Intelligent Earth Seminar: Peter Manshausen (Nvidia)

27 November 14:00
Seminar Room 1a, Doctoral Training Centre, 1-4 Keble Rd
screenshot 2025 11 25 at 10 29 49

Peter Manshausen is a research scientist in NVIDIA’s weather and climate simulation group. He joined the group after defending his PhD thesis in Atmospheric Physics in Oxford in March 2025, supervised by Philip Stier. His PhD research focused on aerosol-cloud interactions using opportunistic experiments in large quantities of satellite data. His research currently focuses on generative climate model emulation and interactivity through diffusion guidance, as well as score-based data assimilation. 

Climate in a Bottle—towards interactive generative climate models at km-scales.

 

Kilometer-scale climate data, which is now being produced at Petabyte volumes poses enormous challenges for storage and queries. We present Climate in a Bottle (cBottle), a generative diffusion-based framework emulating global 5 km climate simulations and reanalysis on the HEALPix grid. cBottle samples directly from the full distribution of atmospheric states, avoiding auto-regressive rollout, and is the first to reach this 12.5M-pixel global resolution. cBottle passes a battery of tests, including diurnal-to-seasonal variability, large-scale modes of variability, tropical cyclone statistics, and trends of climate change and weather extremes. It is a step toward a foundation model: bridging data modalities (reanalysis and simulation), enabling zero-shot bias correction, downscaling, and data infilling. It also enables new interactivity via guided diffusion. For example, we train a tropical cyclone (TC) classifier alongside the generator, guide towards TC states, and obtain physically credible samples. This opens the door to guidance methods for a wide array of user queries and new ways of interacting with climate data.