GTC Silicon Valley-2019 ID:S9731:Combining Machine Learning and GPU Acceleration to Transform Atmospheric Science
Richard Loft(National Center for Atmospheric Research)
Scientific model performance has begun to stagnate over the last decade due to plateauing core speeds, increasing model complexity, and mushrooming data volumes. Learn how our team at the National Center for Atmospheric Research is pursuing an end-to-end hybrid approach to surmounting these barriers. We'll discuss how combining ML-based emulation with GPU acceleration of numerical models can pave the way toward new scientific modeling capabilities. We'll also detail our approach, which uses machine learning and GPU acceleration to produce what we hope will be a new generation of ultra-fast meteorological and climate models that provide enhanced fidelity with nature and increased value to society.