High-concentration salt wastewater evaporation pond identification and supervision method based on hyperspectral remote sensing

Abstract

The invention discloses a high-concentration salt wastewater evaporation pond identification and supervision method based on hyperspectral remote sensing. The method specifically comprises the following steps: acquiring hyperspectral remote sensing image data of a target area; a2, preprocessing the hyperspectral remote sensing image data to eliminate atmospheric and topographic influences, utilizing hyperspectral data with hundreds of continuous wavebands to finely capture unique spectral characteristics of the high-concentration salt wastewater, effectively distinguishing the high-concentration salt wastewater from common water, soil and other ground features, greatly improving the accuracy and reliability of evaporation pond identification, and improving the identification accuracy and reliability of the evaporation pond. The method is advantaged in that misjudgment and missed judgment are reduced, through automatic comparison and analysis of multi-temporal data, abnormal changes of the evaporation pond in area, shape or spectral characteristics can be timely discovered, an early warning mechanism is automatically triggered based on a preset threshold value, crossing from static identification to dynamic supervision and from post-event disposal to pre-event early warning is realized, and the method is advantaged in that the early warning efficiency is improved. And the response speed and initiative of environment supervision are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of high-concentration saline wastewater evaporation identification and monitoring technology, specifically a method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing. Background Technology

[0002] Evaporation ponds are facilities, either naturally or artificially constructed, that vaporize water in high-salt wastewater through natural evaporation or artificial heating, concentrating salt and impurities to ultimately form salt crystals or high-concentration salt solutions. According to the patent document, entitled "A Wastewater Pollution Monitoring Method and Device Based on Multispectral Imagery" (Patent Publication No.: CN115639159A, Patent Publication Date: 2023-01-24), the method includes: acquiring time-series multispectral remote sensing image data of the water area to be monitored, and using the 2SeaColor analytical model to invert each multispectral remote sensing image data in the time-series multispectral remote sensing image data to obtain the optical characteristic data of each multispectral remote sensing image data; calculating the wastewater pollution index of each multispectral remote sensing image data based on the optical characteristic data of each multispectral remote sensing image data; constructing a wastewater pollution index time series based on the wastewater pollution index of each multispectral remote sensing image data; and performing spatiotemporal pattern analysis on the wastewater pollution index time series to obtain the analysis results. The analysis results are used to characterize the water quality change trend of the water area to be monitored, thus solving the technical problem of poor applicability of existing wastewater pollution remote sensing monitoring algorithms.

[0003] Based on the descriptions in the aforementioned documents, existing traditional remote sensing methods have limited and discontinuous spectral bands, making it difficult to capture the subtle and unique spectral characteristics of high-concentration saline wastewater. This leads to easy confusion with ordinary water bodies, saline-alkali land, or other spectrally similar features during identification, resulting in misjudgments and missed detections, and insufficient reliability. Furthermore, traditional methods primarily focus on static identification and mapping, failing to achieve efficient and automated dynamic monitoring. Supervision often relies on manual comparison of images from different periods, and by the time an anomaly is detected, it is often too late, representing a passive, reactive approach with slow response times, unable to provide early warnings and risk prevention. Therefore, this invention provides a method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method for identifying and monitoring evaporation ponds of high-concentration saline wastewater based on hyperspectral remote sensing. This method solves the problems of traditional remote sensing methods having limited and discontinuous spectral bands, making it difficult to capture the subtle and unique spectral characteristics of high-concentration saline wastewater. This leads to easy confusion with ordinary water bodies, saline-alkali land, or other spectrally similar features, resulting in misjudgments and missed detections, and insufficient reliability. Furthermore, traditional methods primarily focus on static identification and mapping, failing to achieve efficient and automated dynamic monitoring. Monitoring often relies on manual comparison of images from different periods, and by the time anomalies are detected, it is often too late, representing a passive, reactive approach with slow response times, unable to provide early warnings and risk prevention.

[0005] To achieve the above objectives, the present invention provides a method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing, specifically comprising the following steps: A1. Acquire hyperspectral remote sensing image data of the target area; A2. Preprocess the hyperspectral remote sensing image data to eliminate the effects of atmosphere and topography; A3. Based on the preprocessed hyperspectral data, extract the spectral features related to the high-concentration saline wastewater evaporation pond; A4. Analyze the extracted spectral features using a classification model to identify the distribution area of ​​high-concentration saline wastewater evaporation ponds; A5. Based on the identification results, dynamic monitoring of the high-concentration saline wastewater evaporation pond will be carried out, including change monitoring and anomaly early warning.

[0006] Preferably, acquiring hyperspectral remote sensing image data in A1 includes: Use airborne or spaceborne hyperspectral sensors to collect data in the visible to short-wave infrared bands, with no fewer than 100 bands and a spectral resolution better than 10 nanometers.

[0007] Preferably, the preprocessing in A2 includes: Radiometric calibration, atmospheric correction, and geometric correction are performed on hyperspectral remote sensing image data to generate surface reflectance data.

