Timezone: »

 
Calibration of Large Neural Weather Models
Andre Graubner · Kamyar Azizzadenesheli · Jaideep Pathak · Morteza Mardani · Mike Pritchard · Karthik Kashinath · Anima Anandkumar

Fri Dec 09 09:00 AM -- 09:09 AM (PST) @
in Tackling Climate Change with Machine Learning »
Event URL: https://www.climatechange.ai/papers/neurips2022/87 »

Uncertainty quantification of weather forecasts is a necessity for reliably planning for and responding to extreme weather events in a warming world. This motivates the need for well-calibrated ensembles in probabilistic weather forecasting. We present initial results for the calibration of large-scale deep neural weather models for data-driven probabilistic weather forecasting. By explicitly accounting for uncertainties about the forecast's initial condition and model parameters, we generate ensemble forecasts that show promising results on standard diagnostics for probabilistic forecasts. Specifically, we are approaching the Integrated Forecasting System (IFS), the gold standard on probabilistic weather forecasting, on: (i) the spread-error agreement; and (ii) the Continuous Ranked Probability Score (CRPS). Our approach scales to state-of-the-art data-driven weather models, enabling cheap post-hoc calibration of pretrained models with tens of millions of parameters and paving the way towards the next generation of well-calibrated data-driven weather models.

Author Information

Andre Graubner (Tsinghua University)
Kamyar Azizzadenesheli (Nvidia)
Kamyar Azizzadenesheli

Kamyar is a Senior Research Scientist at Nvidia since Summer 2022. Prior to his role at Nvidia, he was an assistant professor at Purdue University, department of computer science, from Fall 2020 to Fall 2022. Prior to his faculty position, he was at the California Institute of Technology (Caltech) as a Postdoctoral Scholar in the Department of Computing + Mathematical Sciences. Before his postdoctoral position, he was appointed as a special student researcher at Caltech, working with ML and Control researchers at the CMS department and the Center for Autonomous Systems and Technologies. He is also a former visiting student researcher at Caltech. Kamyar Azizzadenesheli is a former visiting student researcher at Stanford University, and researcher at Simons Institute, UC. Berkeley. In addition, he is a former guest researcher at INRIA France (SequeL team), as well as a visitor at Microsoft Research Lab, New England, and New York. He received his Ph.D. at the University of California, Irvine.

Jaideep Pathak (NVIDIA Corporation)
Morteza Mardani (Nvidia)
Mike Pritchard (Nvidia)
Karthik Kashinath (NVIDIA)
Anima Anandkumar (NVIDIA/Caltech)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors