Fall Meeting 2022

December 12 - 16, 2022

Data scarcity has historically challenged the parameterization and validation of physically-based earth system models. However, a rapid influx of data in recent years because of the emergence of relatively inexpensive, non-invasive, remotely sensed, and readily available data collection systems have resolved many issues surrounding data scarcity. Rapid increases in computing power coupled with a wealth of new data have created exciting new opportunities to model and understand hydrologic systems. Physically-based process models are being run at increasingly high spatial and temporal resolutions. The emergence of hydroinformatics, including machine learning and deep learning techniques, could revolutionize the face of hydrology and water quality modeling. However, managing and interpreting voluminous simulation outputs can be challenging. The hydrologic sciences community continues to develop advanced informatics practices and technologies that have addressed some known concerns, including data sharing, making data for modeling open and accessible, quantifying uncertainty, and rigorous parameterization to provide more accountability for the simulated outputs. This session invites abstracts from researchers who have experienced and/or are experiencing the benefits of developing and using new and novel hydroinformatics, including deep learning, to advance hydrologic and water quality modeling across spatial-temporal scales. It is hoped that the session will serve as a bridge to bring like-minded global researchers together, where they can find cohorts or camaraderie, learn, and share their findings to have a more integrated, connected, open, and networked science.