[0008] Preferably, the extraction of spectral features from A3 includes: Calculate spectral characteristic parameters based on the salinity index, which includes the normalized differential salinity index and the salinity absorption characteristic depth.

[0009] Preferably, the classification model in A4 is a machine learning model, including support vector machine, random forest and neural network models, and the training of the classification model is supervised learning using the spectral feature data of the extracted evaporation pond samples.

[0010] Preferably, the dynamic monitoring in A5 includes: By comparing multi-temporal hyperspectral data, changes in the area, shape, or spectral characteristics of evaporation ponds can be monitored, and change reports can be automatically generated.

[0011] Preferably, the anomaly warning is triggered based on a preset threshold as follows: When the spectral characteristics of the evaporation pond change beyond a threshold, the system automatically issues an alarm and sends it to the monitoring terminal via the communication network.

[0012] Preferably, the identification and monitoring results are output in the form of a visual map and integrated into a geographic information system platform for environmental management decision-making.

[0013] Beneficial effects This invention provides a method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing. Compared with existing technologies, it has the following advantages: This method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing acquires hyperspectral remote sensing image data of the target area; preprocesses the hyperspectral remote sensing image data to eliminate atmospheric and topographical influences; extracts spectral features related to high-concentration saline wastewater evaporation ponds based on the preprocessed hyperspectral data; analyzes the extracted spectral features using a classification model to identify the distribution areas of high-concentration saline wastewater evaporation ponds; and dynamically monitors the high-concentration saline wastewater evaporation ponds based on the identification results, including change monitoring and anomaly early warning. Utilizing hyperspectral data with hundreds of continuous bands, it can precisely capture the unique spectral characteristics of high-concentration saline wastewater, effectively distinguishing it from ordinary water bodies, soil, and other land features, greatly improving the accuracy and reliability of evaporation pond identification and reducing false positives and false negatives. Through automatic comparative analysis of multi-temporal data, it can promptly detect abnormal changes in the area, shape, or spectral characteristics of evaporation ponds and automatically trigger an early warning mechanism based on preset thresholds. This achieves a leap from static identification to dynamic monitoring, and from post-event handling to pre-event early warning, greatly improving the response speed and proactivity of environmental supervision. Attached Figure Description

[0014] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Please see Figure 1 This invention provides two technical solutions: A method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing, specifically including the following steps: A1. Acquire hyperspectral remote sensing image data of the target area; A2. Preprocess the hyperspectral remote sensing image data to eliminate the effects of atmosphere and topography; A3. Based on the preprocessed hyperspectral data, extract the spectral features related to the high-concentration saline wastewater evaporation pond; A4. Analyze the extracted spectral features using a classification model to identify the distribution area of ​​high-concentration saline wastewater evaporation ponds; A5. Based on the identification results, dynamic monitoring of the high-concentration saline wastewater evaporation pond will be carried out, including change monitoring and anomaly early warning.

[0017] In this embodiment, acquiring hyperspectral remote sensing image data in A1 includes: Use airborne or spaceborne hyperspectral sensors to collect data in the visible to short-wave infrared bands, with no fewer than 100 bands and a spectral resolution better than 10 nanometers.

[0018] By using airborne or spaceborne hyperspectral sensors to collect data in the visible to shortwave infrared bands, with no fewer than 100 bands and a spectral resolution better than 10 nanometers, high-precision, high-spectral-resolution hyperspectral remote sensing image data can be obtained. This provides rich and continuous spectral information for subsequent identification, effectively supporting the fine identification of high-concentration saline wastewater evaporation ponds and avoiding the misjudgment and omission problems caused by the limited number of bands in traditional multispectral data.

[0019] In this embodiment, the preprocessing in A2 includes: Radiometric calibration, atmospheric correction, and geometric correction are performed on hyperspectral remote sensing image data to generate surface reflectance data.

[0020] By performing radiometric calibration, atmospheric correction, and geometric correction on hyperspectral remote sensing image data, surface reflectance data is generated, effectively eliminating the influence of atmosphere and topography, improving the accuracy and reliability of the data, ensuring that subsequent spectral feature extraction and classification analysis are based on real surface reflectance information, reducing interference from environmental factors, and improving the stability of high-concentration saline wastewater evaporation pond identification.

[0021] In this embodiment, the extraction of spectral features from A3 includes: Calculate spectral characteristic parameters based on the salinity index, which includes the normalized differential salinity index and the salinity absorption characteristic depth.

[0022] By calculating spectral feature parameters based on salinity index, including normalized differential salinity index and salinity absorption feature depth, the unique spectral features of high-concentration saline wastewater evaporation ponds can be precisely captured, enhancing the ability to distinguish them from other land features such as ordinary water bodies and saline-alkali land, improving identification specificity and accuracy, and providing key input features for classification models.

