现代信息科技2025，Vol.9Issue(5)：51-55,61,6.DOI:10.19850/j.cnki.2096-4706.2025.05.009
基于3D卷积神经网络的热带气旋强度估测
Estimation of Tropical Cyclone Intensity Based on 3D Convolutional Neural Networks
王瑜 1孙凤远2
作者信息
- 1. 湖南现代物流职业技术学院,湖南 长沙 410131
- 2. 中国人民解放军75841部队,湖南 长沙 410000
- 折叠
摘要
Abstract
In the fields of meteorology and disaster management,the estimation of the TC intensity is of vital significance.With the advancement of technology,methods based on Deep Learning have demonstrated excellent performance in the estimation of the TC intensity,providing strong support for research and practice in related fields.Focusing on the spatiotemporal characteristics of TC,combined with Deep Learning technology,this paper proposes an innovative TC intensity estimation method namely the T3D-Net model.The MAE of this model on the TCIR dataset is 6.92 kt,and the RMSE is 9.14 kt.Compared with multiple existing methods for estimating the TC intensity,this method exhibits a certain competitiveness and superiority.关键词
热带气旋强度估测/3D卷积神经网络/TCIR/时空特征Key words
estimation of intensity of TC/3D Convolutional Neural Networks/TCIR/spatiotemporal feature分类
计算机与自动化引用本文复制引用
王瑜,孙凤远..基于3D卷积神经网络的热带气旋强度估测[J].现代信息科技,2025,9(5):51-55,61,6.
