Abstract

Clean water is a scarce resource, fundamental for human development and well-being. Remote sensing techniques are used to monitor and retrieve quality estimators from water bodies. In situ sampling is an essential and labour-intensive task with high costs. As an alternative, a large water quality dataset from a potabilization plant can be beneficial to this step. Combining laboratory measurements, given by a water treatment plant in North-East Argentina, and spectral data from Sentinel-2 satellite platform, several algorithms were proposed, trained, and compared for turbidity estimation at the plant inlet water, in a local river. The highest performance metrics were from a random forest model with a coefficient of determination close to unit (0.913) and the lowest root-mean squared error (143.9 nephelometric turbidity units). The most influential spectral bands were identified by global feature importance and partial dependencies profiles techniques. Maps and histograms were made to explore the turbidity spatial distribution.