AOSC Seminar by Marybeth Arcodia, 9/3/2026

AOSC Seminar

Marybeth Arcodia

University of Miami

Title

Harnessing Data Science to Advance Climate Prediction through Forecasts of Opportunity

Abstract

The climate system is chaotic and noisy, yet within this noise lie windows of predictability that enhance our ability to make accurate weather and climate predictions. This talk highlights innovative machine learning and data science approaches that identify forecasts of opportunity—climate states where prediction skill and confidence are elevated—ultimately advancing prediction beyond traditional limits. I will overview how neural networks trained on large ensemble climate model data, validated with observations, reveal subseasonal (2 week–3 month) U.S. precipitation predictability. North Atlantic sea surface salinity, a relatively untapped source, holds predictive information for Midwest precipitation forecasts of opportunity. Explainable AI techniques provide insights into model decision-making, building trust while uncovering new sources of predictability and improving our understanding of the climate system. Building on these insights, our team is developing a machine learning–based real-time subseasonal U.S. precipitation forecasting tool that identifies when, where, and why a forecast is a forecast-of-opportunity. By quantifying forecast confidence and effectively communicating predictions to forecasters and users, this tool integrates scientific understanding with actionable information. Ongoing and future research in the group spans multiple domains: predicting lead times for coral heat stress events, applying machine learning for uncertainty quantification in coastal sea level predictions, predicting the timing of critical temperature threshold crossings in future climates, and utilizing purely AI-based weather models to push the frontiers of climate prediction. I will conclude with future research directions, highlighting opportunities for interdisciplinary collaboration at the intersection of data science and climate.

Bio

Dr. Marybeth Arcodia earned a Bachelor of Arts in Mathematics from Georgetown University in 2014 before completing a Ph.D. in Atmospheric Science at the University of Miami Rosenstiel School of Marine, Atmospheric and Earth Science in 2021. She is now an Assistant Professor joint between the Rosenstiel School of Marine, Atmospheric, and Earth Sciences Department of Atmospheric Sciences and the Frost Institute for Data Science and Computing at the University of Miami. Her research bridges Earth system predictability and prediction, integrating atmospheric science and AI-based techniques to explore variability and change across weather-to-climate scales. Her work focuses on localized impacts in future climates to further our understanding of the stressed climate system and aid in advancing preparedness for climate risk. She is a member of the US CLIVAR Predictability, Predictions, and Applications Interface Panel and the Working Group on Climate Data and Predictions for Coastal Solutions.

Contact

Maria Molina

If you are not subscribed to seminar announcements and need a link to this online seminar please contact aosc-helper. You can also subscribe to weekly links and announcements below. 

AOSC Seminar

Pre-seminar refreshment: N/A
Seminar: 3:30-4:30pm, Room: ATL 2400(only when in-person)
Meet-the-Speaker: 4:30-5:00pm, Room: ATL 3400(only when in-person) [For AOSC Students only]

[ Subscribe to receive seminar announcements | Email aosc-deptseminar@umd.edu to give a seminar ]