Data Science Webinar Series

We are pleased to announce the US CLIVAR Data Science Webinar Series. Organized by the Data Science Working Group, the webinar series will feature experts in Earth science, statistics, and computer science with the specific goal of fostering collaboration across these disciplinary boundaries. Our general mission is to accelerate the understanding, adoption, and further development of modern data science tools (artificial intelligence, machine learning, and statistics) for the analysis of large-to-massive climate data sets. The webinars will occur biweekly, with 30min talks and 15min for Q&A from the online audience. The talk and Q&A will be posted on the US CLIVAR Youtube channel as part of the US CLIVAR’s mission to serve the broader climate community and society. Upcoming webinars can be found on our Google Calendar.

If you are interested in attending the biweekly seminar, please fill out this Google Form and we will add you to our webinar's mailing list.

To learn more about the different US CLIVAR webinar series and instructions on how to join an upcoming webinar, click here. 

Next webinar: October 26, 2020 @ 3pm EDT/12pm PDT

Presenter: Grey Nearing (University of Alabama)

Talk: What role does hydrological science play in the age of machine learning?

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