AUTHOR=Huang Peng , Chen Qiong , Wang Dong , Wang Mingqing , Wu Xi , Huang Xiaomeng 

TITLE=TripleConvTransformer: A deep learning vessel trajectory prediction method fusing discretized meteorological data

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.1012547

DOI=10.3389/fenvs.2022.1012547

ISSN=2296-665X

ABSTRACT=The shipping industry is increasingly threatened by global climate change. A reliable trajectory prediction can perceive potential risks and ensure navigation efficiency. However, many existing studies have not fully considered the impact of complex ocean environmental factors, and only have focused on local regions, which are difficult to be extended to a global scale. To this end, we propose a deep learning vessel trajectory prediction method fusing discretized meteorological data (TripleConvTransformer). First, we clean the automatic identification system (AIS) data to form a high-quality spatiotemporal trajectory dataset. Then, we fuse the trajectory data with the meteorological data after feature discretization to deeply mine the motion information of ocean-going ships. Finally, we design the three modules of global convolution, local convolution, and trend convolution based on the simplified Transformer model to capture multi-scale features. We compare TripleConvTransformer with the state-of-the-art prediction models. The experimental results show that in the prediction of the trajectory points in the next 90 minutes, TripleConvTransformer obtains the smallest root mean square error of longitude and latitude, and the highest overall prediction accuracy. Our method not only fully considers the influence of meteorological factors in the ocean-going process, but also effectively extracts the important information hidden in the data, thus achieving the accurate trajectory prediction on a global scale.