“…The increasing practice of Data Science in environmental applications—i.e., transforming data into understandable and actionable knowledge relevant for informed decision making (Gibert, Horsburgh, Athanasiadis, & Holmes, )—is also influencing hydrology, particularly with the application of machine learning and deep learning techniques to emerging large data sets generated by in situ sensors and by aerial and satellite remote sensing (Shen, ). Advancing and comparing these methods requires the availability of shared example, training, and benchmark datasets, a pattern that has been demonstrated across many domains where Data Science methods are employed (e.g., Deng et al, ; Wu et al, ).…”