An Efficient LSTM Neural Network-Based Framework for Vessel Location Forecasting

doi:10.1109/TITS.2023.3247993

An Efficient LSTM Neural Network-Based Framework for Vessel Location Forecasting

2023-05-01

15

PRE

AI

DOI：10.1109/TITS.2023.3247993

Original

Original request for help

Save

Abstract

En 中文

Forecasting vessel locations is of major importance in the maritime domain, with applications in safety, logistics, etc. Nowadays, vessel tracking has become possible largely due to the increased GPS-based data availability. This paper introduces a novel Vessel Location Forecasting (VLF) framework, based on Long-Short Term Memory (LSTM) Neural Networks, aiming to perform effective location forecasting in time horizons up to 60 minutes, even for vessels not recorded in the past. The proposed VLF framework is specially designed for handling vessel data by addressing some major GPS-related obstacles including variable sampling rate, sparse trajectories, and noise contained in such data. Our framework also learns by incorporating a novel trajectory data augmentation method to improve its predictive power. We validate VLF framework using three real-word datasets of vessels moving in different sea areas, comparing with various methods, and examining several aspects. Results prove VLF framework's generic nature, robustness regarding parameter changes, and superiority against state of the art in terms of prediction accuracy (higher than 30%) and computational effort.

Keywords:

Trajectory

Forecasting

Artificial neural networks

Predictive models

Hidden Markov models

Spatiotemporal phenomena

Time series analysis

Future location prediction

long-short term memory neural networks

maritime data

moving objects trajectories

vessel location forecasting

trajectory data augmentation

An Efficient LSTM Neural Network-Based Framework for Vessel Location Forecasting

Abstract

Journal

Organization