PEAR: Equal Area Weather Forecasting on the Sphere

TL;DR

PEAR is a transformer-based deep learning model that performs weather forecasting on the HEALPix sphere grid, eliminating biases caused by traditional equiangular discretization and outperforming similar models without extra computational cost.

Contribution

The paper introduces PEAR, a novel deep learning model that operates directly on the HEALPix sphere grid for weather forecasting, addressing grid bias issues.

Findings

PEAR outperforms equiangular grid models in accuracy.

PEAR operates efficiently without additional computational overhead.

The model leverages the HEALPix grid to reduce unphysical biases.

Abstract

Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where machine learning models can now rival and even surpass traditional numerical simulations. Following the success of the landmark models Pangu Weather and Graphcast, outperforming traditional numerical methods for global medium-range forecasting, many novel data-driven methods have emerged. A common limitation shared by many of these models is their reliance on an equiangular discretization of the sphere which suffers from a much finer grid at the poles than around the equator. In contrast, in the Hierarchical Equal Area iso-Latitude Pixelization (HEALPix) of the sphere, each pixel covers the same surface area, removing unphysical biases. Motivated by a growing support for this grid in meteorology and climate sciences, we propose to perform weather forecasting with deep learning models which natively operate on the HEALPix grid. To this end, we introduce Pangu Equal ARea (PEAR), a transformer-based weather forecasting model which operates directly on HEALPix-features and outperforms the corresponding model on an equiangular grid without any computational overhead.