Water quality hotspot identification using a remote sensing and machine learning approach: A case study of the River Ganga near Varanasi

Abstract

Turbidity (Turb) and Chlorophyll-a (Chl-a) are crucial indicators of water quality because they can reveal the presence of suspended particles and algae, respectively. Understanding the health of rivers and spotting long-term water quality changes can both benefit from monitoring these measures. Traditional methods of monitoring these parameters, like in-situ measurements, is time-consuming, expensive, and inconvenient in some places. Sentinel-2, a multispectral satellite, might offer a more workable and economical option for monitoring water quality, though. This study used 100 in-situ data collected from the Ganga River near Varanasi in the pre-monsoon season (pre-MS) and post-monsoon season (post-MS) in order to create a model for the prediction of optically active water quality parameters by combining Multispectral Instrument (MSI) data and machine learning method (Random Forest). To create spatial distribution maps for Chl-a and Turb, 14 spectral indices and band ratios were employed as independent variables. The results showed that the prediction accuracy for Turb (R2 = 0.91, MAE = 1.13 and MAPE = 7.76% during pre-MS and R2 = 0.93, MAE = 0.88 and MAPE = 2.29% during post-MS) and for Chl-a (R2 = 0.97, MAE = 0.59, and MAPE = 2.07% during pre-MS and R2 = 0.95, MAE = 0.61, and MAPE = 2.71% during post-MS). The Ganga near Varanasi abruptly turned green due to an increase in algal bloom in May and June 2021. This study not only revealed the reasons behind the green appearance but also identified potential areas of concern or hotspots. In order to identify hotspot locations, drainage networks, point source discharge locations and LU-LC were used.