Abstract
With the rapid growth of global shipping, accurate vessel traffic prediction is essential for waterway management and navigation safety. This study proposes the Fusion Spatio-Temporal Transformer (FSTformer) to address non-Gaussianity, non-stationarity, and spatiotemporal heterogeneity in traffic flow prediction. FSTformer incorporates a Weibull–Gaussian Transformation for distribution normalization, a hybrid Transformer encoder with Heterogeneous Mixture-of-Experts (HMoE) to model complex dependencies, and a Kernel MSE loss function to enhance robustness. Experiments on AIS data from the Fujiangsha waters of the Yangtze River show that FSTformer consistently outperforms baseline models across multiple horizons. Compared with the best baseline (STEAformer), it reduces MAE, RMSE, and MAPE by 3.9%, 1.8%, and 6.3%, respectively. These results demonstrate that FSTformer significantly improves prediction accuracy and stability, offering reliable technical support for intelligent shipping and traffic scheduling in complex waterways.