Predicting Regional Wastewater Treatment Plant Discharges Using Machine Learning and Population Migration Big Data

• DOI: 10.1021/acsestwater.2c00639
• Publication Date: 2023-03-06T15:07:45Z
• Authors: Jiang Yu; Yong Tian; Hao Jing; Taotao Sun; Xiaoli Wang; Charles B. Andrews; Chunmiao Zheng
• Keywords: Predictive modelling

Quantifying the temporal variation of wastewater treatment plant (WWTP) discharges is essential for water pollution control and environment protection in metropolitan areas. This study develops an ensemble machine learning (ML) model to predict from WWTPs quantify contribution extraneous (mixed precipitation infiltrated groundwater) by leveraging power ML population migration big data. The approach applied at 265 Guangdong–Hong Kong–Macao Greater Bay Area (GBA) China. major conclusions are as follows. First, provides efficient reliable way WWTP using data easily accessible public. predicted treated sewage amount increased 20.4 × 106 m3/day 2015 24.5 2020. Second, predictors, including daily precipitation, average past proceeding days, temperature, migration, play different roles predicting city's discharges. Finally, mixed groundwater account for, on average, 1.6 10.3% total GBA. represents first attempt bring into data-driven environmental engineering modeling can be extended other variables concern.