What Role Does Hydrological Science Play in the Age of Machine Learning?

This paper is derived from a keynote talk given at the Google's 2020 Flood Forecasting Meets Machine Learning Workshop. Recent experiments applying deep learning to rainfall-runoff simulation indicate that there significantly more information in large-scale hydrological data sets than hydrologists have been able translate into theory or models. While growing interest machine sciences community, many ways, our community still holds deeply subjective and nonevidence-based preferences for models based on certain type of “process understanding” has historically not translated accurate theory, models, predictions. commentary call action hydrology focus developing quantitative understanding where when process valuable modeling discipline increasingly dominated by learning. We offer some potential perspectives preliminary examples about how this might be accomplished.