ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation

Truong Vinh Le; Yuei An Liou

doi:10.1109/IET-ICETA56553.2022.9971544

ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

摘要

Estimation of tropical cyclones (TCs) intensity is crucial for disaster reduction and risk management. This study aims to estimate TC intensity using ensemble machine learning models. We utilized four Random Forest (RF) models to predict TC intensity. The input factors include TC's location, central pressure, distance to land, landfall in the next six-hour, storm speed, and storm direction, which are extracted from the International Best Track Archive for Climate Stewardship Version 4 (IBTrACS V4). This dataset was divided into four sub-datasets based on the ENSO phases (Neutral, El Niño, and La Niña). Inputs for the RF models were taken from each sub-dataset separately. Results show that central pressure has the greatest effect on TC intensity estimate with the maximal root mean square error (RMSE) of 4.92 knots (equivalent to 2.50 m/s) and accuracy of 94-96 %.

原文	???core.languages.en_GB???
主出版物標題	Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022
發行者	Institute of Electrical and Electronics Engineers Inc.
ISBN（電子）	9781665491389
DOIs	https://doi.org/10.1109/IET-ICETA56553.2022.9971544
出版狀態	已出版 - 2022
事件	2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022 - Changhua, Taiwan 持續時間: 14 10月 2022 → 16 10月 2022

出版系列

名字	Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022
國家/地區	Taiwan
城市	Changhua
期間	14/10/22 → 16/10/22

UN SDG

此研究成果有助於以下永續發展目標

存取文件

10.1109/IET-ICETA56553.2022.9971544

人工智慧架構的地球環境災害防減抗策略TWAI(湍)(1/2)
Chen, C.-C. (PI)
1/11/21 → 31/10/22
研究計畫: Research

引用此

Le, T. V., & Liou, Y. A. (2022). ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation. 於 Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022 (Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IET-ICETA56553.2022.9971544

Le, Truong Vinh ; Liou, Yuei An. / ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation. Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022).

@inproceedings{555831f4b5f648218c2a428b87a563ad,

title = "ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation",

abstract = "Estimation of tropical cyclones (TCs) intensity is crucial for disaster reduction and risk management. This study aims to estimate TC intensity using ensemble machine learning models. We utilized four Random Forest (RF) models to predict TC intensity. The input factors include TC's location, central pressure, distance to land, landfall in the next six-hour, storm speed, and storm direction, which are extracted from the International Best Track Archive for Climate Stewardship Version 4 (IBTrACS V4). This dataset was divided into four sub-datasets based on the ENSO phases (Neutral, El Ni{\~n}o, and La Ni{\~n}a). Inputs for the RF models were taken from each sub-dataset separately. Results show that central pressure has the greatest effect on TC intensity estimate with the maximal root mean square error (RMSE) of 4.92 knots (equivalent to 2.50 m/s) and accuracy of 94-96 %.",

keywords = "ENSO, NWP, machine learning, random forest, tropical cyclone",

author = "Le, {Truong Vinh} and Liou, {Yuei An}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022 ; Conference date: 14-10-2022 Through 16-10-2022",

year = "2022",

doi = "10.1109/IET-ICETA56553.2022.9971544",

language = "???core.languages.en_GB???",

series = "Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022",

}

Le, TV & Liou, YA 2022, ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation. 於 Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022. Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022, Institute of Electrical and Electronics Engineers Inc., 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022, Changhua, Taiwan, 14/10/22. https://doi.org/10.1109/IET-ICETA56553.2022.9971544

ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation. / Le, Truong Vinh; Liou, Yuei An.
Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022).

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

TY - GEN

T1 - ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation

AU - Le, Truong Vinh

AU - Liou, Yuei An

PY - 2022

Y1 - 2022

N2 - Estimation of tropical cyclones (TCs) intensity is crucial for disaster reduction and risk management. This study aims to estimate TC intensity using ensemble machine learning models. We utilized four Random Forest (RF) models to predict TC intensity. The input factors include TC's location, central pressure, distance to land, landfall in the next six-hour, storm speed, and storm direction, which are extracted from the International Best Track Archive for Climate Stewardship Version 4 (IBTrACS V4). This dataset was divided into four sub-datasets based on the ENSO phases (Neutral, El Niño, and La Niña). Inputs for the RF models were taken from each sub-dataset separately. Results show that central pressure has the greatest effect on TC intensity estimate with the maximal root mean square error (RMSE) of 4.92 knots (equivalent to 2.50 m/s) and accuracy of 94-96 %.

AB - Estimation of tropical cyclones (TCs) intensity is crucial for disaster reduction and risk management. This study aims to estimate TC intensity using ensemble machine learning models. We utilized four Random Forest (RF) models to predict TC intensity. The input factors include TC's location, central pressure, distance to land, landfall in the next six-hour, storm speed, and storm direction, which are extracted from the International Best Track Archive for Climate Stewardship Version 4 (IBTrACS V4). This dataset was divided into four sub-datasets based on the ENSO phases (Neutral, El Niño, and La Niña). Inputs for the RF models were taken from each sub-dataset separately. Results show that central pressure has the greatest effect on TC intensity estimate with the maximal root mean square error (RMSE) of 4.92 knots (equivalent to 2.50 m/s) and accuracy of 94-96 %.

KW - ENSO

KW - NWP

KW - machine learning

KW - random forest

KW - tropical cyclone

UR - http://www.scopus.com/inward/record.url?scp=85145358102&partnerID=8YFLogxK

U2 - 10.1109/IET-ICETA56553.2022.9971544

DO - 10.1109/IET-ICETA56553.2022.9971544

M3 - 會議論文篇章

AN - SCOPUS:85145358102

T3 - Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022

BT - Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022

Y2 - 14 October 2022 through 16 October 2022

ER -

Le TV, Liou YA. ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation. 於 Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Proceedings - 2022 IET International Conference on Engineering Technologies and Applications, IET-ICETA 2022). doi: 10.1109/IET-ICETA56553.2022.9971544

ENSO-based Ensemble Learning Approach for Tropical Cyclone Intensity Estimation

摘要

出版系列

???event.eventtypes.event.conference???

UN SDG

存取文件

指紋

專案

人工智慧架構的地球環境災害防減抗策略TWAI(湍)(1/2)

引用此