Mike Pritchard (@scipritchard) 's Twitter Profile
Mike Pritchard

@scipritchard

Director of Climate Simulation Research for NVIDIA and Professor at UC Irvine. Enthused about Earth system science, HPC, machine learning. Views are my own.

ID: 88519494

calendar_today08-11-2009 21:53:29

567 Tweet

2,2K Followers

686 Following

Mike Pritchard (@scipritchard) 's Twitter Profile Photo

It’s been so exciting to see all this organic energy around our benchmark for hybrid AI + physics multi-scale climate simulation. I love working with LEAP-STC UCI ESS NVIDIA and all the institutions that contributed… can’t wait to see what new is learnt from the top fits!

Mike Pritchard (@scipritchard) 's Twitter Profile Photo

Despite how much has changed in the AI / climate space since this excellent 2022 workshop, many of the challenges reviewed in its summary paper remain relevant research frontiers. Grateful to its leaders for including our viewpoint from work NVIDIA UCI ESS UC Irvine School of Physical Sciences LEAP-STC

Pierre Gentine (@pierregentine) 's Twitter Profile Photo

Excited to share our latest paper led by ⁦Xu Lian⁩ discussing the key role of windthrow and water deficit on the Amazon seasonality - Water deficit and storm disturbances co-regulate Amazon rainforest seasonality | Science Advances science.org/doi/10.1126/sc…

Morteza Mardani (@mardanimorteza) 's Twitter Profile Photo

🌪️ Can Gaussian-based diffusion models handle heavy-tailed data like extreme scientific events? The answer is NO. We’ve redesigned diffusion models with multivariate "Student-t" noise to tackle heavy tails! 📈 📝 Read more: arxiv.org/abs/2410.14171

🌪️ Can Gaussian-based diffusion models handle heavy-tailed data like extreme scientific events? The answer is NO. We’ve redesigned diffusion models with multivariate "Student-t" noise to tackle heavy tails! 📈

📝 Read more: arxiv.org/abs/2410.14171
Mike Pritchard (@scipritchard) 's Twitter Profile Photo

Please see this new work on reformulating diffusion ML models to more naturally handle the heavy tailed statistics that are intrinsic to water cycle state variables in the earth system. It’s delightful to work on atmospheric science with generative AI experts NVIDIA research!

Mike Pritchard (@scipritchard) 's Twitter Profile Photo

Happy to share this latest work led by NVIDIA research colleagues on stochastic downscaling AI modeling demonstrated for weather and climate applications. Escalating adventures in multivariate super resolution & new channel synthesis using generative AI!

Mike Pritchard (@scipritchard) 's Twitter Profile Photo

I'm hiring for 1-2 new FTEs within 1 year of PhD to join our @Nvidia research team. Outstanding ML research & technical ability are a must-have, ideally alongside climate/weather/fluids/physics domain expertise or equivalent experience. Details: nvidia.wd5.myworkdayjobs.com/NVIDIAExternal…

Mike Pritchard (@scipritchard) 's Twitter Profile Photo

Thanks for shining a light on our latest hybrid simulation results. I’ve been working on this problem for > 7 years starting with Pierre Gentine and Stephan Rasp & these are phase-changing results. Zeyuan Hu absolutely excelled during his NVIDIA internship. Check out his talk!