Abstract
Daily rainfall forecasting is crucial in Indonesia. Because rainfall in Indonesia give rise to floods and landslides, affecting agriculture related to the adequacy of the amount of water on the ground, and affecting transportation, especially sea transportation and air transportation. Daily rainfall data in Indonesia is obtained from Meteorological, Climatological, and Geophysical Agency (BMKG Indonesia). In this research, the daily rainfall modeling was carried out using three methods, which are Autoregressive Integrated Moving Average (ARIMA), Neural Network (NN) and Long Short Term Memory (LSTM). Based on the results of the ARIMA analysis, the model is not good enough because there are no models that meet the assumption of ARIMA. Therefore, rainfall data is analyzed using machine learning methods. The Machine Learning methods that used in this research are NN and LSTM. Based on the results of NN and LSTM, it can be concluded that the NN model is better than the LSTM model. This is due to the root mean square error (RMSE) value on the NN model is smaller than the LSTM model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dinisari, M.C.: Ekonomi Bisnis, 16 July 2016. https://ekonomi.bisnis.com/read/20160716/98/566451/penerbangan-domestik-di-bali-terganggu-cuaca-buruk. Accessed 28 Aug 2021
Setiawan, B.: Nasional Tempo, Tempo, 3 February 2016. https://nasional.tempo.co/read/741852/hujan-deras-guyur-bali-bandara-ngurah-rai-sempat-ditutup. Accessed 28 Aug 2021
BMKG. Informasi Cuaca Aktual Bandara. Badan Meteorologi, Klimatologi dan Geofisika (BMKG), 3 September 2021. https://www.bmkg.go.id/cuaca/cuaca-aktual-bandara.bmkg. Accessed 3 Sept 2021
NV. Delapan Penerbangan Luar Negeri ke Bali Cancel, Nusa Bali, 2 December 2017. https://www.nusabali.com/berita/21894/delapan-penerbangan-luar-negeri-ke-bali-cancel. Accessed 3 Sept 2021
Setiawan, O.: Media Neliti, 22 April 2012. https://media.neliti.com/media/publications/95390-ID-analisis-variabilitas-curah-hujan-dan-su.pdf. Accessed 6 Sept 2021
Rai, B.N.: Dampak La Lina, BMKG Ngurah Rai, Denpasar (2020)
Ouma, Y.O., Cheruyot, R., Wachera, A.N.: Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia hydrologic basin. Compl. Intell. Syst. 8(1), 213–236 (2021)
Permai, S.D., Ohyver, M., Aziz, M.K.B.M.: Daily rainfall modeling using Neural Network. J. Phys. Conf. Seri. 1988(1), 012040 (2021)
Wu, X., et al.: The development of a hybrid wavelet-ARIMA-LSTM model for precipitation amounts and drought analysis. Atmosphere 12(1), 74 (2021)
Khan, M.M.R., Siddique, M.A.B., Sakib, S., Aziz, A., Tasawar, I.K., Hossain, Z.: Prediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks. IEEE, Turkey (2020)
MuttalebAlhashimi, S.A.: Prediction of monthly rainfall in Kirkuk using artificial neural network and time series models. J. Eng. Developm. 18(1), 129–143 (2014)
Ho, M.K., Darman, H., Musa, S.: Stock price prediction using ARIMA, neural network and LSTM models. IOP J. Phys.: Conf. Ser. Kuantan (2021)
Ma, Q.: Comparison of ARIMA, ANN and LSTM for stock price prediction. E3S Web Conf. 218, 01026 (2020)
Zhou, K., Wang, W.Y., Hu, T., Wu, C.H.: Comparison of time series forecasting based on statistical ARIMA Model and LSTM with attention mechanism. J. Phys.: Conf. Ser. 1631(1), 012141 (2020)
Salman, A.G., Heryadi, Y., Abdurahman, E., Suparta, W.: Weather forecasting using merged long short-term memory model (LSTM) and autoregressive integrated moving average (ARIMA) model. J. Comput. Sci. 14(7), 930–938 (2018)
Han, J.H.: Comparing Models for Time Series Analysis. Wharton Research Scholars, Philadelphia (2018)
BMKG. Data Online Pusat Database BMKG, BMKG, 31 Desember 2020. https://dataonline.bmkg.go.id/home. Accessed 1 Aug 2021
Kourentzes, N.: Cran R Project, 16 January 2019. https://cran.r-project.org/web/packages/nnfor/nnfor.pdf. Accessed 31 Aug 2021
Acknowledgments
This work is supported by Research and Technology Transfer Office, Bina Nusantara University as a part of Bina Nusantara University’s International Research Grant entitled Rainfall Modeling to Prevent Flooding in Jakarta using Machine Learning Method with contract number: No. 026/VR.RTT/IV/2020 and contract date: 6 April 2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Permai, S.D., Ho, M.K. (2022). Daily Rainfall Analysis in Indonesia Using ARIMA, Neural Network and LSTM. In: Bourennane, S., Kubicek, P. (eds) Geoinformatics and Data Analysis. ICGDA 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 143. Springer, Cham. https://doi.org/10.1007/978-3-031-08017-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-08017-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08016-6
Online ISBN: 978-3-031-08017-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)