Hybrid Intelligence for Wave Prediction: Integrating Sparse LSTM-Transformer with an Expert System

Accurate and computationally efficient wave height prediction is critical for marine operations, coastal engineering, and offshore safety. However, existing models struggle to capture both short- and long-term dependencies in complex sea states. This study presents a hybrid forecasting framework that combines Long Short-Term Memory (LSTM) networks and Transformer encoders, augmented by a sparse attention mechanism to reduce computational cost while preserving key temporal features. To further enhance reliability under extreme conditions, a knowledge-based expert system is incorporated, consisting of 21 domain-specific rules addressing physical constraints, safety thresholds, and control logic. These rules refine the model’s outputs through a confidence-weighted fusion approach. The model is evaluated using five years of half-hourly wave height data from the Muluraba buoy station. Experimental results demonstrate that the proposed hybrid system outperforms traditional statistical models (e.g., ARIMA) and baseline deep learning models (e.g., CNN-LSTM, standard LSTM-Transformer), achieving a correlation coefficient of 0.97, RMSE of 0.027, and MAE of 0.019. These results demonstrate the effectiveness of integrating neural networks with expert systems for robust wave forecasting.