Contact person
Olof Mogren
Senior Researcher
Contact Olof
-
María J. Molina: Machine learning for Earth system prediction and predictability
At RISE Learning Machines Seminar on March 27, 2025, we have the pleasure to listen to María J. Molina, University of Maryland, give her talk: Machine learning for Earth system prediction and predictability. This seminar is a collaboration between RISE and Climate AI Nordics.
Abstract
Machine learning can be used for Earth system prediction, or to study the uppermost limit of prediction skill theoretically achievable given the system's initial state or other factors, otherwise known as predictability. In traditional numerical weather prediction frameworks, we solve the governing partial differential equations starting from an initial state.
This initialized prediction framework usually involves three stages:
- generating the initial conditions of the Earth system,
- running the mathematical representation of the system on a computer forward in time, and
- analyzing the output and converting it into a format that is useful for end users.
Machine learning can be used to improve each of these individual stages, or to circumvent the three stage framework altogether, and examples of each will be given in this seminar. More time during the seminar will be dedicated to the challenges surrounding subseasonal prediction, which focuses on lead times of three to four weeks, and how we can use machine learning to both uncover potential biases in our initialized prediction systems and how we can bias-correct them.
About the speaker
Dr. Maria J. Molina is an Assistant Professor at the University of Maryland, College Park, affiliated with the Artificial Intelligence Interdisciplinary Institute and the Institute for Advanced Computer Studies. She is also affiliated with NSF NCAR in Boulder, Colorado, serves as Vice Chair of the AMS Committee on AI Applications to Environmental Science, and is a member of the US CLIVAR PPAI panel and the WCRP ESMO Scientific Steering Group.
She recently received NASA’s Early Career Investigator Award. Her research applies machine learning (e.g., neural networks) and numerical modeling (e.g., CESM) to climate and extreme weather studies, focusing on Earth system prediction, extreme event genesis, and multi-scale climate patterns. She emphasizes open-source tools, accessible communication, and interdisciplinary collaboration.
