Membrane fouling prediction and uncertainty analysis using machine learning: A wastewater treatment plant case study

Membrane bioreactors (MBRs) have proven to be an extremely effective wastewater treatment process combining ultrafiltration with biological processes to produce high-quality effluent. However, one of the major drawbacks to this technology is membrane fouling. Currently, mechanistic models are often used to estimate membrane fouling through transmembrane pressure (TMP), but their performance is not always satisfactory. In this study, data-driven machine learning techniques consisting of random forest (RF), artificial neural network (ANN), and long-short term memory network (LSTM) are used to build models to predict transmembrane pressure (TMP) at various stages of the MBR production cycle. The models are built with 4 years of high -resolution data from a confidential full-scale municipal WWTP. The model performances are examined using statistical measures such as coefficient of determination (R2), root mean squared error, mean absolute percentage error, and mean squared error. The results show that all models provide reliable predictions while the RF models have the best accuracy. Model uncertainty is quantified to determine the impact of hyperparameter tuning and the variance of extreme predictions. The proposed models can be useful tools in providing decision support to WWTP operators employing fouling mitigating strategies, leading to reduced capital and operational costs.

Automated summary

In this study, machine learning techniques were used to build models that can predict transmembrane pressure (TMP) at different stages of the membrane bioreactors (MBRs) production cycle. The models provide reliable predictions, with the random forest (RF) model showing the highest accuracy. These models can be valuable tools for decision support in wastewater treatment plants, leading to cost reduction.