Retrieval of Water Quality Parameters Based on Near-Surface Remote Sensing and Machine Learning Algorithm

Abstract

With the development of industrialization and urbanization, the consumption and pollution of water resources are becoming more and more serious. Water quality monitoring is an extremely important technical means to protect water resources. However, the current popular water quality monitoring methods have their shortcomings, such as a low signal-to-noise ratio of satellites, poor time continuity of unmanned aerial vehicles, and frequent maintenance of in situ underwater probes. A non-contact near-surface system that can continuously monitor water quality fluctuation is urgently needed. This study proposes an automatic near-surface water quality monitoring system, which can complete the physical equipment construction, data collection, and processing of the application scenario, prove the feasibility of the self-developed equipment and methods and obtain high-performance retrieval results of four water quality parameters, namely chemical oxygen demand (COD), turbidity, ammoniacal nitrogen (NH3-N), and dissolved oxygen (DO). For each water quality parameter, fourteen machine learning algorithms were compared and evaluated with five assessment indexes. Because the ensemble learning models combine the prediction results of multiple basic learners, they have higher robustness in the prediction of water quality parameters. The optimal determination coefficients (R2) of COD, turbidity, NH3-N, and DO in the test dataset are 0.92, 0.98, 0.95, and 0.91, respectively. The results show the superiority of near-surface remote sensing, which has potential application value in inland, coastal, and various water bodies in the future.

A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years

“…Cherukuru et al [39] have successfully developed a new semianalytical remote sensing inversion model for retrieving suspended sediment and dissolved organic carbon in coastal waters. High-performance inversion results were achieved for four water quality parameters: chemical oxygen demand (COD), turbidity, ammonia nitrogen (NH 3 -N), and dissolved oxygen (DO), indicating the potential application value of near-surface remote sensing in inland, coastal, and various water bodies [68]. Yuan Fong Su et al [69] established univariate and multivariate water quality evaluation models for retrieving sea surface reflectance using SPOT remote sensing images, applying them to SPOT multispectral images to generate distribution maps for three water quality variables: Secchi disc depth, turbidity, and total suspended solids.…”

An Integrated Framework for Remote Sensing Assessment of the Trophic State of Large Lakes

“…The European Space Agency (ESA) offers free downloads of satellite images. Compared to other satellites such as MODIS, MERIS, and Landsat-8/OLI [30], S-2/MSI has a higher spatial resolution (10 m, 20 m, and 60 m), and its revisit period is 5 days. The feasibility of the TSI inversion algorithm varies considerably between different sensors because of their various band configurations [31].…”

A New Method for Spatial Estimation of Water Quality Using an Optimal Virtual Sensor Network and In Situ Observations: A Case Study of Chemical Oxygen Demand

“…In recent decades, remote sensing technology has provided a promising way for lake water quality continuous monitoring at local scales, which is an ideal method for monitoring aquatic environments because it allows interpretation of received radiance at multiple wavelengths, thereby enabling long-term monitoring of water quality parameters [ 11 , 20 , 21 ]. Numerous studies have focused on applying remote sensing techniques to obtain water quality parameters.…”