Deep Learning-Based Sea Level Forecasting  Using Informer in Cilacap, Indonesia

Reva Rivandi Salim; Didit Adytia

doi:10.30595/juita.v13i3.27176

Authors

Reva Rivandi Salim Telkom University
Didit Adytia Telkom University

DOI:

https://doi.org/10.30595/juita.v13i3.27176

Keywords:

sea level forecasting, informer, deep learning, time series prediction

Abstract

Sea level forecasting is very important for coastal risk management and operational planning, especially in regions vulnerable to frequent tidal flooding events. Tidal Harmonic Analysis (THA) and other traditional methods can effectively reconstruct tidal components but typically overlook non-tidal influences such as meteorological variability and ocean swell. This study mitigates these limitations by proposing the Informer model, a Transformer-based deep learning architecture for long-range sequence forecasting, to predict sea levels using 11 months of hourly observational data (December 2023 – October 2024) from Cilacap, a tropical coastal region in Indonesia. A new preprocessing pipeline is introduced, integrating THA-based tidal reconstruction with interpolation techniques to handle missing data. Forecasting performance is evaluated across multiple prediction horizons (1, 3, 5, 7, and 14 days) and compared against XGBoost, LSTM, and the standard Transformer. The results show that Informer does better than the other models, especially over longer horizons. It has the lowest RMSE (0.091), the lowest MAPE (2.14%), and the highest correlation coefficient (0.98) on the 14-day forecast. In this study, we focused on the Informer’s capability for long horizon from sea level data for providing a reliable solution for sea level prediction. This results show that the model is applicable for integration into early warning systems.

References

[1] S. Tumse and U. Alcansoy, “Statistical and Deep Learning Approaches in Estimating Present and Future Global Mean Sea Level Rise,” Natural Hazards, 2025, doi: 10.1007/s11069-025-07203-5.

[2] Kiera L. O’Donnell, Emily S. Bernhardt, Xi Yang, Ryan E. Emanuel, Marcelo Ardón, Manuel T. Lerdau, Alex K. Manda, Anna E. Braswell, Todd K. BenDor, Eric C. Edwards, Elizabeth Frankenberg, Ashley M. Helton, John S. Kominoski, Amy E. Lesen, Lindsay Naylor, Greg Noe, Kate L. Tully, Elliott White, and Justin P. Wright, “Saltwater Intrusion and Sea Level Rise Threatens U.S. Rural Coastal Landscapes and Communities,” Mar. 2024, Elsevier Ltd. doi: 10.1016/j.ancene.2024.100427.

[3] A. Nurlatifah, Martono, I. Susanti, and M. Suhermat, “Variability and Trend of Sea Level in Southern Waters of Java, Indonesia,” Journal of Southern Hemisphere Earth Systems Science, vol. 71, no. 3, pp. 272–283, Dec. 2021, doi: 10.1071/ES21004.

[4] Y. Li, J. Feng, X. Yang, S. Zhang, G. Chao, L. Zhao, and H. Fu, “Analysis of Sea Level Variability and Its Contributions in the Bohai, Yellow Sea, and East China Sea,” Frontiers in Marine Science, vol. 11, 2024, doi: 10.3389/fmars.2024.1381187.

[5] N. Alenezi, A. Alsulaili, and M. Alkhalidi, “Prediction of Sea Level in the Arabian Gulf Using Artificial Neural Networks,” Journal of Marine Science and Engineering, vol. 11, no. 11, Nov. 2023, doi: 10.3390/jmse11112052.

[6] A. W. Ramadhan, D. Adytia, D. Saepudin, S. Husrin, and A. Adiwijaya, “Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 12, no. 3, p. 130, Oct. 2021, doi: 10.24843/lkjiti.2021.v12.i03.p01.

[7] E. J. Lee, K. Kim, and J. H. Park, “Reconstruction of long-term sea-level data gaps of tide gauge records using a neural network operator,” Frontiers in Marine Science, vol. 9, Oct. 2022, doi: 10.3389/fmars.2022.1037697.

[8] E. Forootan, S. Farzaneh, K. Naderi, and J. P. Cederholm, “Analyzing GNSS Measurements to Detect and Predict Bridge Movements Using the Kalman Filter (KF) and Neural Network (NN) Techniques,” Geomatics, vol. 1, no. 1, pp. 65–80, Feb. 2021, doi: 10.3390/geomatics1010006.

