南京航空航天大学学报（英文版）2025，Vol.42Issue(6)：710-727,18.DOI:10.16356/j.1005-1120.2025.06.002
基于局部-全局特征的极光图像中局部地磁场分量建模
Local Geomagnetic Component Modeling of Auroral Images Based on Local-Global Feature
摘要
Abstract
Accurately predicting geomagnetic field is of great significance for space environment monitoring and space weather forecasting worldwide.This paper proposes a vision Transformer(ViT)hybrid model that leverages aurora images to predict local geomagnetic station component,breaking the spatial limitations of geomagnetic stations.Our method utilizes the ViT backbone model in combination with convolutional networks to capture both the large-scale spatial correlation and distinct local feature correlation between aurora images and geomagnetic station data.Essentially,the model comprises a visual geometry group(VGG)image feature extraction network,a ViT-based encoder network,and a regression prediction network.Our experimental findings indicate that global features of aurora images play a more substantial role in predicting geomagnetic data than local features.Specifically,the hybrid model achieves a 39.1%reduction in root mean square error compared to the VGG model,a 29.5%reduction compared to the ViT model and a 35.3%reduction relative to the residual network(ResNet)model.Moreover,the fitting accuracy of the model surpasses that of the VGG,ViT,and ResNet models by 2.14%1.58%,and 4.1%,respectively.关键词
紫外极光图像/地磁场预测/ViT混合模型Key words
ultraviolet aurora image/geomagnetic field prediction/vision Transformer(ViT)hybrid model分类
天文与地球科学引用本文复制引用
王博,张元舒,成巍,田馨沁,盛庆红,李俊,凌霄,刘祥..基于局部-全局特征的极光图像中局部地磁场分量建模[J].南京航空航天大学学报（英文版）,2025,42(6):710-727,18.基金项目
This work was supported by the Na-tional Natural Science Foundation of China(No.41471381) （No.41471381）
the General Project of Jiangsu Natural Science Foundation(No.BK20171410) （No.BK20171410）
and the Major Scientific and Technolog-ical Achievements Cultivation Fund of Nanjing University of Aeronautics and Astronautics(No.1011-XBD23002). （No.1011-XBD23002）
