Toward an Interpretable CNN Model for the Classification of Lightning‐Produced VLF/LF Signals

Author:

Xiao Lilang1ORCID,Chen Weijiang2,Wang Yu34ORCID,Bian Kai2,Fu Zhong5,Xiang Nianwen6,He Hengxin1ORCID,Cheng Yang5

Affiliation:

1. State Key Laboratory of Advanced Electromagnetic Engineering and Technology HUST Wuhan People's Republic of China

2. State Grid Corporation of China Beijing People's Republic of China

3. State Grid Electric Power Research Institute Nanjing People's Republic of China

4. Wuhan NARI Co., Ltd of State Grid Electric Power Research Institute Wuhan People's Republic of China

5. Electric Power Research Institute State Grid Anhui Electric Power Company Hefei People's Republic of China

6. School of Electrical Engineering and Automation Hefei University of Technology Hefei People's Republic of China

Abstract

AbstractAn interpretable convolutional neural network model is proposed for the classification of very low frequency and low frequency lightning electric field waveforms. This model adopts multi‐scale convolutional kernels and shortcut connections to enhance the ability of lightning waveform classification. Based on the data recorded from five provinces in China, the proposed model achieves an accuracy of 98.56% for a four‐type classification task including return strokes, the intra‐cloud lightning, preliminary breakdown, and narrow bipolar events. The proposed model is validated with another open‐source data set from Argentina with an accuracy of 98.45%, which shows good robustness. To ensure the classification, the features learned by the model are visualized. The class activation mapping (CAM) method is adopted to visualize the class‐specific contribution of different waveform parts by using the feature maps of the final convolutional layer. It is highlighted by the CAM method that the proposed model focuses on waveform parts that align with those areas of interests identified by human experts. The high‐contribution waveform parts are furtherly analyzed, which indicate that the proposed model possesses the capability to associate waveform features with the corresponding lightning discharge processes.

Funder

State Grid Corporation of China

Publisher

American Geophysical Union (AGU)

Subject

Space and Planetary Science,Earth and Planetary Sciences (miscellaneous),Atmospheric Science,Geophysics

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3