[9] M. Cho, C. Kim, K. Jung, and H. Jung, “Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction,” Water (Switzerland), vol. 14, no. 14, Jul. 2022, doi: 10.3390/w14142221.

[10] Cornelius Stephanus Alfredo and D. A. Adytia, “Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 5, pp. 776–781, Oct. 2022, doi: 10.29207/resti.v6i5.4160.

[11] M. Waqas and U. W. Humphries, “A Critical Review of RNN and LSTM Variants in Hydrological Time Series Predictions,” MethodsX, vol. 13, p. 102946, Dec. 2024, doi: 10.1016/j.mex.2024.102946.

[12] D. Saepudin, Egi Shidqi Rabbani, Dio Navialdy, and Didit Adytia, “Water Level Time Series Forecasting Using TCN Study Case in Surabaya,” Jurnal Online Informatika, vol. 9, no. 1, pp. 61–69, Apr. 2024, doi: 10.15575/join.v9i1.1312.

[13] A. Puspita Sari and D. Adytia, Sea Level Time Series Forecasting by using LSTM with Attention Mechanism, A Case Study in Jakarta, Indonesia. IEEE, 2024. doi: 10.1109/ICoDSA62899.2024.10652146.

[14] H. Zhou, “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting,” 2021. doi: https://doi.org/10.48550/arXiv.2012.07436.

[15] P. Lu, Y. He, W. Li, Y. Chen, R. Kong, and T. Wang, “An Informer-based multi-scale model that fuses memory factors and wavelet denoising for tidal prediction,” Electronic Research Archive, vol. 33, no. 2, pp. 697–724, 2025, doi: 10.3934/era.2025032.

[16] N. Tepetidis, D. Koutsoyiannis, T. Iliopoulou, and P. Dimitriadis, “Investigating the Performance of the Informer Model for Streamflow Forecasting,” Water (Switzerland), vol. 16, no. 20, Oct. 2024, doi: 10.3390/w16202882.

[17] Zhang, T., Lin, P., Liu, H., Wang, P., Wang, Y., Zheng, W., Yu, Z., Jiang, J., Li, Y., & He, H. (2025). A New Transformer Network for Short-Term Global Sea Surface Temperature Forecasting: Importance of Eddies. Remote Sensing, 17(9), 1507. https://doi.org/10.3390/rs17091507

[18] A. Frifra, M. Maanan, M. Maanan, and H. Rhinane, “Harnessing LSTM and XGBoost algorithms for storm prediction,” Scientific Reports, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-62182-0.

[19] C. Chen and J. Dong, “Deep Learning Approaches For Time Series Prediction in Climate Resilience Applications,” Frontiers in Environmental Science vol. 13, 2025, doi: 10.3389/fenvs.2025.1574981.

[20] M. Vicens-Miquel, P. E. Tissot, and F. A. Medrano, “Exploring Deep Learning Methods for Short-Term Tide Gauge Water Level Predictions,” Water (Switzerland), vol. 16, no. 20, Oct. 2024, doi: 10.3390/w16202886.

[21] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention Is All You Need,” Jun. 2017, [Online]. Available: http://arxiv.org/abs/1706.03762

[22] I. Aguilera-Martos, A. Herrera-Poyatos, J. Luengo, and F. Herrera, “Local Attention Mechanism: Boosting the Transformer Architecture for Long-Sequence Time Series Forecasting,” Oct. 2024, doi: https://doi.org/10.48550/arXiv.2410.03805.

[23] M. N. Adli Zakaria, A. N. Ahmed, M. A. Malek, A. H. Birima, Md. M. Hayet Khan, M. Sherif, and A. Elshafie, “Exploring Machine Learning Algorithms For Accurate Water Level Forecasting in Muda River, Malaysia,” Heliyon, vol. 9, no. 7, Jul. 2023, doi: 10.1016/j.heliyon.2023.e17689.

[24] N. Raj, Z. Gharineiat, A. A. M. Ahmed, and Y. Stepanyants, “Assessment and Prediction of Sea Level Trend in the South Pacific Region,” Remote Sensing (Basel), vol. 14, no. 4, Feb. 2022, doi: 10.3390/rs14040986.