arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00521cs.LGcs.AI
收藏

Phys-Diff:一种基于物理的潜在扩散模型用于热带气旋预测

Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting

Lei Liu, Xiaoning Yu, Kang Chen, Jiahui Huang, Tengyuan Liu, Hongwei Zhao, Bin Li

AI总结:

Phys-Diff通过结合物理启发的归纳偏置和多模态数据整合,提升热带气旋预测的物理一致性与性能

摘要:

热带气旋(TC)预测对于灾难预警和应急响应至关重要。深度学习方法解决了计算挑战,但往往忽视TC属性之间的物理关系,导致预测缺乏物理一致性。为此,我们提出了Phys-Diff,一种基于物理的潜在扩散模型,将潜在特征分解为任务特定的组件(轨迹、压力、风速),并采用跨任务注意力机制引入先验物理启发的归纳偏置,从而在TC属性之间嵌入物理一致的依赖关系。Phys-Diff通过Transformer编码器-解码器架构整合多模态数据,包括历史气旋属性、ERA5再分析数据和风王预测场,进一步提升预测性能。实验表明,Phys-Diff在全局和区域数据集上均取得最佳性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