###
计算机系统应用英文版:2024,33(9):28-37
本文二维码信息
码上扫一扫!
融合物理信息的热带气旋强度估计
(南京信息工程大学 计算机学院, 南京 210044)
Physical Factor Fusion for Tropical Cyclone Intensity Estimation
(School of Computer, Nanjing University of Information Science and Technology, Nanjing 210044, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 196次   下载 1521
Received:March 20, 2024    Revised:April 16, 2024
中文摘要: 热带气旋强度的精确估计是进行有效强度预测的基础工作, 对于灾害预报至关重要. 当前基于深度学习的热带气旋强度估计技术展现出了优越的性能, 但仍然存在着物理信息融合不足的问题. 因此, 本文基于深度学习框架, 提出一种融合物理信息的热带气旋强度估计模型(physical factor fusion for tropical cyclone intensity estimation, PF-TCIE), 来估计西北太平洋的热带气旋强度. PF-TCIE由多通道卫星云图学习分支和物理信息提取分支组成. 多通道卫星云图学习分支用于提取热带气旋云系特征, 物理信息提取分支用于提取物理因子特征, 来约束云系特征的学习. 本文数据选用葵花-8卫星资料和ERA-5再分析资料. 实验证明, 在引入多个通道后, 模型的RMSE误差较单通道降低了3.7%. 同时, 物理信息的引入使模型的误差进一步下降了8.5%. PF-TCIE的RMSE最终达到了4.83 m/s, 优于大部分深度学习方法.
Abstract:Accurate estimation of tropical cyclone intensity is the basis of effective intensity prediction and is crucial for disaster forecasting. Current tropical cyclone intensity estimation technology based on deep learning shows superior performance, but there is still a problem of insufficient physical information fusion. Therefore, based on the deep learning framework, this study proposes a physical factor fusion for tropical cyclone intensity estimation model (PF-TCIE) to estimate the intensity of tropical cyclones in the northwest Pacific. PF-TCIE consists of a multi-channel satellite cloud image learning branch and a physical information extraction branch. The multi-channel satellite cloud image learning branch is used to extract tropical cyclone cloud system features, and the physical information extraction branch is used to extract physical factor features to constrain the learning of cloud system features. The data used in this article include Himawari-8 satellite data and ERA-5 reanalysis data. Experimental results show that after introducing multiple channels, the root mean squared error (RMSE) of the model is reduced by 3.7% compared with a single channel. At the same time, the introduction of physical information further reduces the model error by 8.5%. The RMSE of PF-TCIE finally reaches 4.83 m/s, which is better than most deep learning methods.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(U21B2049)
引用文本:
丁嘉慕,乐璐辉,杭仁龙.融合物理信息的热带气旋强度估计.计算机系统应用,2024,33(9):28-37
DING Jia-Mu,YUE Lu-Hui,HANG Ren-Long.Physical Factor Fusion for Tropical Cyclone Intensity Estimation.COMPUTER SYSTEMS APPLICATIONS,2024,33(9):28-37