A novel methodology based on LCA plus DEA to detect eco-efficiency shifts in wastewater treatment plants

The high-frequency on-line measurements coming from sensors installed in wastewater treatment plants (WWTPs) can be used for alert systems and decision support tools. Given the complexity of WWTPs, many authors developed efficient techniques for plant assessment. By contrast, few contributions are focussed on the identification of regime shifts in WWTPs on short-term, even if the early detection of occurring inefficiencies is a relevant information for plant managers. In order to fill this gap, the present paper uses a daily LCA + DEA analysis in order to monitor the potential deterioration of the eco-efficiency. This approach consists of an original combination of environmental life cycle assessment (LCA), data envelopment analysis (DEA), time series analysis and statistical tests. The main innovation in DEA algorithm consists of the set of decision-making units (DMUs), here composed of the 1-day operation datasets of a single WWTP. The results show a good performance in the regime shifts classification, for which the receiving operating characteristic (ROC) analysis returned a score of 0.8 (in a range 0-1).