Machine learning–enabled wastewater treatment plants: applications, system integration, and sustainability pathways aligned with the SDGs

The increasing complexity of wastewater characteristics, stricter discharge regulations, and rising energy and operational costs pose significant challenges to conventional wastewater treatment plant (WWTP) operation. Machine learning (ML) has emerged as a powerful enabler of predictive, adaptive, and data-driven wastewater management by leveraging the growing availability of online sensors and operational data. This review critically synthesizes recent advances in ML applications across WWTPs, with emphasis on predictive modeling, process control and optimization, soft sensing, fault detection and diagnostics, membrane fouling management, and digital twin development. Beyond classifying algorithms, this study provides a structured taxonomy linking ML techniques to specific treatment functions, operational metrics, and sustainability outcomes. Quantitative evidence from full-scale and pilot-scale studies is discussed, demonstrating improvements such as reductions in aeration energy demand, enhanced effluent quality stability, optimized chemical consumption, and improved system resilience. Emerging trends including hybrid physics–data models, explainable artificial intelligence, reinforcement learning–based control, and carbon-aware operation are highlighted alongside persistent challenges in decentralized or resource-limited contexts. By mapping ML-enabled interventions to operational indicators aligned with the United Nations Sustainable Development Goals (SDGs), particularly SDG 6 (Clean Water and Sanitation), SDG 9 (Industry, Innovation and Infrastructure), and SDG 12 (Responsible Consumption and Production), this review positions ML not only as a performance-enhancing tool but as a strategic component of sustainable wastewater infrastructure.