Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang, Dmitry A. Abanin · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28512 · open-access PDF
해결되지 않은 대기 프로세스는 많은 날씨 예측 모델에 의해 사용되는 짧은 입력 창을 넘어 역사의 의존성을 도입할 수 있습니다. 우리는 GraphCast--Mamba를 도입합니다.이 창은 GraphCast의 2 프레임 입력 이외의 시간 컨텍스트에 의해 알려진 교정을 학습하여 6 시간 예측 단계를 통해 일시 메모리 상태를 유지합니다. 교육은 ERA5 데이터를 사용하여 2015-2021 년을 사용하여 교정 부서로 제한됩니다.
Machine translation (Meta M2M100); the English original follows.
Unresolved atmospheric processes can introduce history dependence beyond the short input windows used by many weather forecasting models. We introduce GraphCast--Mamba, which augments a frozen, pretrained $1^\circ$ GraphCast backbone with a trainable Mamba correction branch combining graph message passing and Mamba layers. The branch retains a temporal memory state across successive six-hour forecast steps, learning corrections informed by temporal context beyond GraphCast's two-frame input. Training is confined to the correction branch, using ERA5 data from 2015--2021. After 2,500 optimizer u
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28512, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange