorption characteristics of the complex in the red edge or near-infrared band were obtained. Subsequently, using adaptive key band selection, spectral smoothing, and normalization processing, the spectral features reflecting the absorption characteristics of the complex were directly extracted from the image data, and a non-linear regression model was established in combination with the on-site environmental parameters to achieve direct prediction of the phosphate concentration.

[0047] The experimental results and comparisons are shown in Table 1:

[0048]

[0049] Table 1

[0050] Prediction accuracy: The experimental results show that there are large deviations between the prediction results of the conventional method under different environmental conditions and the actual water sample detection values, and the error fluctuations are obvious.

[0051] Since the method of the present invention directly utilizes the absorption characteristics of the complex, the prediction results are more consistent with the actual detection data, and the overall error is significantly reduced.

[0052] Environmental adaptability: Since the conventional method relies on indirect indicators, its prediction results are easily affected by environmental factors such as light and meteorology, and there is a large degree of uncertainty.

[0053] The method of the present invention determines the key absorption characteristics through the laboratory and applies the corresponding correction strategy to the on-site data, effectively eliminating the influence of environmental light changes and other interferences on the prediction results and improving the stability of the system.

[0054] Spatio-temporal continuity: When making spatial predictions for water body areas, due to large data fluctuations, the prediction results of the conventional method are not smooth enough in spatial distribution.

[0055] The method of the present invention combines Kriging interpolation and time series smoothing processing, not only achieving continuous and uniform prediction effects in space, but also effectively correcting short-term fluctuations, making the prediction results more stable in the time domain.

[0056] It can be seen from the comparison experiment that the method of the present invention has higher prediction accuracy, better environmental adaptability and better spatio-temporal continuity in the real-time monitoring of water body phosphate concentration compared with the traditional remote sensing method based on multi-spectral images, which provides more reliable technical support for actual water quality monitoring and early warning.

[0057] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those of ordinary skill in the field to which the present invention belongs. The terms "including" or "comprising" and the like used in the present invention mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. The terms "connected" or "coupled" and the like are not limited to physical or mechanical connections, and may also include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0058] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting phosphate concentration in water based on multispectral images, characterized in that: include: S1. Data acquisition, used to collect multi-phase multi-spectral image data of the target water body and on-site environmental parameters, where the environmental parameters include pH value, temperature, dissolved oxygen content, and iron and aluminum metal ion concentrations of the water body; S2, image preprocessing, used to perform atmospheric, geometric and radiation correction on the collected images, and use water mask technology to segment the water area of ​​the image, so as to extract the spectral reflectance data of the effective area of ​​the water body; S3, absorption characteristics determination, used to determine the absorption peak position, absorption depth and bandwidth parameters of the complex formed by the reaction of iron and aluminum metal ions with phosphate in the red edge or near infrared band under laboratory conditions by simulating the water environment and adjusting the metal ion concentration and pH value; S4, key band selection and feature extraction, according to the results of S3, the key band corresponding to the absorption peak of the complex is adaptively selected, the reflectance data of each key band is extracted from the image data extracted by S2, and smoothing filtering is used to improve the data signal-to-noise ratio, and the spectral feature vector of the water area is constructed; S5, model building and training, is used to use the phosphate concentration data obtained from field sampling, combined with the metal ion concentration and pH value collected in S1, to establish a mathematical model between the phosphate concentration and the spectral features extracted by S4 through a nonlinear least squares regression method, and to optimize the model parameters using cross-validation; S6, real-time prediction and optimization, is used to input the spectral features of the latest multispectral image data extracted by S4 into the S5 model, calculate the phosphate concentration in each area of ​​the water body in real time, and use Kriging interpolation and time series analysis to perform spatiotemporal coupling optimization on the preliminary prediction results to improve the continuity and accuracy within the prediction area.

2. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The multispectral image data collected in step S1 includes visible light, red edge and near infrared band data, and the on-site environmental parameters are collected in real time through a portable water quality monitoring instrument to ensure data synchronization and accuracy.

3. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The image preprocessing used in step S2 includes: Use atmospheric correction algorithm to eliminate atmospheric scattering interference; Use geometric correction technology to eliminate image distortion; The water mask algorithm based on threshold segmentation or edge detection is used to accurately distinguish water areas from land and clouds.

4. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: In the step S3, the absorption peak position, absorption depth and bandwidth parameters of the complex are determined by performing spectral scanning under the conditions of controlling temperature, pH value and metal ion concentration, and the quantitative relationship between the absorption peak position, absorption depth and bandwidth parameters as the metal ion concentration and pH value change is recorded.

5. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The spectral feature vector extracted in step S4 is normalized after being smoothed and filtered to eliminate the reflectivity deviation caused by changes in ambient light, ensuring that the proposed feature reflects the complex absorption characteristics.

6. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The calibration model established in step S5 is a nonlinear least squares regression model, in which the model parameters are determined by cross-validation, and the metal ion concentration and pH value are used as covariates in the model to improve the prediction accuracy.

7. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The spatiotemporal optimization used in step S6 includes: The spatial distribution data are interpolated using the Kriging interpolation method to ensure the continuity of the predicted values ​​in each area of ​​the water body; Combined with time series analysis, multi-temporal data are smoothed and trend corrected to eliminate the impact of short-term fluctuations on prediction accuracy.

8. The method for predicting phosphate concentration in water based on multispectral imaging according to claim 1, characterized in that: The water body phosphate concentration prediction results after S6 optimization are output in the form of spatiotemporal distribution diagrams and statistical diagrams, and data visualization is achieved through a GIS system.

Images