2025-10-23 All-Hands Presentation Meeting Notes
Advancing Earth System Modeling using AI/ML
Dan Lu
Computational Sciences and Engineering Division, Oak Ridge National Laboratory
Abstract: Understanding and predicting the Earth system is essential for advancing Earth science and strengthening energy system reliability. Dan’s research focuses on integrating diverse datasets—including in situ measurements, remote sensing observations, and model simulation outputs—with both physics-based and machine learning (ML) approaches to enhance Earth system predictability.
In this talk, she will introduce an uncertainty quantification framework designed to improve the predictive skill of physics-based Earth system models. She will then discuss the development of multimodal, explainable, and trustworthy ML methods that advance the generalizability, interpretability, and reliability of data-driven models under changing conditions. Finally, she will explore AI foundation models in Earth system modeling and highlight ongoing efforts to build regional digital testbeds—focusing on groundwater mapping in the Pacific West, flood prediction in the Mid-Atlantic, and reservoir inflow forecasting in the Southeastern United States.
Date Oct 23, 2025
Time
PT: 8:30 am
ET: 11:30 am
Call Info
web session: https://global.gotomeeting.com/join/570361173
call number: (571) 317-3122 Access Code: 570-361-173, If busy, use alternate number: (773) 945-1029
Joining from a video-conferencing room or system? Dial: 67.217.95.2##570361173 , Cisco devices: 570361173@67.217.95.2
Time | Title | Presenter | Presentation | Recording | Notes |
|---|---|---|---|---|---|
30 min | Advancing Earth System Modeling using AI/ML | Dan Lu | 
|
|