Comparative Analysis of ARIMA and LSTM Methods for Sea Surface Temperature Forecasting in the Sunda Strait

Yenni Angraini; Raihan Sabillah Adisecha; Nabil Ibni Nawawi Nawawi; Naiya Dzil Izzati; Muhammad Tsaqif Najmuddin; Nawwaf Ariq Rabbani; Adelia Putri Pangestika

doi:10.20956/j.v21i3.42565

Authors

Yenni Angraini IPB University
Raihan Sabillah Adisecha IPB University
Nabil Ibni Nawawi Nawawi IPB University
Naiya Dzil Izzati IPB University
Muhammad Tsaqif Najmuddin IPB University
Nawwaf Ariq Rabbani IPB University
Adelia Putri Pangestika IPB University

DOI:

https://doi.org/10.20956/j.v21i3.42565

Keywords:

ARIMA, LSTM, Sunda Strait, Temperature, MAPE

Abstract

The Sunda Strait is an important area for Indonesia because it is the main domestic and international transportation route. As a water area, the Sunda Strait has weather conditions that are greatly influenced by sea surface temperature (SST). Crucial SST forecasting is carried out to assist maritime transportation activities. This study aims to compare the performance of the ARIMA and LSTM methods in forecasting SST in the Sunda Strait. The data used in this study are daily SST data for the Sunda Strait from August 20, 2022, to January 1, 2024. The best ARIMA model obtained in this data modeling is ARIMA(1,1,1), where this model has significant overall parameters, the smallest AIC and BIC values, and model diagnostic results that meet the assumptions. Meanwhile, in LSTM modeling, the best combination of hyperparameters obtained is a neuron of 150, an epoch of 150, and a batch size of 32, where this combination produces the lowest MSE value of 0.003799. A comparison of the performance of the ARIMA and LSTM methods is carried out by considering the MAPE values of the training data and test data. The LSTM method is superior to the ARIMA method, with a MAPE value of 0.512% for training data and 0.564 for testing data. The forecasting results using the LSTM method show a similar pattern in both training and testing data. Meanwhile, the forecasting results of the LSTM method for the following 30 periods show a fluctuating pattern throughout the day.

References

[1] Alim, M., N., 2023. Pemodelan Time Series Data Saham LQ45 dengan Algoritma LSTM, RNN, dan Arima, PRISMA: Prosiding Sem-Nas Matematika, Vol. 6 thn 2024, 694-701. Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Negeri Semarang, Semarang.

[2] Amalia, DW, 2024. Peramalan Jumlah Incident Information Technology PT XYZ Menggunakan Artificial Neural Network (ANN). Journal of Emerging Information Systems and Business Intelligence. Vol. 5, No. 3, 20–27.

[3] Arissinta, I., O., Sulistiyowati, I., D Kurnianto, D. & Kharisudin, I., 2022. Pemodelan Time Series untuk Peramalan Web Traffic Menggunakan Algoritma Arima, LSTM, dan GRU, PRISMA: Prosiding Sem-Nas Matematika, Vol. 5 thn 2022, 693–700. Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Negeri Semarang, Semarang.

[4] Batubara, M., P., N., Zainuri, M., Kunarso, K. & Puryajati, A., D., 2022, Diagnosa Perilaku MJO Aktif pada saat La Nina Kuat (2011/2012) di Perairan Tropis. Buletin Oseanografi Marina. Vol. 11, No. 2, 193–205.

[5] Christofi, V., P., Wang, X., Christofi, V., P. & Wang, X., 2024. Optimizing the LSTM Deep Learning Model for Arctic Sea Ice Melting Prediction. Atmospheric and Climate Sciences. Vol. 14, No. 4, 429–449.

[6] Cryer, J., D. & Chan, K., S. 2008. Time Series Analysis with Applications in R, Second Edition. Springer Science & Business Media., New York.

[7] Dhakal, D., Gautam, Y. & Bhattarai, A., 2021. Exploring a deep LSTM neural network to forecast daily PM2.5 concentration using meteorological parameters in Kathmandu Valley, Nepal, Air Quality. Atmosphere and Health, Vol. 14, 83–96.

[8] Elsaraiti, M. & Merabet, A., 2021. A Comparative Analysis of the ARIMA dan LSTM Predictive Models and Their Effectiveness for Predicting Wind Speed. Energies, Vol. 14, No. 20, 1-16.

[9] Gestel, T., V., Suykens, J., A., K., Baestaens, D., E., Lambrechts, A., Lanckriet, G. & Vandaele, B., 2001. Financial Time Series Prediction Using Least Squares Support Vector Machines Within the Evidence Framework. IEEE Transactions on Neural Networks, Vol. 12, No. 4, 809–821.

[10] Hilal, Y., N., Nainggolan, G., D., A., Syahputri, S., H. & Kartiasih, F., 2024. Comparsion of ARIMA and LSTM methods in predicting Jakarta sea level. Jurnal Ilmu Dan Teknologi Kelautan Tropis, Vol. 16, No. 2, 163–178.

[11] JAXA, JAXA Earth-graphy / Space Technology Directorate, (2024).

[12] Jeong, K., J. & Shin, Y., M., 2022. Time-Series Anomaly Detection with Implicit Neural Representation. arXiv preprint arXiv: 2201.11950.

