Comprehensive Review on Application of Machine Learning Algorithms for Water Quality Parameter Estimation Using Remote Sensing Data

Abstract

Water is an integral aspect of the world necessary for living creatures to thrive. Owing to unplanned urbanization, rapid industrialization, and uncontrollable human intervention, water quality is gradually degrading. This affects not only marine animals but also humans. Thus, the quality of water should be examined regularly. Water quality parameters should be estimated to monitor water quality. In general, water quality parameters are measured by in situ measurements. Although these measurements are accurate, they are costly and do not provide real-time spatial and temporal changes in water quality. To overcome this limitation, water quality parameters can be estimated using machine learning (ML) along with remote sensing (RS) data. A combination of ML and RS data is a powerful approach for the routine assessment of spatial and temporal variations in water quality parameters. In this paper, some articles based on this approach are reviewed. By analyzing the literature, it was found that the integrated use of RS-based geospatial data with ML helps to produce an accurate result. Most of the authors used the regression algorithm in the estimation of the water quality parameters, with a support vector machine (SVM) regression intensively used. The artificial neural network (ANN) algorithm was the most used algorithm of ML in many of the studies. The researchers used multispectral images for their study. By applying ML to RS data, water quality monitoring systems are evolving into real-time artificial intelligence (AI)-enabled models that provide valuable recommendations and insights to support farmers to make decisions and take action in aquaculture.

Water quality monitoring and assessment based on cruise monitoring, remote sensing, and deep learning: A case study of Qingcaosha Reservoir

“…Support vector regression (SVR) is a traditional supervised machine learning that is applied widely in RST inversion Wagle et al (2020). The SVR model was also conducted by calling the function in the Python package scikit-learn.…”

Advances in machine learning and IoT for water quality monitoring: A comprehensive review

“…It also discusses prospects in water research. Wagle et al [ 20 ] examined the application of ML and remote sensing data for estimating WQ parameters. The integration of regression algorithms and ANN is explored, and the potential of real-time AI-enabled WQM systems is discussed.…”

Utilizing residual networks for remote sensing estimation of total nitrogen concentration in Shandong offshore areas

“…Water quality remote sensing monitoring is a technology that uses spaceborne sensors to obtain image data, constructs a water quality parameter inversion model based on image reflectance, and calculates water environment factors (Wagle et al, 2020). It explores the internal relationship between spectral reflectance and water composition (Harvey et al, 2015).…”