Open Access
ARTICLE
A Lightning Disaster Risk Assessment Model Based on SVM
Jianqiao Sheng1, Mengzhu Xu2, Jin Han3,*, Xingyan Deng2
1 Information and Communication Branch of State Grid Anhui Electric Power Co., Ltd., Hefei, 230041, China
2 Information and Communication Branch of State Grid Shanxi Electric Power Co., Ltd., Taiyuan, 030000, China
3 School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China
* Corresponding Author: Jin Han. Email:
Journal on Big Data 2021, 3(4), 183-190. https://doi.org/10.32604/jbd.2021.024892
Received 05 November 2021; Accepted 18 November 2021; Issue published 20 December 2021
Abstract
Lightning disaster risk assessment, as an intuitive method to reflect the
risk of regional lightning disasters, has aroused the research interest of many
researchers. Nowadays, there are many schemes for lightning disaster risk
assessment, but there are also some shortcomings, such as the resolution of the
assessment is not clear enough, the accuracy rate cannot be verified, and the weight
distribution has a strong subjective trend. This paper is guided by lightning disaster
data and combines lightning data, population data and GDP data. Through support
vector machine (SVM), it explores a way to combine artificial intelligence
algorithms with lightning disaster risk assessment. By fitting the lightning disaster
data, the weight distribution between the various impact factors is obtained. In the
experiment, the probability of lightning disaster is used to compare with the actual
occurrence of lightning disaster. It can be found that the disaster risk assessment
model proposed in this paper is more reasonable for the lightning risk. It has been
verified that the accuracy rate of the assessment model in this paper has reached
80.2%, which reflects the superiority of the model.
Keywords
Cite This Article
J. Sheng, M. Xu, J. Han and X. Deng, "A lightning disaster risk assessment model based on svm,"
Journal on Big Data, vol. 3, no.4, pp. 183–190, 2021. https://doi.org/10.32604/jbd.2021.024892