Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang, Dmitry A. Abanin · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28512 · open-access PDF
Proses atmosferik yang belum terselesaikan dapat memperkenalkan ketergantungan sejarah di luar jendela input pendek yang digunakan oleh banyak model prediksi cuaca. Kami memperkenalkan GraphCast--Mamba, yang meningkatkan tulang belakang GraphCast yang beku, pra-latih $1\circ$ dengan cabang koreksi Mamba yang dapat dilatih yang menggabungkan pengalihan pesan grafis dan lapisan Mamba. Cabang ini mempertahankan status memori temporal melalui langkah-langkah prediksi enam jam berturut-turut, belajar koreksi yang diinformasikan oleh konteks waktu di luar input dua frame GraphCast. Pelatihan terbatas pada cabang koreksi, menggunakan data ERA5 dari 2015-2021. Setelah 2,500 optimizer u
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