Prediction of Biochemical Oxygen Demand and Chemical Oxygen Demand Using Artificial Neural Network and Long Short-Term Memory

Abstract

River water quality is a significant factor in environmental sustainability and public health. The identification and monitoring of major pollutant indices such as chemical oxygen demand (COD) and biochemical oxygen demand (BOD) are critical in monitoring river water quality. Several studies have employed artificial neural networks (ANN) and long-short-term memory (LSTM) to predict river water quality based on pollutant data such as COD and BOD; however, their performance has to be evaluated further. The purpose of this study is to assess how well ANN and LSTM predict these parameters in river water. In this study, two machine learning models, ANN and LSTM, are implemented in Python. The BOD and COD parameters are trained using both models, and to see if the ANN and LSTM models perform well on this data, the first step is to examine the loss model on the ANN and LSTM. The discussion results reveal that both models capture river water quality trends and are consistent when compared to real and forecasted data. Model performance evaluation using mean squared error (MSE) and root mean squared error (RMSE) shows that LSTM outperforms ANN in predicting BOD and COD parameters as river water quality indicators