← Back to all news
arXiv Statistics ML By Rongwen Li, Haixin Xie, Mingyang Wang, Hongwu Liu, Kun Fang, Changjian Chen, Zhuo Tang, Kenli Li

STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting

Read the original on arXiv Statistics ML →

STCFormer is an adaptive spatio‑temporal Transformer that dynamically clusters weather stations within each temporal patch, combining fine‑grained local attention inside clusters with global attention over regional summaries. The model’s design is supported by a Lipschitz upper bound that suggests robustness benefits, and it achieves the lowest 24‑hour mean squared error across eight temperature and wind forecasting tasks on three real‑world datasets, ranking first or second in 47 of 48 comparisons. Ablation studies and case analyses confirm the advantages of locally adaptive grouping and complementary local‑global interactions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv Machine Learning
Sep 22

UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations

UniGIO is a generative framework that models global in‑situ weather dynamics directly from incomplete GIO data, unifying forecasting, imputation, and generation across arbitrary missing ratios. It employs an Observation Mixer, Event Aligner, Adaptive Temporal Mixer, and a Mixture‑of‑Experts structure to capture station‑level complementarity, temporal dependencies, and extreme events, refining outputs with a Local Refiner. Experiments on the Weather‑5K dataset show state‑of‑the‑art performance, improving accuracy, fidelity, and extreme event capture by 11%, 12%, and 5% respectively.

By Songru Yang, Zili Liu, Tao Han, Ben Fei, Lei Bai, Chang Liu, Zhengxia Zou, Xiangyang Ji, Wanli Ouyang, Zhenwei Shi
benchmarks
More like this →
arXiv AI
Sep 2

Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Earth System Prediction

The paper introduces STORM, a one‑stage generative AI framework that reformulates Earth system data assimilation as diffusion‑based Bayesian posterior sampling, replacing costly PDE ensemble forecasts with scalable AI inference. STORM employs a spatiotemporal transformer with a global‑attention algorithm that reduces computational complexity from quadratic to linear, enabling high‑resolution, long‑context modeling. The system scales to 74,400 GPUs on Frontier, achieving 96–99 % strong‑scaling efficiency and up to 6 ExaFLOPs sustained BF16 throughput, while supporting 32,768‑member ensembles for uncertainty quantification in just 34 seconds on 4,096 GPUs, and demonstrates improved hurricane tracking and climate reanalysis accuracy.

By Xiao Wang, Zezhong Zhang, Isaac Lyngaas, Hong-Jun Yoon, Jong-Youl Choi, Siming Liang, Janet Wang, Hristo G. Chipilski, Ashwin M. Aji, Feng Bao, Peter Jan van Leeuwen, Dan Lu, Guannan Zhang
llmsdiffusionefficiency
More like this →