Lightning disaster risk assessment based on machine learning

Yu Ye; Li Li; Tao Feng; Zelin Cai

doi:10.1117/12.3004347

25 September 2023 Lightning disaster risk assessment based on machine learning

Yu Ye, Li Li, Tao Feng, Zelin Cai

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 1278838 (2023) https://doi.org/10.1117/12.3004347
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

In recent years, lightning disasters have caused a large number of economic losses and casualties worldwide, posing a huge threat to human activities. How to effectively reduce the occurrence of lightning disasters has become a concern of researchers. Based on the original lightning data monitored by the lightning location system of Guangdong Province from 2010 to 2018, this paper analyzes the year-on-year change trend and distribution law of lightning to mine electric density in the the Pearl River Delta, and analyzes the change trend of probability distribution characteristics of lightning current amplitude in different years. Analyze meteorological data, analyze the annual change rules of the data, and visualize the data results. In the Inception convolutional neural network model established in this article, in the classification test set, the average probability of each sample being classified into each category under four rotational transformations is calculated, and the final score on the test set is 14.26446749. Compared with traditional ARIMA models, deep learning models can demonstrate good prediction performance. In particular, RNN-LSTM series models can be used as a conventional method for regional refined temperature prediction due to their strong series learning and prediction capabilities, providing guidance and suggestions for disaster prevention and mitigation work in power grids.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yu Ye, Li Li, Tao Feng, and Zelin Cai "Lightning disaster risk assessment based on machine learning", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 1278838 (25 September 2023); https://doi.org/10.1117/12.3004347

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Lightning

Deep learning

Clouds

Risk assessment

Data modeling

Education and training

Convolutional neural networks

Show All Keywords

Keywords/Phrases

Search In:

Publication Years