AI Paper Atlas

Research map / Video / Video segmentation and tracking

STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather Forecasting

Qihe Huang, Zhengyang Zhou, Yangze Li, Jiaming Ma, Kuo Yang, Binwu Wang, Xu Wang, Yang Wang

ICLR 2026 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add temporal evolution encoder (ablation)STORM · ERA5 global, 10 variablesRMSEImproved
add multi-scale modeling instead of single scale (ablation)STORM · ERA5 global, 10 variablesRMSEImproved
add spatial encoder (ablation)STORM · ERA5 global, 10 variablesRMSEImproved
add cross-scale message passing (ablation)STORM (3 scales) · ERA5 globalACC: 0.976 -> 0.984Improved
add cross-scale message passing (ablation)STORM (5 scales) · ERA5 globalRMSE: 16.879 -> 15.757Improved
use different temporal scales across branches instead of the same (ablation)STORM (3 scales) · ERA5 globalACC: 0.948 -> 0.984Improved
use different temporal scales across branches instead of the same (ablation)STORM (2 scales) · ERA5 globalRMSE: 16.547 -> 16.093Improved
increase number of scales from 1 to 5 branches (d_model 64 to 256-512) (ablation)STORM · ERA5 globalACC: 0.941 -> 0.988Improved
increase number of branches from 4 to 5 (d_model 256) (ablation)STORM · ERA5 globalACC: 0.987 -> 0.988Improved
increase d_model from 256 to 512 at 4 branches (ablation)STORM · ERA5 globalACC: 0.987 -> 0.986Hurt
use multi-scale STORM instead of PanguSTORM vs Pangu · Efficiency, inferenceseconds per 100 samples: 5.11 -> 0.87Improved
use STORM instead of Triton on regional forecasting at 10 daysSTORM vs Triton · South America 1deg, 10-dayACC: 0.251 -> 0.499Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy