.svg)
.svg)
.svg)
.svg)
.svg)
.svg)
.png)
Minisymposium Presentation
NVIDIA and Earth-2's Contributions to Tools, Libraries, Data and Workflow Infrastructure in the Era of ML-Driven Weather and Climate Modeling
Presenter
Karthik Kashinath is a principal engineer and scientist in HPC+AI at NVIDIA. He co-leads NVIDIA’s Earth-2 initiative, which utilizes cutting-edge large-scale AI to build Earth digital twins for weather and climate applications. A current focus of Earth-2 is on adapting generative AI technologies that are transforming the industry for scientific computing. Karthik is trained as a mechanical and aerospace engineer with a Bachelors from the Indian Institute of Technology – Madras, Masters from Stanford University and PhD from the University of Cambridge. Prior to joining NVIDIA, he worked at Lawrence Berkeley Lab in climate informatics, big data analytics, and physics-informed machine learning for fluid dynamics and Earth system science applications.
Description
In this talk I will discuss contributions from NVIDIA and the Earth-2 Initiative towards scalable, performance-portable, user-friendly tools, libraries, data and workflow infrastructure in the era of ML-driven weather and climate modeling. I'll delve into what approaches might move the needle on digital twinning at ultra-high-resolutions (km- and sub-km-scales), a shared goal across Destination Earth, Earth-2, EVE, and other large international initiatives. This talk will not only provide a few examples that are showing early successes but also speculate on what approaches might be most impactful in this fast changing landscape, especially when data compression and data re-generation, in contrast to data movement, might become the norm in just a few years.