TC-Next：零样本多模态热带气旋预测模型
TC-Next: Zero-Shot Multimodal Cyclone Forecasting
浏览论文内容
中文总结 AI 辅助
TC-Next是一种多模态深度学习模型，仅在西太平洋GraphCast预报数据上训练，零样本应用于多种气象模型预报数据时，均优于传统规则追踪器，可提升热带气旋路径与强度预测性能。
中文摘要 AI 辅助
我们提出了热带气旋预测模型TropicalCycloneNext（简称TC-Next），这是一种多模态深度学习模型，可利用基础模型输出的大气运动学与热力学场预报量及GridSat红外卫星影像，提前6至24小时预测热带气旋的路径与强度。TC-Next仅在西太平洋（WP）的GraphCast预报数据上训练，且仅依赖通用大气变量；相较于传统基于规则的追踪器TempestExtremes，它在GraphCast预报数据上的路径误差降低了15%-44%，强度误差缩小至原来的1/3至1/6；无需重新训练即可应用于盘古气象（Pangu-Weather）和欧洲中期天气预报中心的IFS HRES预报数据，在两类指标上均优于TempestExtremes。将TC-Next零样本应用于WeatherNext Cyclones模型输出的2025年西太平洋季节通用气象场，与该模型的专用直接追踪器进行确定性对比时，TC-Next在所有提前时效下的强度误差均更低，路径误差则更低或相当。消融实验表明，该多模态模型能够利用额外模态，在所有提前时效下提升路径预测误差，在较长提前时效下提升强度预测性能。
英文摘要
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 fields of atmospheric kinematic and thermodynamic fields and 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 a conventional, rule-based tracker, TempestExtremes; applied without retraining to the forecast fields of Pangu-Weather and IFS HRES, it stays ahead of TempestExtremes on both. Applied zero-shot to the generic weather fields of WeatherNext Cyclones on the 2025 WP season, TC-Next attains lower intensity error at every lead time, and lower or comparable track error, compared to that model's specialized direct tracker in a deterministic comparison. Our ablation studies show that our multimodal model is able to utilize the additional modality to improve performance in tracking errors at every lead time and in intensity prediction at longer lead times.
发表机构
- Carnegie Mellon University（卡内基梅隆大学）
- Seoul National University（首尔大学）
- Durham University（杜伦大学）
机构由 AI 辅助整理，请以论文原文为准。
