Mapping of total suspended solids using Landsat imagery and machine learning

Abstract The main objective of this work is to propose a new technique for water quality parameters monitoring by applying artificial intelligence methods optimize remote sensing data processing. A multiple regression model was developed create total suspended solids (TSS) prediction model, using unsupervised machine learning. Currently, bodies throughout the world are poorly supervised in terms quality, so it necessary implement efficient mechanisms obtain synoptic information good diagnosis TSS evolution, because they key indicator biophysical state lakes and an essential marker continuous monitoring. Conventional used monitor physical bodies, example, situ sampling, have proven impractical due time, cost space constraints, tools can help achieve purpose more efficiently. proposed requires calibration that end, Lake Chapala from time series collected National Water Commission (CONAGUA) were used. largest freshwater body Mexico, human intervention develops around lake has caused drastic changes such as decrease size increase matter aquatic vegetation. These alter balance system, endangering health lake. This presents generalized semi-empirical uses Landsat image learning estimating with precision ( R = 0.81, RMSE 32.52).