aiqbench analysis
This study addresses the computational inefficiencies and accuracy limits of standard Transformer models when processing long-term maritime trajectory data. By integrating an Informer-based encoder with Fourier-like frequency expansions, TempTPI significantly reduces overhead while capturing cyclic vessel behavior patterns for improved situational awareness. The framework demonstrates a substantial reduction in Mean Squared Error compared to state-of-the-art baselines over extended forecasting horizons.
TempTPI: Informer-Based trajectory prediction for maritime vessels
arXiv:2609.09840v1 Announce Type: new Abstract: Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularly Transformers, have shown promise in processing Automatic Identification System (AIS) data, they often struggle with the quadratic computational complexity of self-attention and the loss of accuracy over extended forecasting horizons. This study proposes TempTPI, a novel prediction framework that integrates an Informer-based encoder with a multi-channel temporal encoding mechanism. The Informer architecture leverages a ProbSparse self-attention mechanism to reduce computational overhead and focus on the most significant dependencies, while the temporal encoder utilizes Fourier-like frequency expansions to capture cyclic patterns (hourly, daily, and seasonal) in vessel behavior. We evaluate our model against the state-of-the-art TPTrans architecture using AIS data from Danish waters. Experimental results demonstrate that TempTPI consistently outperforms existing methods across prediction windows of 1 to 5 hours. Notably, at a 5-hour horizon, the proposed model achieves a 55% improvement in Mean Squared Error (MSE), offering a robust solution for long-range maritime situational awareness.
Abstract:Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularly Transformers, have shown promise in processing Automatic Identification System (AIS) data, they often struggle with the quadratic computational complexity of self-attention and the loss of accuracy over extended forecasting horizons. This study proposes TempTPI, a novel prediction framework that integrates an Informer-based encoder with a multi-channel temporal encoding mechanism. The Informer architecture leverages a ProbSparse self-attention mechanism to reduce computational overhead and focus on the most significant dependencies, while the temporal encoder utilizes Fourier-like frequency expansions to capture cyclic patterns (hourly, daily, and seasonal) in vessel behavior. We evaluate our model against the state-of-the-art TPTrans architecture using AIS data from Danish waters. Experimental results demonstrate that TempTPI consistently outperforms existing methods across prediction windows of 1 to 5 hours. Notably, at a 5-hour horizon, the proposed model achieves a 55% improvement in Mean Squared Error (MSE), offering a robust solution for long-range maritime situational awareness.
Accepted to IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2026. \c{opyright} 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media
Machine Learning (cs.LG)
arXiv:2609.09840 [cs.LG]
(or arXiv:2609.09840v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.09840 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 219 words
Related coverage
Context-Informed Ship Trajectory Prediction via Conditional Attention
arXiv · Jul 31, 2026
AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks
arXiv · Jun 6, 2026
NaviAIS: A Scenario-Level Vessel Trajectory Prediction Dataset withVectorized Lane Priors and the NaviLane Forecasting Framework
arXiv · Jul 23, 2026
Digital Surveillance Reshapes Fishery Enforcement in Indonesia
IEEE Spectrum · Jul 16, 2026