Search

Water pollution generated from intensive anthropogenic activities has emerged as a critical issue concerning ecosystem balance and livelihoods worldwide. Although optimizing wastewater treatment efficiency is widely regarded as the foremost step to minimize pollutants released into the environment, this widespread application has encountered two major problems: firstly, the significant variation of influent wastewater constituents; secondly, complex treatment processes within wastewater treatment plants (WWTPs). Based on the data collected hourly using real-time sensors in three different full-scale WWTPs (24 h × 365 days × 3 WWTPs × 10 wastewater parameters), this work introduced the potential application of Machine Learning (ML) to predict wastewater quality. In this work, six different ML algorithms were examined and compared, varying from shallow to deep learning architectures including Seasonal Autoregressive Integrated Moving Average (SARIMAX), Random Forest (RF), Support Vector Machine (SVM), Gradient Tree Boosting (GTB), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Long Short-Term Memory (LSTM). These models were developed to detect total phosphorus in the outlet (Outlet-TP), which served as an output variable due to the rising concerns about the eutrophication problem. Irrespective of WWTPs, SARIMAX consistently demonstrated the best performance for regression estimation as evidenced by the lowest values of Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the highest coefficient of determination (R

In biological wastewater treatment systems, extracellular polymeric substances (EPS) are continuously excreted as a response to environmental changes and substrate conditions. It could severely affect the treatment efficacy such as membrane fouling, dewaterability and the formation of carcinogenic disinfection by-products (DBPs). The heterogeneous dissolved organic matter (DOM) with varying size and chemical nature constitute a primary proportion of EPS. In the last few decades, fluorescence spectroscopy has received increasing attention for characterizing these organic substances due to the attractive features of this low-cost spectroscopic approach, including easy sample handling, rapid, non-destructive and highly sensitive nature. In this review, we summarize the application of fluorescence spectroscopy for characterizing EPS and provide the potential implications for online monitoring of water quality along with its limitations. We also link the dynamics of fluorescent dissolved organic matter (FDOM) in EPS with operational and environmental changes in wastewater treatment systems as well as their associations with metal binding, membrane fouling, adsorption, toxicity, and dewaterability. The multiple modes of exploration of fluorescence spectra, such as synchronous spectra with or without coupling with two-dimensional correlation spectroscopy (2D-COS), excitation-emission matrix (EEM) deconvoluted fluorescence regional integration (FRI), and parallel factor analysis (PARAFAC) are also discussed. The potential fluorescence indicators to depict the composition and bulk characteristics of EPS are also of interest. Further studies are highly recommended to expand the application of fluorescence spectroscopy paired with appropriate supplementary techniques to fully unravel the underlying mechanisms associated with EPS.