DL-Corrector-Remapper: A grid-free bias-correction deep learning methodology for data-driven high-resolution global weather forecasting

TL;DR

This paper introduces DL-Corrector-Remapper, a deep learning approach using AFNO architecture to bias-correct and remap high-resolution weather forecasts directly against observational data, improving accuracy.

Contribution

The novel DLCR method combines AFNO with NUIDFT to correct and remap weather forecasts based on sparse observations, bridging the gap between model outputs and real-world data.

Findings

DLCR outperforms baseline forecasts in accuracy.

It effectively remaps non-uniform observational data.

Demonstrates potential for bias correction in weather forecasting.

Abstract

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.