To provide real-time prediction of wastewater treatment plant (WWTP) effluent water quality, a machine learning (ML) model was developed by combining an improved feedforward neural network (IFFNN) with an optimization algorithm. Data used as input variables of the IFFNN included hourly influent water quality parameters, influent flow rate and WWTP process monitoring and operational parameters. Additionally, input variables included historical effluent water quality parameters for future prediction. The model was demonstrated in a WWTP in Jiangsu Province, China, where prediction of effluent chemical oxygen demand (COD) and total nitrogen (TN) with large variations were tested. Relative to the traditional feedforward neural network (FFNN) model without considering historical effluent water quality parameter input, the IFFNN enhanced prediction performance by 52.3% (COD) and 72.6% (TN) based on the mean absolute percentage errors of test datasets, after its model structure was optimized with a genetic algorithm (GA). The problem of over-fitting could also be overcome through the use of the IFFNN, with the determination of coefficient increased from 0.20 to 0.76 for test datasets of effluent COD. The GA-IFFNN model, which was efficient in capturing complex non-linear relationships and extrapolation, could be a useful tool for real-time direction of regulatory changes in WWTP operations.

Microbial contamination in urban stormwater is one of the most widespread and challenging water quality issues in developed countries. Low impact development (LID) best management practices (BMPs) restore pre-urban hydrology by treating and/or harvesting urban runoff and stormwater, and can be designed to remove many contaminants including pathogens. One particular type of LID BMP, stormwater biofilters (i.e., vegetated media filters, also known as bioinfiltration, bioretention, or rain gardens), is becoming increasingly popular in urban environments due to its multiple co-benefits (e.g., improved hydrology, water quality, local climate and aesthetics). However, increased understanding of the factors influencing microbial removal in biofilters is needed to effectively design and implement biofilters for microbial water quality improvement. This paper aims to provide a holistic view of microbial removal in biofilter systems, and reviews the effects of various design choices such as filter media, vegetation, infauna, submerged zones, and hydraulic retention time on microbial removal. Limitations in current knowledge and recommendations for future research are also discussed.