Prediction of Key Variables in Wastewater Treatment Plants Using Machine Learning Models

Prediction of key variables is an important part of the monitoring, control, and optimization of industrial processes, since it is important to anticipate certain behaviors so that the correct actions can be taken. To assess which algorithm is best suited to the prediction of a number of key variables at various stages of wastewater treatment plants (WWTP), five computational algorithms were researched: Artificial Neural Network, Long Short-Term Memory, deep learning Transformer model, Adaptive Neuro-Fuzzy Inference System, and Gaussian Mixture Model. With these models, techniques already well established in the state-of-the-art are evaluated, as well as more recent methods that have been exhibiting good performance in variable prediction regression problems. These algorithms were evaluated in four WWTP case studies, in which the objective is to predict the following key variables: total suspended solids, nitrate and nitrite, ammonia and ammonium, and biochemical oxygen demand. The learning process of each algorithm was performed using extensive tests in order to select the input variables, and define the topologies and hyper-parameters of the presented models by cross-validation. The results indicate that it is possible to adequately predict the four variables, and the best results were achieved by the Transformer algorithm, which presents the lower error values in the considered metrics.