MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shchur, Andrii, Skarga-Bandurova, Inna
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911514738294784
author Shchur, Andrii
Skarga-Bandurova, Inna
author_facet Shchur, Andrii
Skarga-Bandurova, Inna
contents Weather forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly for frequent regional updates, as high-resolution nests require intensive boundary coupling. We introduce Multi-Resolution Graph Neural Forecasting (MR-GNF), a lightweight, physics-aware model that performs short-term regional forecasts directly on an ellipsoidal, multi-scale graph of the Earth. The framework couples a 0.25° region of interest with a 0.5° context belt and 1.0° outer domain, enabling continuous cross-scale message passing without explicit nested boundaries. Its axial graph-attention network alternates vertical self-attention across pressure levels with horizontal graph attention across surface nodes, capturing implicit 3-D structure in just 1.6 M parameters. Trained on 40 years of ERA5 reanalysis (1980-2024), MR-GNF delivers stable +6 h to +24 h forecasts for near-surface temperature, wind, and precipitation over the UK-Ireland sector. Despite a total compute cost below 80 GPU-hours on a single RTX 6000 Ada, the model matches or exceeds heavier regional AI systems while preserving physical consistency across scales. These results demonstrate that graph-based neural operators can achieve trustworthy, high-resolution weather prediction at a fraction of NWP cost, opening a practical path toward AI-driven early-warning and renewable-energy forecasting systems. Project page and code: https://github.com/AndriiShchur/MR-GNF
format Preprint
id arxiv_https___arxiv_org_abs_2603_13563
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
Shchur, Andrii
Skarga-Bandurova, Inna
Machine Learning
Artificial Intelligence
I.2.6; I.5.1; G.2.2
Weather forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly for frequent regional updates, as high-resolution nests require intensive boundary coupling. We introduce Multi-Resolution Graph Neural Forecasting (MR-GNF), a lightweight, physics-aware model that performs short-term regional forecasts directly on an ellipsoidal, multi-scale graph of the Earth. The framework couples a 0.25° region of interest with a 0.5° context belt and 1.0° outer domain, enabling continuous cross-scale message passing without explicit nested boundaries. Its axial graph-attention network alternates vertical self-attention across pressure levels with horizontal graph attention across surface nodes, capturing implicit 3-D structure in just 1.6 M parameters. Trained on 40 years of ERA5 reanalysis (1980-2024), MR-GNF delivers stable +6 h to +24 h forecasts for near-surface temperature, wind, and precipitation over the UK-Ireland sector. Despite a total compute cost below 80 GPU-hours on a single RTX 6000 Ada, the model matches or exceeds heavier regional AI systems while preserving physical consistency across scales. These results demonstrate that graph-based neural operators can achieve trustworthy, high-resolution weather prediction at a fraction of NWP cost, opening a practical path toward AI-driven early-warning and renewable-energy forecasting systems. Project page and code: https://github.com/AndriiShchur/MR-GNF
title MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
topic Machine Learning
Artificial Intelligence
I.2.6; I.5.1; G.2.2
url https://arxiv.org/abs/2603.13563