Machine learning methods have shown tremendous potential in both process-understanding and prediction – two of the main focus areas in hydrology. New datasets with high spatial and temporal resolutions are emerging at an unprecedented rate, which has opened up various new avenues of research in the field. Machine learning algorithms are well suited to leverage these new datasets and solve hydrologic problems across a range of spatial and temporal scales. We hereby invite studies that use machine learning to solve problems of catchment hydrology, considering either the quantity or quality or both aspects of water. The studies with generalizable results are strongly encouraged.