A Comparative Study on Water Quality Prediction Using Machine Learning and Deep Learning Techniques

Water quality monitoring and prediction plays an energetic role in the preservation of water resources, decision-making, and environmental management. The freshwater resources have been severely impacted by water contamination due to rising industrialization and rapid economic growth. The Water Quality Index (WQI) is a rapid approach which is utilized to determine the water quality status of ground and surface water systems from physicochemical and bacteriological information. In recent years, various researchers have discovered achievable ways for accurate prediction by using the latest machine learning and deep learning techniques. This survey represents various methodologies like Random Forest (RF), Principal Component Analysis (PCA), Naïve Bayes, Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long-Short Term Memory (LSTM), and so on are used for water quality prediction analysis. The RNN and LSTM give more accurate results compared to other techniques. This survey, concludes that the prediction of water quality is a difficult task and various factors are involved in the prediction.