Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA)

Rezzy Eko Caraka, Sakhinah Abu Bakar, Muhammad Tahmid

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Rainfall variation in the tropics is caused by several factors, such as: geographic, topographical, and orographic. Therefore, the importance of rainfall analysis is needed to know the factors also local characteristics that affect fluctuations in daily rainfall / monthly in each particular area. Rainfall is one element of weather that has a vital role in various sectors in Indonesia. In the agriculture sector, rainfall prediction is used to know the schedule prediction of cropping pattern to optimize food crop production result. In the land, sea and air transport sector, the weather factor that rainfall has a role in the level of safety. In this paper, we used daily rainfall data in Manado, North Sulawesi province in January 2017-December 2017. In short, we combined of SARIMA, and Localized Multi Kernel Support Vector Regression (LMKL SVR) with linear kernel and polynomial kernel reached accuracy model R2 98.76%. On the one hand, after obtained rainfall prediction, we compared with actual rainfall data in January 2018 -February 2018 (59 data). Mainly, Rainfall is difficult to predict even though the model obtained has good accuracy. Still, after validation data forecast and actual data, there is a very far different with RMSE amount 24.43 because the data climate is very dynamic also there are variables that need to be analyzed in building prediction model of rainfall

Original languageEnglish
Title of host publication2018 UKM FST Postgraduate Colloquium
Subtitle of host publicationProceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium
EditorsNoor Hayati Ahmad Rasol, Kamarulzaman Ibrahim, Siti Aishah Hasbullah, Mohammad Hafizuddin Hj. Jumali, Nazlina Ibrahim, Marlia Mohd Hanafiah, Mohd Talib Latif
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735418431
DOIs
Publication statusPublished - 27 Jun 2019
Event2018 UKM FST Postgraduate Colloquium - Selangor, Malaysia
Duration: 4 Apr 20186 Apr 2018

Publication series

NameAIP Conference Proceedings
Volume2111
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference2018 UKM FST Postgraduate Colloquium
CountryMalaysia
CitySelangor
Period4/4/186/4/18

Fingerprint

forecasting
regression analysis
rain
rainfall
sectors
predictions
seeds
weather
Indonesia
agriculture
crops
prediction
schedules
tropical regions
food
climate
meteorological data
safety
polynomials
land transportation

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics
  • Ecology
  • Plant Science
  • Physics and Astronomy(all)
  • Nature and Landscape Conservation

Cite this

Caraka, R. E., Abu Bakar, S., & Tahmid, M. (2019). Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA). In N. H. A. Rasol, K. Ibrahim, S. A. Hasbullah, M. H. H. Jumali, N. Ibrahim, M. M. Hanafiah, & M. T. Latif (Eds.), 2018 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium [020014] (AIP Conference Proceedings; Vol. 2111). American Institute of Physics Inc.. https://doi.org/10.1063/1.5111221

Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA). / Caraka, Rezzy Eko; Abu Bakar, Sakhinah; Tahmid, Muhammad.

2018 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium. ed. / Noor Hayati Ahmad Rasol; Kamarulzaman Ibrahim; Siti Aishah Hasbullah; Mohammad Hafizuddin Hj. Jumali; Nazlina Ibrahim; Marlia Mohd Hanafiah; Mohd Talib Latif. American Institute of Physics Inc., 2019. 020014 (AIP Conference Proceedings; Vol. 2111).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Caraka, RE, Abu Bakar, S & Tahmid, M 2019, Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA). in NHA Rasol, K Ibrahim, SA Hasbullah, MHH Jumali, N Ibrahim, MM Hanafiah & MT Latif (eds), 2018 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium., 020014, AIP Conference Proceedings, vol. 2111, American Institute of Physics Inc., 2018 UKM FST Postgraduate Colloquium, Selangor, Malaysia, 4/4/18. https://doi.org/10.1063/1.5111221
Caraka RE, Abu Bakar S, Tahmid M. Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA). In Rasol NHA, Ibrahim K, Hasbullah SA, Jumali MHH, Ibrahim N, Hanafiah MM, Latif MT, editors, 2018 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium. American Institute of Physics Inc. 2019. 020014. (AIP Conference Proceedings). https://doi.org/10.1063/1.5111221
Caraka, Rezzy Eko ; Abu Bakar, Sakhinah ; Tahmid, Muhammad. / Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA). 2018 UKM FST Postgraduate Colloquium: Proceedings of the Universiti Kebangsaan Malaysia, Faculty of Science and Technology 2018 Postgraduate Colloquium. editor / Noor Hayati Ahmad Rasol ; Kamarulzaman Ibrahim ; Siti Aishah Hasbullah ; Mohammad Hafizuddin Hj. Jumali ; Nazlina Ibrahim ; Marlia Mohd Hanafiah ; Mohd Talib Latif. American Institute of Physics Inc., 2019. (AIP Conference Proceedings).
@inproceedings{c072be7be21647ab9ba42176b20a03ce,
title = "Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA)",
abstract = "Rainfall variation in the tropics is caused by several factors, such as: geographic, topographical, and orographic. Therefore, the importance of rainfall analysis is needed to know the factors also local characteristics that affect fluctuations in daily rainfall / monthly in each particular area. Rainfall is one element of weather that has a vital role in various sectors in Indonesia. In the agriculture sector, rainfall prediction is used to know the schedule prediction of cropping pattern to optimize food crop production result. In the land, sea and air transport sector, the weather factor that rainfall has a role in the level of safety. In this paper, we used daily rainfall data in Manado, North Sulawesi province in January 2017-December 2017. In short, we combined of SARIMA, and Localized Multi Kernel Support Vector Regression (LMKL SVR) with linear kernel and polynomial kernel reached accuracy model R2 98.76{\%}. On the one hand, after obtained rainfall prediction, we compared with actual rainfall data in January 2018 -February 2018 (59 data). Mainly, Rainfall is difficult to predict even though the model obtained has good accuracy. Still, after validation data forecast and actual data, there is a very far different with RMSE amount 24.43 because the data climate is very dynamic also there are variables that need to be analyzed in building prediction model of rainfall",
author = "Caraka, {Rezzy Eko} and {Abu Bakar}, Sakhinah and Muhammad Tahmid",
year = "2019",
month = "6",
day = "27",
doi = "10.1063/1.5111221",
language = "English",
series = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",
editor = "Rasol, {Noor Hayati Ahmad} and Kamarulzaman Ibrahim and Hasbullah, {Siti Aishah} and Jumali, {Mohammad Hafizuddin Hj.} and Nazlina Ibrahim and Hanafiah, {Marlia Mohd} and Latif, {Mohd Talib}",
booktitle = "2018 UKM FST Postgraduate Colloquium",

