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.
Achieving Skilled and Reliable Daily Probabilistic Forecasts of Wind Power at Subseasonal-to-Seasonal Timescales over France
Atos Inno’Lab TS Bezons（阿托斯创新实验室TS贝宗）；EDF R&D Lab（EDF研发实验室）；Laboratoire des Sciences du Climat & de l’Environnement（气候与环境科学实验室）；CEA（法国国家科学研究中心）；CNRS（法国国家科学研究中心）；UVSQ（法国大学巴黎-萨克雷）；Université Paris-Saclay（巴黎-萨克雷大学）；Laboratoire de Mathématiques d’Orsay（奥赛数学实验室）
CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；DAMO Academy, Alibaba Group（阿里巴巴达摩院）
FuXi-S2S: A machine learning model that outperforms conventional global subseasonal forecast models
Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化研究院）；Shanghai Academy of Artificial Intelligence for Science（上海科学人工智能研究院）；Xiong’an Institute of Meteorological Artificial Intelligence（雄安气象人工智能研究院）；University of Gothenburg（哥德堡大学）；Scripps Institution of Oceanography, University of California San Diego（加州大学圣迭戈分校斯克里普斯海洋研究所）；School of Data Science, Fudan University（复旦大学数据科学学院）；Institute for Big Data, Fudan University（复旦大学大数据研究院）
University of Minnesota, Twin Cities（明尼苏达大学双城校区）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；George Mason University（乔治梅森大学）
Sub-seasonal climate forecasting (SSF) is the prediction of key climate variables such as temperature and precipitation on the 2-week to 2-month time horizon. Skillful SSF would have substantial societal value in areas such as agricultural productivity, hydrology and water resource management, and emergency planning for extreme events such as droughts and wildfires. Despite its societal importance, SSF has stayed a challenging problem compared to both short-term weather forecasting and long-term seasonal forecasting. Recent studies have shown the potential of machine learning (ML) models to ad…
Microsoft（微软）；Department of Atmospheric Sciences, University of Washington（华盛顿大学大气科学系）；Microsoft Research（微软研究院）
We present an ensemble prediction system using a Deep Learning Weather Prediction (DLWP) model that recursively predicts key atmospheric variables with six-hour time resolution. This model uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts. The approach is computationally efficient, requiring just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4° resolution. Ensemble spread is primarily produced by randomizing the CNN training process to create a set of 32 DLWP models with slightly different learned weights. Althou…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven sea ice forecasting, we propose an attention-based Long Short Term Memory (LSTM) ensemble method to predict monthly sea ice extent up to 1 month ahead. Using daily and monthly satellite retrieved sea ice data from NSIDC and atmospheric and oceanic variables f…
Data-driven Seasonal Climate Predictions via Variational Inference and Transformers
Barcelona Supercomputing Center, Earth Sciences Department, Spain（巴塞罗那超级计算中心，地球科学部门，西班牙）；Facultat de Física, Universitat de Barcelona, Martí i Franquès 1, 08028 Barcelona（巴塞罗那大学物理学院，Martí i Franquès 1，08028 巴塞罗那）；Lobelia Earth, Barcelona, 08005, Spain（Lobelia Earth，巴塞罗那，08005，西班牙）；Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain（加泰罗尼亚高级研究与教育研究所（ICREA），巴塞罗那，西班牙）
