<![CDATA[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.]]>
Copyrights © 2025
