Modern scientific progress is often driven by numerical computations and simulations to represent large numbers of complex and interrelated physical processes. In recent years, machine learning (ML) applications in earth system simulation and prediction have promised to accelerate the accuracy and computational processing power of Earth system models including physics-constrained approaches, super ultra-high resolution, large language models for earth systems, and uncertainty quantification.
In this workshop we aim to bring together experts from diverse fields related to earth system simulation (e.g. computer science, mathematics, atmospheric science, earth system science, etc.) to explore the intersection of mathematics, traditional numerical methods, data assimilation, and cutting-edge machine learning techniques.
Topics that will be discussed include
Donifan Barahona
(NASA)
Katherine Breen
(NASA)
Nico Caltabiano
(University of Southampton)
Milan Curcic
(University of Miami)
Adam Rupe
(Pacific Northwest National Laboratory)
Marcus van Lier-Walqui
(Columbia University)
Copyright. All Rights Reserved.