Comprehensive assessment, intelligent prediction, and precise mitigation strategies for greenhouse gas emissions in full-scale wastewater treatment plants

Wastewater treatment plants (WWTPs) are major contributors to global anthropogenic greenhouse gas (GHG) emissions, with China ranks among the leading emitters. In the context of China's "dual-carbon" journey, precision quantification and predictive forecasting of GHG fluxes, particularly methane (CH4) and nitrous oxide (N2O)-are crucial for developing advanced mitigation strategies of WWTPs. To accurately assess GHG emissions, this study firstly introduced customized emission factors (EFs) to precisely evaluate the GHG emissions of a full- scale A2O- based WWTP in Beijing. This approach addressed the overestimation of emissions when using the IPCC's standard EFs. Additionally, the study proposed machine learning (ML) techniques to predict GHG fluxes based on routine wastewater quality parameters. Specifically, Long Short-Term Memory (LSTM) and Random Forest (RF) models showed the strong performance in predicting CH4 and N2O emissions, respectively. Moreover, our findings revealed distinct spatiotemporal patterns of GHG emission: CH4 emissions peak during the summer solstice, while N2O emissions rise during the winter months. For the first time, this study identified the nitrification biofilter in the advanced treatment unit as a significant direct source of N2O emissions. Even- though, indirect CO2 emissions account for a dominant 57%-90% of the total GHG emissions. Scenario analyses revealed a strategic mitigation approach. Energy conservation emerged as the most effective measure, capable of reducing emissions by 23.41%, followed by heat recovery, which could cut emissions by 10.15%. In practical applications, improving energy efficiency is of utmost importance in real- world mitigation strategies. This highlights the significance of integrated approaches for achieving the sustainable development of WWTPs in the "dual- carbon" background.