Prediction of Wastewater Treatment Plant Effluent Water Quality Using Recurrent Neural Network (RNN) Models

Abstract

Artificial Intelligence (AI) has recently emerged as a powerful tool with versatile applications spanning various domains. AI replicates human intelligence processes through machinery and computer systems, finding utility in expert systems, image and speech recognition, machine vision, and natural language processing (NLP). One notable area with limited exploration pertains to using deep learning models, specifically Recurrent Neural Networks (RNNs), for predicting water quality in wastewater treatment plants (WWTPs). RNNs are purpose-built for handling sequential data, featuring a feedback mechanism. However, standard RNNs may exhibit limitations in accommodating both short-term and long-term dependencies when addressing intricate time series problems. The solution to this challenge lies in adopting Long Short-Term Memory (LSTM) cells, known for their inherent memory management through a ‘forget gate’ mechanism. In general, LSTM architecture demonstrates superior performance. WWTP data represent a historical series influenced by fluctuating environmental conditions. This study employs simple RNNs and LSTM architecture to construct prediction models for effluent parameters, systematically assessing their performance through various training data scenarios and model architectures. The primary objective was to determine the most suitable WWTP dataset model. The study revealed that an epoch setting of 50 and a batch size of 100 yielded the lowest training time and root mean square error (RMSE) values for both RNN and LSTM models. Furthermore, when these models are applied to predict effluent parameters, they exhibit precise RMSE values for all parameters. The study results can be applied to detect potential upsets in WWTP operations.

En-WBF: A Novel Ensemble Learning Approach to Wastewater Quality Prediction Based on Weighted BoostForest

“…For instance, Foschi et al [25] employed shallow artificial neural networks (ANNs) to predict the quality of sewage, and they reported that, although the shallow fully connected layer was unstable at mimicking the time dependency in the time series, the shallow ANN was superior at capturing the nonlinear correlations among the wastewater quality series. Based on time series analysis, Wongburi et al [26] employed long short-term memory networks (LSTMs) to predict forecast sewage quality to resolve nonlinear and long-term dependent intricacies within the wastewater quality. Yang et al [17] developed a principal component analysis-dynamic nonlinear autoregressive with exogenous inputs (PCA-NARX) model to forecast effluent quality.…”

An Empirical Modal Decomposition-Improved Whale Optimization Algorithm-Long Short-Term Memory Hybrid Model for Monitoring and Predicting Water Quality Parameters

“…Water quality parameter data exhibit nonlinearity and temporality. With the development of deep learning, Recurrent Neural Network (RNN) is more suitable for processing nonlinear time series compared to ANN [22]. Kumar et al [23] conducted a model prediction study on monthly river flow data using a RNN network and proved that RNN has high accuracy in predicting time series data.…”

Computing River Discharge Using Water Surface Elevation Based on Deep Learning Networks

“…Some deep learning networks are born to handle data with time steps, RNN (recurrent neural network) for instance, their hidden states can be passed along time steps, and RNNs (RNN and its variants) are successfully employed to various kinds of hydrology tasks [18][19][20][21][22][23][24][25]. In particular, to deal with short-term runoff prediction problems, a deep learning multi-dimensional ensemble method has proven to be effective [26,27].…”