IMPLEMENTATION OF BACKPROPAGATION AND HYBRID ARIMA-NN METHODS IN PREDICTING ACCURACY LEVELS OF RAINFALL IN MAKASSAR CITY
Abstract
Hybrid ARIMA-NN is a combined approach of the ARIMA model used to capture linear patterns in time series data and Artificial Neural Networks (ANN) to handle non-linear and stochastic patterns. Using a gradient descent algorithm, backpropagation adjusts synaptic weights based on the error between the network's prediction and actual training data values. In this study, a comparison was made between the Backpropagation method and Hybrid ARIMA-NN in forecasting rainfall in Makassar City. Rainfall data in Makassar City uses data from the rainfall measuring station at the Paotere Maritime Meteorological Station in Makassar. The activation functions used are ReLU and Leaky ReLU with epoch parameters set at 350, and learning rates of 0.01, 0.001, 0.0001, and 0.00001. The two best methods selected for further evaluation are Backpropagation with architecture 12-32-16-8-1 and Hybrid ARIMA-NN (ARIMA [4,0,1]-NN 12-256-128-64-1). The ARIMA model (4,0,1) with AIC values of 1303.4 and RMSE 162,369 is the best compared to other models, which aligns with the advantages of backpropagation architecture. The results showed that the Backpropagation method excelled with an RMSE value of 137.320 or 0.1149, indicating high accuracy in forecasting changes in seasonal trends and patterns. Hybrid ARIMA-NN gives good results with RMSE 145.834, as residues contain better nonlinearity compared to ARIMA models (4,0,1), although it shows a slightly higher error rate compared to Backpropagation.
Downloads
References
E. Alpaydin, Neural Networks and Deep Learning. 2021. doi: 10.7551/mitpress/13811.003.0007.
H. R. Vega-Carrillo, V. M. Hernández-Dávila, E. Manzanares-Acuña, E. Gallego, A. Lorente, and M. P. Iñiguez, “Artificial neural networks technology for neutron spectrometry and dosimetry,” Radiat. Prot. Dosimetry, vol. 126, no. 1–4, pp. 408–412, 2007, doi: 10.1093/rpd/ncm084.
Y. Chauvin, D. E. Rumelhart, R. Durbin, and R. Golden, “Backpropagation: The Basic Theory,” Backpropagation Theory, Archit. Appl., no. 1995, pp. 0–34, 1995.
B. J. Wythoff, “Backpropagation neural networks. A tutorial,” Chemom. Intell. Lab. Syst., vol. 18, no. 2, pp. 115–155, 1993, doi: 10.1016/0169-7439(93)80052-J.
N. Sadeghi Gargari, H. Akbari, and R. Panahi, “Forecasting Short-term Container Vessel Traffic Volume Using Hybrid ARIMA-NN Model,” Int. J. Coast. offshore Eng., vol. 3, no. 3, pp. 47–52, 2019, doi: 10.29252/ijcoe.3.3.47.
S. Ayub and Y. Z. Jafri, “Comparative Study of an ANN-ARIMA Hybrid Model for Predicting Karachi Stock Price,” vol. 10, no. 1, pp. 1–9, 2020, doi: 10.5923/j.ajms.20201001.01.
D. Susilokarti, S. S. Arif, S. Susanto, and L. Sutiarso, “Studi Komparasi Prediksi Curah Hujan Metode Fast Fourier Transformation (Fft), Autoregressive Integrated Moving Average (Arima) Dan Artificial Neural Network (Ann),” J. Agritech, vol. 35, no. 02, p. 241, 2015, doi: 10.22146/agritech.9412.
Y. Susanto and B. S. S. Ulama, “Pemodelan Curah Hujan dengan Pendekatan Model ARIMA , Feed Forward Neural Network dan Hybrid (ARIMA-NN) di Banyuwangi,” J. Sains dan Seni ITS, vol. 5, no. 2, p. D-145-D-150, 2016, [Online]. Available: http://ejurnal.its.ac.id/index.php/sains_seni/article/viewFile/16409/3032
Wahyu ngestisari, “The Perbandingan Metode ARIMA dan Jaringan Syaraf Tiruan untuk Peramalan Harga Beras,” Indones. J. Data Sci., vol. 1, no. 3, pp. 96–107, 2020, doi: 10.33096/ijodas.v1i3.18.
D. Pratiwi and M. Hadijati, “Inflation modeling in Indonesia using hybrid autoregressive integrated moving average (ARIMA)-neural network (NN),” IOP Conf. Ser. Mater. Sci. Eng., vol. 1115, no. 1, p. 012058, 2021, doi: 10.1088/1757-899x/1115/1/012058.
