arXiv cs.AI· Zhe Wang, Sijie Chen, Yiming Luo, Daehyun Kim, Chien-Yi Chang·· 3 天前AI 评分27
TC-Next：零样本多模态热带气旋预报模型
TC-Next: Zero-Shot Multimodal Cyclone Forecasting
AI 导读
多模态深度学习模型 TC-Next 可基于 GraphCast 预报与 GridSat 红外卫星图像，实现 6-24 小时热带气旋路径与强度预报。在 GraphCast 上，其路径误差较规则追踪器 TempestExtremes 降低 15-44%，强度误差降至 1/3-1/6，且无需重训练即可迁移至 Pangu-Weather 和 IFS HRES。
正文 · 原文
Abstract:We present TropicalCycloneNext (TC-Next), a multimodal deep learning model that forecasts tropical cyclone track and intensity at $6-24$h leads by leveraging a foundation model's forecast of atmospheric kinematic and thermodynamic fields, along with GridSat infrared satellite imagery. Trained only on GraphCast forecasts over the Western Pacific (WP), yet reliant only on generic atmospheric variables, TC-Next on GraphCast lowers track error by $15-44\%$ and intensity error by a factor of $3-6$ relative to the rule-based tracker TempestExtremes; applied without retraining to Pangu-Weather and IFS HRES forecasts, it stays ahead on both. Applied zero-shot to the generic weather fields of WeatherNext Cyclones on the 2025 WP season, it attains lower average intensity error at every lead time, and lower or comparable average track error, than that model's specialized direct tracker in a deterministic comparison. Ablations show that the satellite branch lowers track error at every lead time and intensity error at longer leads. TC-Next thus gives a common, independently verifiable basis for comparing the AI forecasts that inform cyclone-warning and climate-adaptation decisions as best available science.
| Comments: | 4 pages; Accepted to NeurIPS 2026 Tackling Climate Change with Machine Learning Workshop |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2609.02085 [cs.LG] |
| (or arXiv:2609.02085v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.02085 arXiv-issued DOI via DataCite |
Submission history
From: Chien-Yi Chang [view email]
[v1]
Wed, 2 Sep 2026 04:17:22 UTC (43 KB)
[v2]
Tue, 13 Oct 2026 12:30:07 UTC (44 KB)
来源：arXiv cs.AI · arxiv.org