A Multiscale Attention Network for the Classification of Lightning Safety Risk Warnings

Author:

Luo Zhiyong1,Yin Qiyuan2,Xia Min3,Li Xiang4

Affiliation:

1. Zhongshan Meteorological Bureau

2. China Meteorological Administration

3. Nanjing University of Information Science and Technology

4. Chengdu University of Information Technology

Abstract

Abstract

In order to meet practical business application requirements, this study considered the physical characteristics of lightning, combined with the risk of lightning disasters and disaster responses, to develop a precise classification model for lightning safety risk warnings at target points based on the the multi-scale attention residual network. By analyzing 1404 sets of thunderstorm data from four warning levels in Guangdong region, we trained convolutional neural networks, support vector machines, random forests, extreme gradient enhancement networks, as well as the multi-scale attention residual network (MSA) constructed by our research institute. The results showed that the multi-scale attention residual network has interpretability for lightning safety risk warning, (1) This model proposes an attention mechanism to fuse different features, obtain the importance distribution of different features, and increase the number of neural network layers to extract deeper features. (2) This lightning safety risk warning model is the most reliable among the five models, with an accuracy rate of 93%. (3) For the four-level classification model, it was found that the accuracy of the lightning safety risk warning models based on the MSA remained above 70% (77%), and also achieved the highest recall, lowest standard deviation, and lowest log loss.

Publisher

Springer Science and Business Media LLC

Reference26 articles.

1. Impacts of meteorological disaster on economic growth in China[J];Shi PJ;J Beijing Normal Univ (Natural Science),2016

2. Assessment of Climate and Environment Changes in China (I): Climate and environment changes in China and their projections[J];Jilan Q;Adv Clim Change Res,2006

3. Lightning fatalities in China, 2009–2018[J];Yin Q;J Agricultural Meteorol,2021

4. Review and progress of lightning research[J];Zhang YJ;J Appl Meteorological Sci,2006

5. Variability of lightning activity in south/southeast Asia during 1997–98 and 2002–03 El Nino/La Nina events[J];Kumar PR;Atmos Res,2012

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