Prediction of chlorophyll-a and suspended solids through remote sensing and artificial neural networks

Abstract

Total suspended solids (TSS) and chlorophyll-a concentration are two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, the technique proposed in this paper takes another approach. TSS and chlorophyll-a are optically active components therefore enable measures through remote sensing. Using data from both Sentinel-2 spectral images and laboratory analysis, an artificial neural network was trained to predict the concentration of TSS and chlorophyll-a. The predictions were evaluated using the R2 coefficient, where TSS and chlorophyll-a achieved values of 0.7 and 0.72, respectively.