Topic: Environmental Exposure Assessment in Aquatic Environments: Data-Driven Modelling, Machine Learning, and Explainability Techniques

Aquatic environments are increasingly exposed to a wide range of chemical, biological, and emerging contaminants originating from industrial activities, agriculture, urbanisation, and climate change. Accurate assessment and prediction of environmental exposure are essential for understanding contaminant behaviour, identifying ecological risks, and supporting effective water resource management. However, the complexity of aquatic systems, interactions among multiple environmental factors, and limitations of conventional monitoring approaches present significant challenges for reliable exposure assessment. Recent advances in data-driven modelling, artificial intelligence, and machine learning offer promising opportunities to improve the prediction, interpretation, and spatial-temporal characterisation of environmental contaminants. Furthermore, explainable artificial intelligence (XAI) techniques can enhance model transparency, identify key environmental drivers, and strengthen confidence in data-driven predictions.

This Special Issue aims to bring together innovative research addressing the application of advanced computational approaches to environmental exposure assessment in aquatic environments. Contributions focusing on machine learning, predictive modelling, uncertainty analysis, explainability techniques, contaminant transport, risk assessment, and integrated monitoring frameworks are particularly welcome. The overarching goal is to promote interdisciplinary research and support the development of robust, interpretable, and scientifically informed tools for sustainable aquatic ecosystem management and environmental protection.