Louise J. Slater , Georgios Blougouras, Liangkun Deng, Qimin Deng, Emma Ford, Anne Hoek van Dijke, Feini Huang, Shijie Jiang, Yinxue Liu, Simon Moulds , Andrew Schepen, Jiabo Yin, Boen Zhang

Machine learning (ML) is a powerful tool for hydrological modelling, forecasting, generation of new datasets, and process discovery. It is widely recognised for its ability to produce skillful predictions and generate insights about physical mechanisms through explainable AI (XAI). This manuscript outlines current progress in the use of ML in hydrology, new tools in XAI, and challenges in these areas. Continued areas of research for ML in hydrology include model interpretability, prediction in data-sparse regions, overcoming hydrology's `cascade of uncertainty', multivariate prediction, and causality.