Physics-Informed Teleconnection-Aware Transformer for Global Subseasonal-to-Seasonal Forecasting

TL;DR

TelePiT is a novel deep learning model that integrates physical atmospheric processes and teleconnection patterns to improve global subseasonal-to-seasonal climate forecasts, outperforming existing methods.

Contribution

The paper introduces TelePiT, a new architecture combining physics-informed neural networks and teleconnection modeling for enhanced S2S forecasting accuracy.

Findings

Outperforms state-of-the-art models across all forecast horizons.

Effectively captures multi-scale physical atmospheric processes.

Successfully models global climate teleconnections.

Abstract

Subseasonal-to-seasonal (S2S) forecasting, which predicts climate conditions from several weeks to months in advance, represents a critical frontier for agricultural planning, energy management, and disaster preparedness. However, it remains one of the most challenging problems in atmospheric science, due to the chaotic dynamics of atmospheric systems and complex interactions across multiple scales. Current approaches often fail to explicitly model underlying physical processes and teleconnections that are crucial at S2S timescales. We introduce \textbf{TelePiT}, a novel deep learning architecture that enhances global S2S forecasting through integrated multi-scale physics and teleconnection awareness. Our approach consists of three key components: (1) Spherical Harmonic Embedding, which accurately encodes global atmospheric variables onto spherical geometry; (2) Multi-Scale Physics-Informed Neural ODE, which explicitly captures atmospheric physical processes across multiple learnable frequency bands; (3) Teleconnection-Aware Transformer, which models critical global climate interactions through explicitly modeling teleconnection patterns into the self-attention. Extensive experiments demonstrate that \textbf{TelePiT} significantly outperforms state-of-the-art data-driven baselines and operational numerical weather prediction systems across all forecast horizons, marking a significant advance toward reliable S2S forecasting.