用物理启发的扩散模型提升台风预测准确性
Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting
- 将台风特征解耦为轨迹、气压、风速等独立分量
- 通过跨任务注意力机制引入物理先验，提升预测一致性
- 融合多源数据，在全球和区域数据集上表现领先
台风预测对防灾减灾至关重要。深度学习虽缓解计算压力，但常忽略台风属性间的物理关联，导致预测结果缺乏物理合理性。为此，我们提出Phys-Diff——一种受物理启发的潜在扩散模型，将潜在特征解耦为轨迹、气压、风速等任务相关分量，并利用跨任务注意力引入物理先验归纳偏置，从而嵌入属性间的物理一致依赖关系。Phys-Diff通过Transformer编码器-解码器架构融合历史台风数据、ERA5再分析数据及FengWu预报场，进一步提升预测性能。实验表明，该模型在全局与区域数据集上均达到当前最优水平。
原文摘要 · Abstract (English)
Tropical cyclone (TC) forecasting is critical for disaster warning and emergency response. Deep learning methods address computational challenges but often neglect physical relationships between TC attributes, resulting in predictions lacking physical consistency. To address this, we propose Phys-Diff, a physics-inspired latent diffusion model that disentangles latent features into task-specific components (trajectory, pressure, wind speed) and employs cross-task attention to introduce prior physics-inspired inductive biases, thereby embedding physically consistent dependencies among TC attributes. Phys-Diff integrates multimodal data including historical cyclone attributes, ERA5 reanalysis data, and FengWu forecast fields via a Transformer encoder-decoder architecture, further enhancing forecasting performance. Experiments demonstrate state-of-the-art performance on global and regional datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。