[0023] In this embodiment, the classification model in A4 is a machine learning model, including support vector machine, random forest and neural network models. The training of the classification model is supervised learning using the spectral feature data of the extracted evaporation pond samples.

[0024] By analyzing the extracted spectral features using machine learning models (including support vector machines, random forests, and neural network models) and conducting supervised learning using spectral feature data from known evaporation pond samples, the distribution area of ​​high-concentration saline wastewater evaporation ponds can be accurately identified. This enables automated and high-precision classification and identification, reduces manual intervention, and improves identification efficiency and reliability.

[0025] In this embodiment, the dynamic monitoring mentioned in A5 includes: By comparing multi-temporal hyperspectral data, changes in the area, shape, or spectral characteristics of evaporation ponds can be monitored, and change reports can be automatically generated.

[0026] By comparing multi-temporal hyperspectral data, changes in the area, shape, or spectral characteristics of evaporation ponds can be monitored, and change reports can be automatically generated to achieve dynamic supervision. This enables timely detection of abnormal changes in evaporation ponds, supports continuous monitoring and decision-making in environmental management, shifts from post-event handling to pre-event early warning, and improves the initiative and response speed of supervision.

[0027] In this embodiment, the anomaly warning is triggered based on a preset threshold as follows: When the spectral characteristics of the evaporation pond change beyond a threshold, the system automatically issues an alarm and sends it to the monitoring terminal via the communication network.

[0028] Based on preset thresholds to trigger abnormal early warnings, when the spectral characteristics of the evaporation pond change beyond the threshold, the system automatically issues an alarm and sends it to the monitoring terminal via the communication network, thereby achieving rapid early warning and risk prevention, avoiding the deterioration of environmental problems, and improving the real-time and automation level of monitoring.

[0029] The preset thresholds are: changes in the normalized differential salinity index exceeding ±10% and increases in the salinity absorption feature depth exceeding 0.05 are considered abnormal.

[0030] In this embodiment, the identification and monitoring results are output in the form of a visual map and integrated into a geographic information system platform for environmental management decision-making.

[0031] The identification and monitoring results are output in the form of a visual map and integrated into the geographic information system platform for environmental management decision-making. This provides an intuitive display of spatial information, facilitating managers to conduct visual analysis and policy formulation, and enhancing the practicality and integration of the method.

[0032] In summary, this study involves acquiring hyperspectral remote sensing image data of the target area; preprocessing the hyperspectral remote sensing image data to eliminate atmospheric and topographical influences; extracting spectral features related to high-concentration saline wastewater evaporation ponds based on the preprocessed hyperspectral data; analyzing the extracted spectral features using a classification model to identify the distribution areas of high-concentration saline wastewater evaporation ponds; and dynamically monitoring the high-concentration saline wastewater evaporation ponds based on the identification results, including change monitoring and anomaly early warning.

[0033] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0034] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0035] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing, characterized in that: Specifically, the following steps are included: A1. Acquire hyperspectral remote sensing image data of the target area; A2. Preprocess the hyperspectral remote sensing image data to eliminate the effects of atmosphere and topography; A3. Based on the preprocessed hyperspectral data, extract the spectral features related to the high-concentration saline wastewater evaporation pond; A4. Analyze the extracted spectral features using a classification model to identify the distribution area of ​​high-concentration saline wastewater evaporation ponds; A5. Based on the identification results, dynamic monitoring of the high-concentration saline wastewater evaporation pond will be carried out, including change monitoring and anomaly early warning.

2. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The hyperspectral remote sensing image data acquired in A1 includes: Use airborne or spaceborne hyperspectral sensors to collect data in the visible to short-wave infrared bands, with no fewer than 100 bands and a spectral resolution better than 10 nanometers.

3. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The preprocessing in A2 includes: Radiometric calibration, atmospheric correction, and geometric correction are performed on hyperspectral remote sensing image data to generate surface reflectance data.

4. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The spectral features extracted from A3 include: Calculate spectral characteristic parameters based on the salinity index, which includes the normalized differential salinity index and the salinity absorption characteristic depth.

5. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The classification model in A4 is a machine learning model, including support vector machine, random forest and neural network models. The training of the classification model is supervised learning using the spectral feature data of the extracted evaporation pond samples.

6. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The dynamic monitoring mentioned in A5 includes: By comparing multi-temporal hyperspectral data, changes in the area, shape, or spectral characteristics of evaporation ponds can be monitored, and change reports can be automatically generated.

7. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The abnormal warning is triggered based on a preset threshold as follows: When the spectral characteristics of the evaporation pond change beyond a threshold, the system automatically issues an alarm and sends it to the monitoring terminal via the communication network.

8. The method for identifying and monitoring high-concentration saline wastewater evaporation ponds based on hyperspectral remote sensing according to claim 1, characterized in that: The identification and monitoring results are output in the form of a visual map and integrated into a geographic information system platform for environmental management decision-making.

Images