Water Quality Classification and Machine Learning Model for Predicting Water Quality Status—A Study on Loa River Located in an Extremely Arid Environment: Atacama Desert

Water is the most important resource for human, animal, and vegetal life. Recently, use of artificial intelligence techniques, such as Random Forest, has been combined with other models logical–mathematical reasoning, to generate predictive water quality models. In this study, a rule-based inference technique labels described, using historical physicochemical parameter data on seven monitoring stations in Loa River, collected by Chilean Ministry Environment. Next, model status was created, parameters, expert knowledge. The validation Forest results described three indicators from machine learning model: accuracy (acc), precision (p), recall (r). This paper describes dataset preparation, refinement threshold values used parameters significant class, labeling quality. obtained yielded following mean values: acc = 0.897, p 89.73, r 0.928. ML reported here novel since no previous studies kind predict located an extremely arid zone. study also helps create specific knowledge freshwater