A. A. Gifari, Misbahuddin, and Made Sutha Yadnya, “Penggunaan Jaringan Syaraf Tiruan Metode Backpropagation Untuk Prediksi Curah Hujan Berbasis Website,” Dielektrika, vol. 2, no. 2086–9487, pp. 2–2, 2020.
K. Naveena, S. Singh, S. Rathod, and A. Singh, “Hybrid ARIMA-ANN Modelling for Forecasting the Price of Robusta Coffee in India,” Int. J. Curr. Microbiol. Appl. Sci., vol. 6, no. 7, pp. 1721–1726, 2017, doi: 10.20546/ijcmas.2017.607.207.
I. P. Sutawinaya, I. N. Gede, A. Astawa, N. Kadek, and D. Hariyanti, “Perbandingan Metode Jaringan Saraf Tiruan Pada Peramalan Curah Hujan,” J. Log., vol. 17, no. 2, pp. 92–97, 2017.
S. Kasus et al., “Peramalan Curah Hujan Dengan Pendekatan Seasonal Autoregressive Integrated Moving Average ( Sarima ) Rainfall Forecasting Using Seasonal Autoregressive Integrated Moving Average Model ( Sarima ),” vol. 11, pp. 63–74, 2017.
Y. Andrian and M. R. Wayahdi, “Analisis Algoritma Inisialisasi Nguyen-Widrow Pada Proses Prediksi Curah Hujan Kota Medan Menggunakan Metode Backpropagation Neural Network,” Semin. Nas. Inform. 2014, pp. 57–63, 2014, [Online]. Available: http://e-journal.potensi-utama.ac.id/ojs/index.php/SNIf/article/view/171/118
D. Learning, Charu C. Aggarwal A Textbook 123 Neural Networks and Deep Learning. [Online]. Available: https://doi.org/10.1007/978-3-319-94463-0
I. Guntoro, D. M. Midyanti, and R. Hidayati, “Penerapan Dropout Pada Jaringan Saraf Tiruan Backpropagation Dalam Mengklasifikasi Tingkat Fine Fuel Moisture Code (Ffmc) Untuk Kebakaran Hutan Dan Lahan,” J. Komput. dan Apl., vol. 10, no. 01, pp. 114–123, 2022.
R. Ayu, R. Gernowo, D. Fisika, F. Sains, U. Diponegoro, and S. E-, “Metode Autoregressive Integrated Movingaverage (Arima) Dan Metode Adaptive Neuro Fuzzy Inference System (Anfis) Dalam Analisis Curah Hujan,” Berk. Fis., vol. 22, no. 1, pp. 41–48, 2019.
C. Twumasi and J. Twumasi, “Machine learning algorithms for forecasting and backcasting blood demand data with missing values and outliers: A study of Tema General Hospital of Ghana,” Int. J. Forecast., vol. 38, no. 3, pp. 1258–1277, 2022, doi: 10.1016/j.ijforecast.2021.10.008.
B. A. Safitri, A. Iriany, and N. W. S. Wardhani, “Perbandingan Akurasi Peramalan Curah Hujan dengan menggunakan ARIMA, Hybrid ARIMA-NN, dan FFNN di Kabupaten Malang,” Semin. Nas. Off. Stat., vol. 2021, no. 1, pp. 245–253, 2021, doi: 10.34123/semnasoffstat.v2021i1.853.
I. K. Hasan and Ismail Djakaria, “Perbandingan Model Hybrid ARIMA-NN dan Hybrid ARIMA-GARCH untuk Peramalan Data Nilai Tukar Petani di Provinsi Gorontalo,” J. Stat. dan Apl., vol. 5, no. 2, pp. 155–165, 2021, doi: 10.21009/jsa.05204.
W. Estiningtyas, F. Ramdhani, and E. Aldrian, “Analisis Korelasi Curah Hujan Dan Suhu Permukaan Laut Wilayah Indonesia, Serta Implikasinya Untuk Prakiraan Curah Hujan (Studi Kasus Kabupaten Cilacap),” J. Agromet Indones., vol. 21, no. September, pp. 46–60, 2007.
R. L. Fraiha Lopes, S. G. C. Fraiha, H. S. Gomes, V. D. Lima, and G. P. S. Cavalcante, “Application of Hybrid ARIMA and Artificial Neural Network Modelling for Electromagnetic Propagation: An Alternative to the Least Squares Method and ITU Recommendation P.1546-5 for Amazon Urbanized Cities,” Int. J. Antennas Propag., vol. 2020, 2020, doi: 10.1155/2020/8494185.
Copyright (c) 2024 Hisyam Ihsan, Irwan Irwan, Andi Illa Erviani Nensi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
1.gif)
