Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning

Fadil Ramadhani Darmastowo; Maulana Putra; Djati Handoko; Muhammad Syamsu Rosid

doi:10.1109/iSemantic59612.2023.10295305

Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning

Fadil Ramadhani Darmastowo
, Maulana Putra
, Djati Handoko
, Muhammad Syamsu Rosid

Department of Physics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

The equatorial region has high rainfall because it is located near the equator, where the sun produces very high energy throughout the year. This impacts biological habitats, the global water cycle, and people's everyday life. Accurate rainfall information is important for disaster mitigation, air resources management, and climate modeling. This study calculated estimated rainfall in an area with an equatorial rain pattern in Pontianak, Indonesia. The method applied is a comparison using four machine learning algorithms: Decision Tree, Random Forest, Adaptive Boosting, and Gradient Boosting. This comparison aims to get the estimated value of rainfall. The Decision Tree algorithm produces an accuracy value of RMSE of 0.693 and an R2 correlation of 0.449; Random Forest produces an RMSE of 0.642 and an R2 of 0.527; Adaptive Boosting produces an RMSE of 0.725 and R2 of 0.395, and Gradient Boosting produces RMSE of 0.561 and R2 of 0.638. It was concluded that the Gradient Boosting algorithm could provide the best rainfall estimation in Pontianak, West Kalimantan, Indonesia.

Original language	English
Title of host publication	2023 International Seminar on Application for Technology of Information and Communication
Subtitle of host publication	Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	266-270
Number of pages	5
ISBN (Electronic)	9798350339215
DOIs	https://doi.org/10.1109/iSemantic59612.2023.10295305
Publication status	Published - 2023
Event	2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023 - Semarang, Indonesia Duration: 16 Sept 2023 → 17 Sept 2023

Publication series

Name	2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023

Conference

Conference	2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023
Country/Territory	Indonesia
City	Semarang
Period	16/09/23 → 17/09/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

adaptive boosting
decision tree
gradient boosting
machine learning
rainfall
random forest

Access to Document

10.1109/iSemantic59612.2023.10295305

Cite this

Darmastowo, F. R., Putra, M., Handoko, D., & Rosid, M. S. (2023). Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning. In 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023 (pp. 266-270). (2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iSemantic59612.2023.10295305

Darmastowo, Fadil Ramadhani ; Putra, Maulana ; Handoko, Djati et al. / Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning. 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 266-270 (2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023).

@inproceedings{efb2589266d440d48aff603be6c82a10,

title = "Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning",

abstract = "The equatorial region has high rainfall because it is located near the equator, where the sun produces very high energy throughout the year. This impacts biological habitats, the global water cycle, and people's everyday life. Accurate rainfall information is important for disaster mitigation, air resources management, and climate modeling. This study calculated estimated rainfall in an area with an equatorial rain pattern in Pontianak, Indonesia. The method applied is a comparison using four machine learning algorithms: Decision Tree, Random Forest, Adaptive Boosting, and Gradient Boosting. This comparison aims to get the estimated value of rainfall. The Decision Tree algorithm produces an accuracy value of RMSE of 0.693 and an R2 correlation of 0.449; Random Forest produces an RMSE of 0.642 and an R2 of 0.527; Adaptive Boosting produces an RMSE of 0.725 and R2 of 0.395, and Gradient Boosting produces RMSE of 0.561 and R2 of 0.638. It was concluded that the Gradient Boosting algorithm could provide the best rainfall estimation in Pontianak, West Kalimantan, Indonesia.",

keywords = "adaptive boosting, decision tree, gradient boosting, machine learning, rainfall, random forest",

author = "Darmastowo, \{Fadil Ramadhani\} and Maulana Putra and Djati Handoko and Rosid, \{Muhammad Syamsu\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023 ; Conference date: 16-09-2023 Through 17-09-2023",

year = "2023",

doi = "10.1109/iSemantic59612.2023.10295305",

language = "English",

series = "2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023",

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

pages = "266--270",

booktitle = "2023 International Seminar on Application for Technology of Information and Communication",

address = "United States",

}

Darmastowo, FR, Putra, M, Handoko, D & Rosid, MS 2023, Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning. in 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023. 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023, Institute of Electrical and Electronics Engineers Inc., pp. 266-270, 2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023, Semarang, Indonesia, 16/09/23. https://doi.org/10.1109/iSemantic59612.2023.10295305

Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning. / Darmastowo, Fadil Ramadhani; Putra, Maulana; Handoko, Djati et al.
2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 266-270 (2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning

AU - Darmastowo, Fadil Ramadhani

AU - Putra, Maulana

AU - Handoko, Djati

AU - Rosid, Muhammad Syamsu

PY - 2023

Y1 - 2023

N2 - The equatorial region has high rainfall because it is located near the equator, where the sun produces very high energy throughout the year. This impacts biological habitats, the global water cycle, and people's everyday life. Accurate rainfall information is important for disaster mitigation, air resources management, and climate modeling. This study calculated estimated rainfall in an area with an equatorial rain pattern in Pontianak, Indonesia. The method applied is a comparison using four machine learning algorithms: Decision Tree, Random Forest, Adaptive Boosting, and Gradient Boosting. This comparison aims to get the estimated value of rainfall. The Decision Tree algorithm produces an accuracy value of RMSE of 0.693 and an R2 correlation of 0.449; Random Forest produces an RMSE of 0.642 and an R2 of 0.527; Adaptive Boosting produces an RMSE of 0.725 and R2 of 0.395, and Gradient Boosting produces RMSE of 0.561 and R2 of 0.638. It was concluded that the Gradient Boosting algorithm could provide the best rainfall estimation in Pontianak, West Kalimantan, Indonesia.

AB - The equatorial region has high rainfall because it is located near the equator, where the sun produces very high energy throughout the year. This impacts biological habitats, the global water cycle, and people's everyday life. Accurate rainfall information is important for disaster mitigation, air resources management, and climate modeling. This study calculated estimated rainfall in an area with an equatorial rain pattern in Pontianak, Indonesia. The method applied is a comparison using four machine learning algorithms: Decision Tree, Random Forest, Adaptive Boosting, and Gradient Boosting. This comparison aims to get the estimated value of rainfall. The Decision Tree algorithm produces an accuracy value of RMSE of 0.693 and an R2 correlation of 0.449; Random Forest produces an RMSE of 0.642 and an R2 of 0.527; Adaptive Boosting produces an RMSE of 0.725 and R2 of 0.395, and Gradient Boosting produces RMSE of 0.561 and R2 of 0.638. It was concluded that the Gradient Boosting algorithm could provide the best rainfall estimation in Pontianak, West Kalimantan, Indonesia.

KW - adaptive boosting

KW - decision tree

KW - gradient boosting

KW - machine learning

KW - rainfall

KW - random forest

UR - https://www.scopus.com/pages/publications/85178062109

U2 - 10.1109/iSemantic59612.2023.10295305

DO - 10.1109/iSemantic59612.2023.10295305

M3 - Conference contribution

AN - SCOPUS:85178062109

T3 - 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023

SP - 266

EP - 270

BT - 2023 International Seminar on Application for Technology of Information and Communication

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

Y2 - 16 September 2023 through 17 September 2023

ER -

Darmastowo FR, Putra M, Handoko D , Rosid MS. Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning. In 2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 266-270. (2023 International Seminar on Application for Technology of Information and Communication: Smart Technology Based on Industry 4.0: A New Way of Recovery from Global Pandemic and Global Economic Crisis, iSemantic 2023). doi: 10.1109/iSemantic59612.2023.10295305

Rainfall Estimation In Equatorial Region Using Weather Radar-Based Machine Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this