.png)
Prediksi El Nino Southern Oscillation (ENSO) Menggunakan Jaringan Saraf Tiruan (JST)-Backpropagation
Abstract
Penelitian ini bertujuan untuk memprediksi nilai indeks ENSO yaitu Sea Surface Temperature (Nino 1.2, Nino 3, Nino 3.4 dan Nino 4), Southern Oscillation Index (SOI) dan Multivariate ENSO Index versi 2 (MEI.v2) yang diambil dari tahun 1979-2018. Prediksi dilakukan dengan menggunakan metode JST-backpropagation dengan memvariasikan learning rate dan momentum. Semua indeks menghasilkan nilai akurasi prediksi ENSO yang tinggi, namun indeks Nino 4 merupakan indeks yang memiliki akurasi tertinggi karena nilai Mean Square Error (MSE) pelatihan dan pengujiannya yang relatif lebih kecil dibandingkan dengan indeks lainnya. Indeks Nino 4 memiliki MSE pelatihan 0,0072739 yang berhenti pada epoch ke-69 dan MSE pengujian 0,0085917 dengan akurasi prediksi 99,9989%. Hasil ini diperoleh dari arsitektur JST-backpropagation 12-10-1 dengan nilai learning rate 0,10 dan momentum 0,40. Prediksi ENSO berdasarkan indeks Nino 4 untuk tahun 2021 menunjukkan keadaan iklim dunia dalam kondisi normal.
This study aims to predict ENSO index using Sea Surface Temperature (Nino 1.2, Nino 3, Nino 3.4 and Nino 4 indexes), Southern Oscillation Index (SOI), and Multivariate ENSO Index version 2 (MEI.v2) during 1979 - 2018. The prediction was carried out using the ANN-backpropagation method by varying the learning rate and momentum. All indices produce high ENSO prediction accuracy values, but the Nino 4 index is the best one because the Mean Square Error (MSE) for training and testing steps are relatively smaller than other indexes. The Nino 4 index has a training MSE of 0.0072739 which stops at the 69th epoch and a testing MSE of 0.0085917 with a predictive accuracy of 99.9989%. These results were obtained from the back-propagation architecture ANN 12-10-1 with a learning rate of 0.10 and a momentum of 0.40. The prediction of ENSO in 2021 based on the Nino 4 index shows that the world climate condition is under normal conditions.
Full Text:
PDFReferences
Abbot, J. dan Marohasy, J., 2017, ‘Application Of Artificial Neural Networks To Forecasting Monthly Rainfall One Year In Advance For Locations Within The Murray Darling Basin, Australia’, Int. J. Sus. Dev. Plann, vol.12, no. 8, hal. 1282–1298.
Athoillah, I., Sibarani, R.M. dan Doloksaribu, D.E., 2017, ‘Analisi Spasial El Nino Kuat Tahun 2015 Dan La Nina Lemah Tahun 2016 (Pengaruhnya Terhadap Kelembapan, Angin Dan Curah Hujan Di Indonesia)’, Jurnal Sains & Teknologi Modifikasi Cuaca, vol. 18, no. 1, hal. 33–41.
Baawain, M.S., Nour, M.H., El-Din, A.G. dan El-Din, M.G., 2005, ‘El Nino Southern-Oscillation Prediction Using Selatanern Oscillation Index and Niño3 as Onset Indicators: Application of Artificial Neural Networks’, NRC Research Press, hal. 13–21.
Broni-Bedaiko, C., Katsriku, F.A., Unemi, T., Shinomiya, N., Jamal-Deen Abdulai, J., dan Atsumi, M., 2018, ‘El Nino-Southern Oscillation Forecasting Using Complex Networks Analysis of LSTM Neural Networks’, The Twenty-Third International Symposium on Artificial Life and Robotics, Bappu.
Dewi, S. M. dan Marzuki, 2020, ‘Analisis Pengaruh Pergeseran Lokasi ENSO terhadap Curah Hujan di Indonesia’, Jurnal Fisika Unand, vol. 9, no. 2, hal. 176 – 182.
Dijkstra, H.A., Petersik, P., Hernandez-Garcia, E., dan Lopez, C., 2019, ‘The Application of Machine Learning Techniques to Improve El Niño Prediction Skill’, Frontiers In Physics, vol.7, hal. 1-13.
Feng, Y., dan Tung, K., 2019, ‘ENSO Modulation: Real and Apparent; Implications for Decadal Prediction’, Springer-Verlag GmbH Germany.
Gers F.A., Schmidhuber J., Cummins F., 2000, ‘Learning to Forget: Continual Prediction with LSTM’, Neural Comput, vol. 12, no.10, hal: 2451–2471.
Hasieh, W.W., dan Tang, B., 1998, ‘Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography’, Bulletin of the American Meteorological Society.
Hutabarat, M.A.P., Julham, M. dan Wanto, A., 2018, ‘Penerapan Algoritma Backpropagation dalam Memprediksi Produksi Tanaman Padi Sawah Menurut Kabupaten/Kota di Sumatera Utara’, semanTIK, vol. 4, no. 1.
Li, J., Xie, S., Cook, E.R., Morales, M.S., Christie, D.A., Johnson, N.C., Chen, F., D’Arrigo, R., Fowler, A.M., Gou, X., dan Fang, K., 2013, ‘El Nino Modulations Over The Past Seven Centuries’, Nature Climate Change, vol. 3, hal.822–826.
Ludescher, J., Gozolchianib, A., Bogacheva, M.I., Bundea, A., Havlinb, S., dan Schellnhuberd, H.J., 2014, ‘Very early warning of next El Nino’, Proceedings of the National Academy of Sciences, vol. 111, hal. 2064-2066.
Mu, B., Peng, C., Yuan, S., Chein, L., 2019, ‘ENSO Forecasting over Multiple Time Horizons Using ConvLSTM Network and Rolling Mechanism’, International Joint Conference on Neural Networks, Budapest.
Nooteboom, P.D., 1,3, Feng, Q.Y., 1,3, López, C., 2018, ‘Hernández-García, E., dan Dijkstra, H.A., Using Network Theory and Machine Learning to Predict El Nino’, Earth System Dinamics, 2018, vol. 9, hal: 969-983.
Philander, S.G., 2013, El Nino, La Nina and the Southern Oscillation, Academic Press Inc, San Diego.
Sudibyakto, 2003, ‘Anomali Iklim Dan Mitigasi Kebakaran Hutan Di Indonesia’, Majalah Geografi Indonesia, vol. 17, no. 1, hal.71–80.
Vitri, T. dan Marzuki,, 2014, ‘Analisis Pengaruh El Nino Southern Oscilation (ENSO) terhadap Curah Hujan Di Koto Tabang Sumatera Barat’, Jurnal Fisika Unand, vol. 3, No. 4, hal. 214-221.
DOI: https://doi.org/10.25077/jfu.9.4.421-427.2020
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published by:
Departemen Fisika, FMIPA Universitas Andalas
Kampus Unand Limau Manis Padang Sumatera Barat 25163
Telepon 0751-73307
Email:jfu@sci.unand.ac.id