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.
Sludge Volume Index (SVI) is one of the most important operational parameters in an activated sludge process. It is difficult to predict SVI because of the nonlinearity of data and variability operation conditions. With complex time-series data from Wastewater Treatment Plants (WWTPs), the Recurrent Neural Network (RNN) with an Explainable Artificial Intelligence was applied to predict SVI and interpret the prediction result. RNN architecture has been proven to efficiently handle time-series and non-uniformity data. Moreover, due to the complexity of the model, the newly Explainable Artificial Intelligence concept was used to interpret the result. Data were collected from the Nine Springs Wastewater Treatment Plant, Madison, Wisconsin, and the data were analyzed and cleaned using Python program and data analytics approaches. An RNN model predicted SVI accurately after training with historical big data collected at the Nine Spring WWTP. The Explainable Artificial Intelligence (AI) analysis was able to determine which input parameters affected higher SVI most. The prediction of SVI will benefit WWTPs to establish corrective measures to maintaining stable SVI. The SVI prediction model and Explainable Artificial Intelligence method will help the wastewater treatment sector to improve operational performance, system management, and process reliability.
Wastewater treatment plants (WWTPs) use considerable workforces and resources to meet the regulatory limits without mistakes. The advancement of information technology allowed for collecting large amounts of data from various sources using sophisticated sensors. Due to the lack of specialized tools and knowledge, operators and engineers cannot effectively extract meaningful and valuable information from large datasets. Unfortunately, the data are often stored digitally and then underutilized. Various data analytics techniques have been developed in the past few years. The methods are efficient for analyzing vast datasets. However, there is no wholly developed study in applying these techniques to assist wastewater treatment operation. Data analytics processes can immensely transform a large dataset into informative knowledge, such as hidden information, operational problems, or even a predictive model. The use of big data analytics will allow operators to have a much clear understanding of the operational status while saving the operation and maintenance costs and reducing the human resources required. Ultimately, the method can be applied to enhance the operational performance of the wastewater treatment infrastructure.
24 December 2025 in Chemical Engineering Journal Advances
Wastewater consists of valuable resources that could be recovered or reused. Still it is under threat because of ineffective wastewater management and systems. In Thailand, less than 25% of wastewater generated may be treated while then rest is inadequately treated and sent back directly into waterbodies or the environment. Furthermore, the technologies that have been applied may be inefficient and unsustainable. Efficiency, sustainability, and simplicity are important concepts when designing an appropriate wastewater treatment system in developing countries. The objectives of this study were to review and evaluate wastewater treatment technologies and propose a method to improve or select an appropriate technology. An expert system in Excel® program was developed to determine the best solution. Sensitivity analysis was applied to compare and assess uncertainty factors. Due to the different conditions of each area, the key factor of interest was varied. Furthermore, Robust Decision Making tool was applied to determine the best way to improve existing wastewater treatment facility and to choose the most appropriate wastewater treatment technology.