MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction

Xiong, Caiquan; Li, Jiaming; Zhuang, Yuzhe; Wu, Xinyun; Luo, Mao; Wang, Qi

doi:10.3390/jmse13112119

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction

by

Caiquan Xiong

¹,

Jiaming Li

¹,

Yuzhe Zhuang

¹,

Xinyun Wu

^1,*,

Mao Luo

¹ and

Qi Wang

²

¹

School of Computer Science, Hubei University of Technology, Wuhan 430068, China

²

Aerospace Information Research Institute, Beijing 100094, China

^*

Author to whom correspondence should be addressed.

J. Mar. Sci. Eng. 2025, 13(11), 2119; https://doi.org/10.3390/jmse13112119 (registering DOI)

Submission received: 25 September 2025 / Revised: 24 October 2025 / Accepted: 27 October 2025 / Published: 8 November 2025

(This article belongs to the Section Ocean Engineering)

Download Versions Notes

Abstract

Vessel trajectory prediction (VTP) plays a critical role in maritime safety and intelligent navigation. Existing methods struggle to simultaneously capture long-term dependencies and nonlinear dynamic patterns in vessel movements. To address this challenge, we propose MKAIS, a novel trajectory prediction model that integrates the selective state space modeling capability of Mamba with the strong nonlinear representation power of Kolmogorov–Arnold Networks (KAN). Specifically, we design a feature-separated embedding strategy for AIS inputs (longitude, latitude, speed over ground, course over ground), followed by an MKAN module that jointly models global temporal dependencies and nonlinear dynamics. Experiments on the public ct_dma dataset demonstrate that MKAIS outperforms state-of-the-art baselines (LSTM, Transformer, TrAISformer, Mamba), achieving up to 16.65% improvement in the Haversine distance over 3 h prediction horizons. These results highlight the effectiveness and robustness of MKAIS for both short-term and long-term vessel trajectory prediction.

Keywords: vessel trajectory prediction; selective state space model; Kolmogorov–Arnold networks; nonlinear spatiotemporal modeling; AIS data

Share and Cite

MDPI and ACS Style

Xiong, C.; Li, J.; Zhuang, Y.; Wu, X.; Luo, M.; Wang, Q. MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction. J. Mar. Sci. Eng. 2025, 13, 2119. https://doi.org/10.3390/jmse13112119

AMA Style

Xiong C, Li J, Zhuang Y, Wu X, Luo M, Wang Q. MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction. Journal of Marine Science and Engineering. 2025; 13(11):2119. https://doi.org/10.3390/jmse13112119

Chicago/Turabian Style

Xiong, Caiquan, Jiaming Li, Yuzhe Zhuang, Xinyun Wu, Mao Luo, and Qi Wang. 2025. "MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction" Journal of Marine Science and Engineering 13, no. 11: 2119. https://doi.org/10.3390/jmse13112119

APA Style

Xiong, C., Li, J., Zhuang, Y., Wu, X., Luo, M., & Wang, Q. (2025). MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction. Journal of Marine Science and Engineering, 13(11), 2119. https://doi.org/10.3390/jmse13112119

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

MKAIS: A Hybrid Mamba–KAN Neural Network for Vessel Trajectory Prediction

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI