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

arXiv: https://arxiv.org/abs/2506.08049 · HTML: https://mlsanity.com/paper/2506.08049/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 66 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Machine learning accelerated computational fluid dynamics](https://mlsanity.com/paper/2102.01010/) (2021)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2208.05419/) (2022)
- [Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems](https://mlsanity.com/paper/2003.04919/) (2020)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs](https://mlsanity.com/paper/2404.10024/) (2024)
- [ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction](https://mlsanity.com/paper/2402.00712/) (2024)
- [SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking](https://mlsanity.com/paper/2109.10399/) (2021)
- [Improving Subseasonal Forecasting in the Western U.S. with Machine Learning](https://mlsanity.com/paper/1809.07394/) (2018)
- [CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer](https://mlsanity.com/paper/2502.19750/) (2025)
- [Unleashing The Power of Pre-Trained Language Models for Irregularly Sampled Time Series](https://mlsanity.com/paper/2408.08328/) (2024)
- [AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting](https://mlsanity.com/paper/2409.16586/) (2024)
- [Learning and Dynamical Models for Sub-seasonal Climate Forecasting: Comparison and Collaboration](https://mlsanity.com/paper/2110.05196/) (2021)
- [NRFormer: Nationwide Nuclear Radiation Forecasting with Spatio-Temporal Transformer](https://mlsanity.com/paper/2410.11924/) (2024)

## Built on by (most cited first, 2 of 2)

- [Skillful Subseasonal-to-Seasonal Forecasting of Extreme Events with a Multi-Sphere Coupled Probabilistic Model](https://mlsanity.com/paper/2512.12545/) (2025)
- [Symmetric Composition of Anisotropic Operators for Global Subseasonal-to-Seasonal Climate Forecasting](https://mlsanity.com/paper/2602.15040/) (2026)

## Abstract (arXiv)

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 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 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.