Machine learning approaches for predicting the performance of stormwater biofilters in heavy metal removal and risk mitigation

The increasing amount of data on biofilter treatment performance over the past decade has made it possible to use data-driven approaches to explore the relationships between biofilter performance and a range of input variables. The knowledge gap lies in lack of models to predict the biofilter performance considering both design and operational variables, especially for heavy metals. In this study, we tested three machine learning (ML) approaches, namely multilinear regression (MLR), artificial neural network (NN), and random forest (RF), to predict biofilter outflow concentrations of heavy metals (Cd, Cr, Cu, Fe, Ni, Pb and Zn) using a range of design and operational factors as input variables. The results show that RF performed relatively better than other two models, with median Nash-Sutcliffe Efficiency (NSE) values of 0.995, 0.317, 0.762, 0.636, 0.726, 0.896 and 0.656 for Cd, Cr, Cu, Fe, Ni, Pb and Zn, respectively during model training. However, all the models were less accurate during model validation, with the better performance found for Cd (average NSE=0.964), Zn (0.530) and Ni (0.393) and poorer performance observed for Cu (0.219), Pb (0.058), Fe (-0.054) and Cr (-0.062). Infiltration rate (IR) and inflow concentration (C-in) were sensitive to all pollutants' removal in biofilters. The ratio of system size to catchment size was also found to be important for Zn, Ni and Cd, while ponding depth was an important variable for Cd. Based on thousands of hypothetical design and operational scenarios (generated using raw data), the best ML models were used to predict the biofilter outflow concentrations and estimate the risk quotient (RQ) values with regards to reuse of treated stormwater for various purposes. Results suggest that biofilters were able to reduce health risks associated with heavy metals in stormwater and therefore produce reliable water fit for reuses such as irrigation, swimming, and toilet flushing. Modelling results showed that biofiltration did not meet the requirements for drinking when Cd contamination exists. Explorative analysis also demonstrated how the key operational and design variables can be optimised to further reduce the health risks that can be fit for drinking purposes (i.e., RQ value <1). (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

The study used machine learning methods to predict the performance of biofilters, with random forest model performing relatively better during training but less accurate during validation. The design and operational factors of biofilters play an important role in the removal of heavy metals.