Evaluation of artificial intelligence algorithms to estimate water quality parameters using satellite images

Abstract

The Ciénaga de la Virgen (Virgen Swamp) is a coastal lagoon in Cartagena de Indias that provides multiple ecosystem services in northern Bolívar. This ecosystem has faced anthropogenic pressure from city growth and improper water resource management, including wastewater and agrochemical discharges. Consequently, environmental authorities must monitor certain sites within the water body and extrapolate the data across its entire expanse. In this study, predictive tools are applied to determine water quality parameters such as chlorophyll-a (CL-a), dissolved oxygen (DO), total suspended solids (TSS), and salinity. This is achieved by correlating traditionally obtained data with the spectral response of medium-resolution satellite images, adjusted using artificial intelligence (AI) algorithms. Support vector machine (SVM) algorithms were used for regression, random forests (RF), and artificial neural networks (ANN), achieving an accuracy of 79% for CL-a, 95% for DO, 89% for TSS, and 96% for salinity. Validation was performed using mean absolute percentage error (MAPE) statistical metrics and root mean square error (RMSE).