Residual Attention-BiConvLSTM:一种新的全球电离层TEC map预测模型  

Residual Attention-BiConvLSTM:A new global ionospheric TEC map prediction model

作　　者：王浩然 刘海军 袁静 乐会军[3] 李良超 陈羿 单维锋 袁国铭 WANG HaoRan;LIU HaiJun;YUAN Jing;LE HuiJun;LI LiangChao;CHEN Yi;SHAN WeiFeng;YUAN GuoMing(School of Emergency Management,Institute of Disaster Prevention,Langfang Hebei 065201,China;School of Information Engineering,Institute of Disaster Prevention,Langfang Hebei 065201,China;Key Laboratory of Earth and Planetary Physics,Institute of Geology and Geophysics,Chinese Academy of Sciences,Beijing 100029,China)

机构地区：[1]防灾科技学院应急管理学院,河北廊坊065201 [2]防灾科技学院信息工程学院,河北廊坊065201 [3]中国科学院地质与地球物理研究所地球与行星物理院重点实验室,北京100029

出　　处：《地球物理学报》2025年第2期413-430,共18页Chinese Journal of Geophysics

基　　金：河北省自然科学基金(D2023512004)资助.

摘　　要：电离层总电子含量(TEC)预测对提高全球卫星导航系统(GNSS)的精度具有重要意义.现有的TEC map预测模型主要通过顺序堆叠时空特征提取单元来实现.这种模型搭建方法会因多个卷积层顺序堆叠而损失细粒度的TEC map的空间特征,导致模型精度不够;还会由于多层堆叠导致梯度消失或梯度爆炸问题.本文借鉴残差注意力(Residual Attention)的思想,在TEC map预测模型中增加了残差注意力模块,提出了Residual Attention-BiConvLSTM模型.该模型中的残差注意力模块能同时提取粗、细粒度空间特征,并对其进行加权.本文在全球TEC map数据上与ConvLSTM、ConvGRU、ED-ConvLSTM和C1PG进行了对比实验.实验结果表明,本文所提出的Residual Attention-BiConvLSTM模型的RMSE、MAE、MAPE和R^(2)在太阳活动高年和年均优于对比模型.本文还在一次磁暴事件中对比了5种模型的预测效果.实验结果表明,大磁暴发生时,本文模型与C1PG相近,优于其他3种对比模型.本文的研究工作为电离层map预测模型搭建提供一个新思路.The prediction of total ionospheric electron content(TEC)is of great significance for improving the accuracy of global satellite navigation systems(GNSS).The existing TEC map prediction models are mainly structured by sequentially stacking spatiotemporal feature extraction units,which will lose fine-grained spatial features of TEC maps due to the sequential stacking of multiple convolutional layers,resulting in insufficient model accuracy;It may also cause gradient vanishing or exploding problems due to multi-layer stacking.Inspired by the idea of residual attention network,we add a residual attention module to the TEC map prediction model,proposing the Residual Attention-BiConvLSTM model.The residual attention module in our model can simultaneously extract coarse and fine-grained spatial features and weight them.This article conducted comparative experiments with ConvLSTM,ConvGRU,ED-ConvLSTM,and C1PG on global TEC maps.The experimental results showed that the RMSE,MAE,MAPE and R^(2) of our Residual Attention-BiConvLSTM are superior to the comparison models in both high and low solar activity years.This article also compared the predictive performance of five models in a magnetic storm event,and the experimental results show that during a large magnetic storm,the model proposed in this paper is similar to C1PG and superior to the other three comparative models.The research work of this article provides a new approach for building ionospheric map prediction models.

关 键 词：电离层TEC map预测 残差注意力模块 Residual Attention-BiConvLSTM 时空预测模型 

分 类 号：P352[天文地球—空间物理学]