.png){kind=icon}
.png){kind=icon}
Return
From data to sustainable clean water: AI/ML contributions to the UN Sustainable Development goals
.png){kind=icon}
PRE
AI
B
S
M
L
K
DOI：10.1016/j.pce.2026.104427.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The growing global water crisis, driven by population growth, industrialization, and climate change, has intensified the need for efficient and sustainable water treatment solutions. Conventional water treatment plants (WTPs) often face challenges such as fluctuating influent quality, high energy consumption, and limited process adaptability. This study aims to provide a comprehensive review of artificial intelligence (AI) and machine learning (ML) applications in water treatment systems, with a particular focus on their role in improving operational efficiency and supporting Sustainable Development Goals (SDGs). The review systematically analyzes AI/ML applications across key domains, including water quality prediction, process optimization, membrane fouling control, anomaly detection, predictive maintenance, energy efficiency, and automated control systems. Reported models are compared in terms of performance, applicability, and limitations. The findings indicate that AI/ML approaches significantly enhance prediction accuracy, reduce chemical and energy consumption, and enable real-time decision-making. However, challenges such as data scarcity, model interpretability, and integration with existing infrastructure remain. Future research directions include explainable AI, digital twins, and adaptive learning systems to ensure scalable and sustainable implementation.
Keywords:
Machine learning
Optimization
Prediction
Sustainable development
Water treatment
Journal
IF:
4.1
Papers:
3.3K
Citations:
6.9K
Organization
Cited Papers