IEICE TRANSACTIONS on Information
A Novel Method for Lightning Prediction by Direct Electric Field Measurements at the Ground Using Recurrent Neural Network
Summary :
A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.9 pp.1624-1628
- Publication Date
- 2022/09/01
- Publicized
- 2022/06/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDL8026
- Type of Manuscript
- LETTER
- Category
- Artificial Intelligence, Data Mining
Authors
Masamoto FUKAWA
Tokyo Institute of Technology
Xiaoqi DENG
Tokyo Institute of Technology
Shinya IMAI
Tokyo Institute of Technology
Taiga HORIGUCHI
Tokyo Institute of Technology
Ryo ONO
Tokyo Institute of Technology
Ikumi RACHI
Tokyo Institute of Technology
Sihan A
Tokyo Institute of Technology
Kazuma SHINOMURA
OTOWA ELECTRIC CO, LTD.
Shunsuke NIWA
OTOWA ELECTRIC CO, LTD.
Takeshi KUDO
OTOWA ELECTRIC CO, LTD.
Hiroyuki ITO
Tokyo Institute of Technology
Hitoshi WAKABAYASHI
Tokyo Institute of Technology
Yoshihiro MIYAKE
Tokyo Institute of Technology
Atsushi HORI
Tokyo Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Masamoto FUKAWA, Xiaoqi DENG, Shinya IMAI, Taiga HORIGUCHI, Ryo ONO, Ikumi RACHI, Sihan A, Kazuma SHINOMURA, Shunsuke NIWA, Takeshi KUDO, Hiroyuki ITO, Hitoshi WAKABAYASHI, Yoshihiro MIYAKE, Atsushi HORI, "A Novel Method for Lightning Prediction by Direct Electric Field Measurements at the Ground Using Recurrent Neural Network" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 9, pp. 1624-1628, September 2022, doi: 10.1587/transinf.2022EDL8026.
Abstract: A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8026/_p
Copy
@ARTICLE{e105-d_9_1624,
author={Masamoto FUKAWA, Xiaoqi DENG, Shinya IMAI, Taiga HORIGUCHI, Ryo ONO, Ikumi RACHI, Sihan A, Kazuma SHINOMURA, Shunsuke NIWA, Takeshi KUDO, Hiroyuki ITO, Hitoshi WAKABAYASHI, Yoshihiro MIYAKE, Atsushi HORI, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Method for Lightning Prediction by Direct Electric Field Measurements at the Ground Using Recurrent Neural Network},
year={2022},
volume={E105-D},
number={9},
pages={1624-1628},
abstract={A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.},
keywords={},
doi={10.1587/transinf.2022EDL8026},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - A Novel Method for Lightning Prediction by Direct Electric Field Measurements at the Ground Using Recurrent Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1624
EP - 1628
AU - Masamoto FUKAWA
AU - Xiaoqi DENG
AU - Shinya IMAI
AU - Taiga HORIGUCHI
AU - Ryo ONO
AU - Ikumi RACHI
AU - Sihan A
AU - Kazuma SHINOMURA
AU - Shunsuke NIWA
AU - Takeshi KUDO
AU - Hiroyuki ITO
AU - Hitoshi WAKABAYASHI
AU - Yoshihiro MIYAKE
AU - Atsushi HORI
PY - 2022
DO - 10.1587/transinf.2022EDL8026
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2022
AB - A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.
ER -
English
