Uso de algoritmos de aprendizado de máquina para previsão e classificação do índice da qualidade da água: um caso de estudo no rio Paraibuna, Juiz de Fora, Brasil

Abstract

This study investigates the use of machine learning algorithms for the prediction and classification of the water quality index (WQI) in the Paraibuna River, in Juiz de Fora, Brazil. The problem lies in the need for faster and more accurate methods to monitor water quality in real time, overcoming limitations of traditional methods that require time and resources. It is justified by the importance of providing reliable and up-to-date data for environmental management and the protection of public health, offering an efficient alternative for decision-making and environmental preservation policies. The overall objective is to develop and apply a machine learning model that predicts and classifies the WQI, using historical and real-time data, while the specific objectives include evaluating the quality of the data, selecting appropriate algorithms, validating the model, and enabling its replication in other rivers in the region. The hypotheses raised suggest that machine learning algorithms will be effective in predicting WQI accurately, offering a more agile response than conventional methods and allowing for more effective environmental interventions.