Explainable AI in Sustainable Water Quality Monitoring System: A Systematic Review

Water quality plays a crucial role in safeguarding ecosystems and supporting human health. Traditional monitoring methods depend heavily on manual sampling and laboratory testing, which are time-consuming and lack scalability. Recent advancements in Artificial Intelligence (AI) and the Internet of Things (IoT) have transformed water quality monitoring by enabling automated, real-time, and predictive analysis. However, most AI models operate as black-box systems, limiting interpretability in environmental decision-making. This paper presents a systematic review of Explainable Artificial Intelligence (XAI) approaches applied to sustainable, AIoT-based water quality monitoring systems. The review critically analyzes sensing technologies, AI algorithms, explainability frameworks, and sustainability strategies adopted in recent research from 2020-2025. A comparison of methodologies highlights key progress in transparency, efficiency, and energy-aware design. The study identifies major gaps in interpretability evaluation, sensor reliability, and lightweight AI models for edge deployment. A conceptual framework is proposed integrating XAI with energy-efficient IoT architecture for real-time, transparent, and sustainable environmental monitoring.