Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures

Brina Miftahurrohmah; Heri Kuswanto; Doni Setio Pambudi; Fatkhurokhman Fauzi; Felix Atmaja

doi:10.1016/j.procs.2024.03.049

Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures

Brina Miftahurrohmah^*, Heri Kuswanto, Doni Setio Pambudi, Fatkhurokhman Fauzi, Felix Atmaja

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Abstract

Climate information can be obtained from General circulation models (GCMs). However, this model has poor resolution, so it is necessary to do bias correction to overcome this problem. This study carried out a bias correction process using the Support Vector Regression (SVR) and Random Forest (RF) approaches. Bias correction is carried out for temperature in Indonesia using the BNU-ESM and MERRA-2 climate models, which act as observational data. The results show that the RF method (RMSE: 0.334; Correlation: 0.694; Standard Deviation: 0.582) is better than SVR (RMSE: 0.341; Correlation: 0.675; Standard Deviation: 0.588) in performing bias correction.

Original language	English
Pages (from-to)	637-644
Number of pages	8
Journal	Procedia Computer Science
Volume	234
DOIs	https://doi.org/10.1016/j.procs.2024.03.049
Publication status	Published - 2024
Event	7th Information Systems International Conference, ISICO 2023 - Washington, United States Duration: 26 Jul 2023 → 28 Jul 2023

Keywords

Bias Correction
Climate Change
Random Forest
Support Vector Machine

UN SDGs

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

Access to Document

10.1016/j.procs.2024.03.049

Cite this

@article{00b569e7fc1a4b6b8a252ea5fdc97592,

title = "Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures",

abstract = "Climate information can be obtained from General circulation models (GCMs). However, this model has poor resolution, so it is necessary to do bias correction to overcome this problem. This study carried out a bias correction process using the Support Vector Regression (SVR) and Random Forest (RF) approaches. Bias correction is carried out for temperature in Indonesia using the BNU-ESM and MERRA-2 climate models, which act as observational data. The results show that the RF method (RMSE: 0.334; Correlation: 0.694; Standard Deviation: 0.582) is better than SVR (RMSE: 0.341; Correlation: 0.675; Standard Deviation: 0.588) in performing bias correction.",

keywords = "Bias Correction, Climate Change, Random Forest, Support Vector Machine",

author = "Brina Miftahurrohmah and Heri Kuswanto and Pambudi, {Doni Setio} and Fatkhurokhman Fauzi and Felix Atmaja",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. Published by Elsevier B.V.; 7th Information Systems International Conference, ISICO 2023 ; Conference date: 26-07-2023 Through 28-07-2023",

year = "2024",

doi = "10.1016/j.procs.2024.03.049",

language = "English",

volume = "234",

pages = "637--644",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures

AU - Miftahurrohmah, Brina

AU - Kuswanto, Heri

AU - Pambudi, Doni Setio

AU - Fauzi, Fatkhurokhman

AU - Atmaja, Felix

PY - 2024

Y1 - 2024

N2 - Climate information can be obtained from General circulation models (GCMs). However, this model has poor resolution, so it is necessary to do bias correction to overcome this problem. This study carried out a bias correction process using the Support Vector Regression (SVR) and Random Forest (RF) approaches. Bias correction is carried out for temperature in Indonesia using the BNU-ESM and MERRA-2 climate models, which act as observational data. The results show that the RF method (RMSE: 0.334; Correlation: 0.694; Standard Deviation: 0.582) is better than SVR (RMSE: 0.341; Correlation: 0.675; Standard Deviation: 0.588) in performing bias correction.

AB - Climate information can be obtained from General circulation models (GCMs). However, this model has poor resolution, so it is necessary to do bias correction to overcome this problem. This study carried out a bias correction process using the Support Vector Regression (SVR) and Random Forest (RF) approaches. Bias correction is carried out for temperature in Indonesia using the BNU-ESM and MERRA-2 climate models, which act as observational data. The results show that the RF method (RMSE: 0.334; Correlation: 0.694; Standard Deviation: 0.582) is better than SVR (RMSE: 0.341; Correlation: 0.675; Standard Deviation: 0.588) in performing bias correction.

KW - Bias Correction

KW - Climate Change

KW - Random Forest

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=85193199932&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2024.03.049

DO - 10.1016/j.procs.2024.03.049

M3 - Conference article

AN - SCOPUS:85193199932

SN - 1877-0509

VL - 234

SP - 637

EP - 644

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 7th Information Systems International Conference, ISICO 2023

Y2 - 26 July 2023 through 28 July 2023

ER -

Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this