Monitoreo de calidad de agua y predicción de coliformes fecales en playas de Montevideo mediante algoritmos de aprendizaje automático

We constructed artificial intelligence (AI) models to predict faecal water quality (CF) aid management in recreational beaches. Historical data base generated by the Laboratorio de Calidad Ambiental la Intendencia Montevideo (IM) was analized and AI wwere CF excess (CF >2.000). Ten years of monitoring 21 beaches (N=19359, november 2009 september 2019) presented a wide range salinity turbidity variability among showed an asymetric distribution (min=4, median=250, average=1.047 máx=1.280.000) with values exceeding threshold all In situ registered, meteorological oceanographic variables were used train models. A stratified random forest best performance evaluated metrics overall accuracy 86% 60% improvement true positive rates respect baseline. High govermental institution together modeling strategies provided relevant framework beach public health management.