<![CDATA[Accurate Significant Wave Height (SWH) forecasting is essential for maritime safety in the northern waters of Central Java, where shallow Java Sea conditions and monsoonal winds generate nonlinear and seasonal wave variability. This study evaluates Autoformer for SWH forecasting and examines the effect of Mutual Information (MI)-based multivariate feature selection on predictive performance. The 2025 BMKG Ocean Forecast System dataset contains 2,913 tri-hourly time-series samples comprising wind speed, wind direction, wave period, sea surface temperature, and SWH. Data were partitioned chronologically into 80% training and 20% testing sets, using a sequence length of 96 steps and a prediction horizon of 24 steps. MI ranked wind speed as the most informative exogenous variable (0.7304), followed by sea surface temperature (0.6101), wind direction (0.3946), and wave period (0.1585). The full multivariate configuration achieved the strongest performance, with MAE of 0.0931 m, RMSE of 0.1193 m, MAPE of 20.30%, and R² of 0.6929. Excluding wave period increased RMSE to 0.1464 m and reduced R² to 0.5376, demonstrating that a modest individual MI score can coexist with valuable temporal complementarity. For maritime operations and coastal engineering, the full-feature configuration offers a promising basis for short-range sea-state guidance supporting route planning, port scheduling, and wave-sensitive coastal decisions.]]>
Copyrights © 2026