}

TY - GEN

T1 - Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA)

AU - Caraka, Rezzy Eko

AU - Abu Bakar, Sakhinah

AU - Tahmid, Muhammad

PY - 2019/6/27

Y1 - 2019/6/27

N2 - Rainfall variation in the tropics is caused by several factors, such as: geographic, topographical, and orographic. Therefore, the importance of rainfall analysis is needed to know the factors also local characteristics that affect fluctuations in daily rainfall / monthly in each particular area. Rainfall is one element of weather that has a vital role in various sectors in Indonesia. In the agriculture sector, rainfall prediction is used to know the schedule prediction of cropping pattern to optimize food crop production result. In the land, sea and air transport sector, the weather factor that rainfall has a role in the level of safety. In this paper, we used daily rainfall data in Manado, North Sulawesi province in January 2017-December 2017. In short, we combined of SARIMA, and Localized Multi Kernel Support Vector Regression (LMKL SVR) with linear kernel and polynomial kernel reached accuracy model R2 98.76%. On the one hand, after obtained rainfall prediction, we compared with actual rainfall data in January 2018 -February 2018 (59 data). Mainly, Rainfall is difficult to predict even though the model obtained has good accuracy. Still, after validation data forecast and actual data, there is a very far different with RMSE amount 24.43 because the data climate is very dynamic also there are variables that need to be analyzed in building prediction model of rainfall

AB - Rainfall variation in the tropics is caused by several factors, such as: geographic, topographical, and orographic. Therefore, the importance of rainfall analysis is needed to know the factors also local characteristics that affect fluctuations in daily rainfall / monthly in each particular area. Rainfall is one element of weather that has a vital role in various sectors in Indonesia. In the agriculture sector, rainfall prediction is used to know the schedule prediction of cropping pattern to optimize food crop production result. In the land, sea and air transport sector, the weather factor that rainfall has a role in the level of safety. In this paper, we used daily rainfall data in Manado, North Sulawesi province in January 2017-December 2017. In short, we combined of SARIMA, and Localized Multi Kernel Support Vector Regression (LMKL SVR) with linear kernel and polynomial kernel reached accuracy model R2 98.76%. On the one hand, after obtained rainfall prediction, we compared with actual rainfall data in January 2018 -February 2018 (59 data). Mainly, Rainfall is difficult to predict even though the model obtained has good accuracy. Still, after validation data forecast and actual data, there is a very far different with RMSE amount 24.43 because the data climate is very dynamic also there are variables that need to be analyzed in building prediction model of rainfall

UR - http://www.scopus.com/inward/record.url?scp=85068446803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068446803&partnerID=8YFLogxK

U2 - 10.1063/1.5111221

DO - 10.1063/1.5111221

M3 - Conference contribution

AN - SCOPUS:85068446803

T3 - AIP Conference Proceedings

BT - 2018 UKM FST Postgraduate Colloquium

A2 - Rasol, Noor Hayati Ahmad

A2 - Ibrahim, Kamarulzaman

A2 - Hasbullah, Siti Aishah

A2 - Jumali, Mohammad Hafizuddin Hj.

A2 - Ibrahim, Nazlina

A2 - Hanafiah, Marlia Mohd

A2 - Latif, Mohd Talib

PB - American Institute of Physics Inc.

ER -