Timezone: »

DL-Corrector-Remapper: A grid-free bias-correction deep learning methodology for data-driven high-resolution global weather forecasting
Tao Ge · Jaideep Pathak · Akshay Subramaniam · Karthik Kashinath

Fri Dec 09 04:11 PM -- 04:21 PM (PST) @
Event URL: https://www.climatechange.ai/papers/neurips2022/77 »

Data-driven models, such as FourCastNet (FCN), have shown exemplary performance in high-resolution global weather forecasting. This performance, however, is based on supervision on mesh-gridded weather data without the utilization of raw climate observational data, the gold standard ground truth. In this work we develop a methodology to correct, remap, and fine-tune gridded uniform forecasts of FCN so it can be directly compared against observational ground truth, which is sparse and non-uniform in space and time. This is akin to bias-correction and post-processing of numerical weather prediction (NWP), a routine operation at meteorological and weather forecasting centers across the globe. The Adaptive Fourier Neural Operator (AFNO) architecture is used as the backbone to learn continuous representations of the atmosphere. The spatially and temporally non-uniform output is evaluated by the non-uniform discrete inverse Fourier transform (NUIDFT) given the output query locations. We call this network the Deep-Learning-Corrector-Remapper (DLCR). The improvement in DLCR’s performance against the gold standard ground truth over the baseline’s performance shows its potential to correct, remap, and fine-tune the mesh-gridded forecasts under the supervision of observations.

Author Information

Tao Ge (Washington University in St. Louis)
Jaideep Pathak (NVIDIA Corporation)
Akshay Subramaniam (NVIDIA)
Akshay Subramaniam

I am a Senior AI Developer Technology Engineer at NVIDIA. I got my PhD in Aeronautics from Stanford in 2019 working on topics related to turbulent flows and fluid mechanics, large eddy simulations, numerical methods and physics informed ML. At NVIDIA, I have been working on topics involving the convergence of physics and deep learning as well as data compression, recommender systems and automatic speech recognition.

Karthik Kashinath (NVIDIA)

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

More from the Same Authors