Climate Modeling
Climate Modeling for the future of the planet
Since the early days of climate modeling, software, hardware, and the way that engineers and scientists collaborate have gone through incredible transformations. Better data and technologies will inform how we mitigate and adapt to global impacts, such as sea level rise, community destruction, and biodiversity loss.
Recent Updates
DSL team leaves AI2, continues with NOAA and NASA, MeteoSchweiz
December 31, 2022This marks the DSL group's last day in AI2. In 2 years at Vulcan and 16 months at AI2, the DSL group, led by Oli Fuhrer, developed a ground-breaking…
AI2 CM presents at NeurIPS 2022 - ML emulation of microphysics
November 28, 2022At the Machine Learning and Physical Sciences workshop on Dec 3, Brenowitz et al. present “Emulating fast processes in climate models” on ML…
AI2 CM presents at NeurIPS 2022 - Corrective ML trained on 1 yr global storm-resolving run
November 28, 2022At the Machine Learning and Physical Sciences workshop on Dec 3, Anna Kwa presents “Machine-learned climate model corrections from a global storm…
AI2 CM presents at NeurIPS 2022 - Novelty detection for selective ML correction
November 28, 2022At the NeurIPS Climate Change AI workshop, AI2 summer intern Clayton Sanford applies novelty detection to increase the stability and accuracy of ML…
AI2 CM trains corrective ML on year-long 3 km global simulation to improve multi-year 200 km runs.
September 23, 2022This preprint extends our past work using NOAA/GFDL's X-SHiELD 3-km grid global storm-resolving model (GSRM), to train corrective ML to improve a…
Recent Papers
Emulating Fast Processes in Climate Models
Noah Brenowitz, W. Perkins, J. M. Nugent, Oliver Watt‐Meyer, S. Clark, Anna Kwa, B. Henn, J. McGibbon, C. BrethertonNeurIPS•Machine Learning and Physical Sciences • 2022 Cloud microphysical parameterizations in atmospheric models describe the formation and evolution of clouds and precipitation, a central weather and climate process. Cloud-associated latent heating is a primary driver of large and small-scale circulations…Improving the predictions of ML-corrected climate models with novelty detection
Clayton Sanford, Anna Kwa, Oliver Watt‐Meyer, S. Clark, Noah Brenowitz, J. McGibbon, C. BrethertonNeurIPS•Climate Change AI • 2022 While previous works have shown that machine learning (ML) can improve the prediction accuracy of coarse-grid climate models, these ML-augmented methods are more vulnerable to irregular inputs than the traditional physics-based models they rely on. Because ML…Machine-learned climate model corrections from a global storm-resolving model
Anna Kwa, S. Clark, B. Henn, Noah Brenowitz, J. McGibbon, W. Perkins, Oliver Watt‐Meyer, L. Harris, C. BrethertonNeurIPS•Machine Learning and Physical Sciences • 2022 Due to computational constraints, running global climate models (GCMs) for many years requires a lower spatial grid resolution ( (cid:38) 50 km) than is optimal for accurately resolving important physical processes. Such processes are approximated in GCMs via…Machine-learned climate model corrections from a global storm-resolving model: Performance across the annual cycle
Anna Kwa, Spencer. K. Clark, Brian Henn, Noah D. Brenowitz, Jeremy McGibbon, Oliver Watt-Meyer, W. Andre Perkins, Lucas Harris, and Christopher S. BrethertonESSOAr • 2022 One approach to improving the accuracy of a coarse-grid global climate model is to add machine-learned state-dependent corrections to the prognosed model tendencies, such that the climate model evolves more like a reference fine-grid global storm-resolving…Pace v0.1: A python-based performance-portable implementation of the FV3 dynamical core
Johann Dahm, Eddie Davis, Florian Deconinck, Oliver Elbert, Rhea George, Jeremy McGibbon, Tobias Wicky, Elynn Wu, Christopher Kung, Tal Ben-Nun, Lucas Harris, Linus Groner, and Oliver FuhrerEGUsphere • 2022 Progress in leveraging current and emerging high-performance computing infrastructures using traditional weather and climate models has been slow. This has become known more broadly as the software productivity gap. With the end of Moore's Law driving forward…