Short-term Inland Vessel Trajectory Prediction with Encoder-Decoder Models

TL;DR

This study compares various encoder-decoder models, including a transformer, for inland vessel trajectory prediction using AIS data and river-specific features, finding that reformulating regression as classification improves accuracy.

Contribution

First application of transformer-based encoder-decoder models to inland vessel trajectory prediction incorporating river-specific features.

Findings

Reformulating regression as classification reduces displacement errors.

LSTM encoder-decoder outperforms transformer in accuracy but is more computationally expensive.

Including river-specific features enhances prediction performance.

Abstract

Accurate vessel trajectory prediction is necessary for save and efficient navigation. Deep learning-based prediction models, esp. encoder-decoders, are rarely applied to inland navigation specifically. Approaches from the maritime domain cannot directly be transferred to river navigation due to specific driving behavior influencing factors. Different encoder-decoder architectures, including a transformer encoder-decoder, are compared herein for predicting the next positions of inland vessels, given not only spatio-temporal information from AIS, but also river specific features. The results show that the reformulation of the regression task as classification problem and the inclusion of river specific features yield the lowest displacement errors. The standard LSTM encoder-decoder outperforms the transformer encoder-decoder for the data considered, but is computationally more expensive. In this study for the first time a transformer-based encoder-decoder model is applied to the problem of predicting the ship trajectory. Here, a feature vector using the river-specific context of navigation input parameters is established. Future studies can built on the proposed models, investigate the improvement of the computationally more efficient transformer, e.g. through further hyper-parameter optimization, and use additional river-specific information in the context representation to further increase prediction accuracy.