[13] Kim, M., Yang, H. & Kim, J., 2020. Sea Surface Temperature and High Water Temperature Occurrence Prediction Using a Long Short-Term Memory Model. Remote Sensing, Vol. 12, No. 21, 3654.

[14] Kundu, A., Sahu, A., Serpedin, E. & Davis, K., 2020. A3D: Attention-based auto-encoder Anomaly Detector for False Data Injection Attacks. Electric Power Systems Research, Vol. 189, No. 106795, 1-7.

[15] Lin, S. & Feng, Y, 2022. Research on stock price prediction based on orthogonal Gaussian basis function expansion and Pearson correlation coefficient weighted lstm neural network, Advances in Computer. Signals and Systems, Vol. 6, No. 5, 23–30.

[16] Lin, Y. & Zhong, G. A., 2021. Multi-Channel LSTM Model for Sea Surface Temperature Prediction. Journal of Physics: Conference Series, Vol. 1880, 012029.

[17] Mahkya, D Anggraini, Fitriawati, Siahaan, R., M., 2020. Pemodelan dan prediksi jumlah penumpang pelabuhan bakauheni selama periode tsunami Selat Sunda menggunakan autoregressive integrated moving average. Journal of Science and Applicative Technology. Vol. 4, No. 1, 32-37.

[18] Mawaddah, S., N., Prakoso, L., Y. & Sudiarso, A., 2021. Aspek Geostrategi pada Selat Sunda dalam Mencapai Visi Poros Maritim Dunia. Jurnal Strategi Pertahanan Laut, Vol. 7, No. 3, 185-194.

[19] Mulyani, A., S., 2020. Antisipasi Terjadinya Pemanasan Global dengan Deteksi Dini Suhu Permukaan Air Menggunakan Data Satelit. e-Journal CENTECH, Vol. 2, No. 1, 22-29.

[20] Nastiti, E., Damayanti, T., Madina, S., A., 2023. Dampak Pelanggaran Asumsi Klasik Terhadap Estimasi Model Ekonometrika. Jurnal Pijar Studi Manajemen Dan Bisnis, Vol. 2, No. 1, 566–577.

[21] Ng, V., K., Y. & Cribbie, R., A., 2018. The Gamma Generalized Linear Model, Log Transformation, and the Robust Yuen-Welch Test for Analyzing Group Means with Skewed and Heteroscedastic Data. Communications in Statistics – Simulation and Computation, Vol. 48, No. 8, 2269-2286.

[22] Nurhambali, M., R., Angraini, Y. & Fitrianto, A., 2024. Implementation of Long Short-Term Memory for Gold Prices Forecasting. Malaysian Journal of Mathematical Sciences, Vol. 18, No. 2, 394-422.

[23] Pamungkas, M., B. & Wibowo, A., 2018. Aplikasi Metode ARIMA Box-Jenkins untuk Meramalkan Kasus DBD di Provinsi Jawa Timur. The Indonesian Journal of Public Health, Vol. 13, No. 2, 181-194.

[24] Pranolo, A., Setyaputri, F., U., Paramarta, A., K., I., Triono, A., P., P., Fadhilla, A., F., Akbari, A., K., G., Utama, A., B., P., Wibawa, A., P., Uriu, W., 2024. Enhanced Multivariate Time Series Analysis Using LSTM: A Comparative Study of Min-Max and Z-Score Normalization Techniques. ILKOM Jurnal Ilmiah, Vol. 16, No. 2, 210–220.

[25] Roza, A., Violita, E., S. & Aktivani, S., 2022. Study of Inflation using Stationary Test with Augmented Dickey Fuller & Phillips-Peron Unit Root Test (Case in Bukttinggi City Inflation for 2014-2019). Eksakta: Berkala Ilmiah Bidang MIPA, Vol. 23, No. 2, 106-116.

[26] Schaffer, A., L., Dobbins, T., A. & Pearson, S., A. 2021. Interrupted Time Series Analysis using Autoregressive Integrated Moving Average (ARIMA) Models: a Guide for Evaluating Large-Scale Health Interventions. BMC Medical Research Methodology, Vol. 21, 1-12.

[27] Switrayana, I., N., Hammad, R., Irfan, P., Sujaka, T., T., Nasri, M., H., 2025. Comparative Analysis of Stock Price Prediction Using Deep Learning with Data Scaling Method, JTIM : Jurnal Teknologi Informasi Dan Multimedia, Vol. 7, No. 1, 78–90.

[28] Taylor, J., Feng, M., 2022. A deep learning model for forecasting global monthly mean sea surface temperature anomalies. Frontiers in Climate, Vol. 4, 932932.

[29] Wiranda, L. & Sadikin, M., 2019. Penerapan Long Short-Term Memory pada Data Time Series untuk Memprediksi Penjualan Produk PT. Metiska Farma. Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI, Vol. 8, No. 3, 184-196.

[30] Yanti, F., Sari, B., N., Defiyanti, S., 2024. Implementasi Algoritma Lstm Pada Peramalan Stok Obat (Studi Kasus: Puskesmas Beber). Jurnal Mahasiswa Teknik Informatika, Vol. 8, No. 4, 6082–6089.

[31] Zhang, Q., Wang, H., Dong, J., Zhong, G., Sun, X., 2017. Prediction of Sea Surface Temperature Using Long Short-Term Memory. IEEE Geoscience and Remote Sensing Letters, Vol. 14, No. 10, 1745–1749.