Research on Ship Arrival Law Based on Route Matching and Deep Learning

Abstract

Maritime transportation has always been the most important mode of transportation in international trade. With the deepening development of economic globalization, the scale of international trade, which is the core content of economic globalization, is also expanding, and the shipping industry is also developing greatly. In this paper, aiming at improving the operation efficiency of container terminals, AIS data is used as the research basis to predict the arrival time of ships and reduce the uncertainty of arrival time of ships, so as to provide support for the construction of smart ports. The transitive closure method based on equivalence relation is used to fuzzy cluster the routes to be matched and the historical routes used for matching, and the optimal route matching is realized by cutting set selection. At the same time, the navigation trajectory features based on AIS data are constructed, and the RNN-LSTM (Recurrent Neural Networks-Long Short-Term Memory) model is proposed by using the characteristics of deep learning and time series.The results show that the RNN-LSTM ship trajectory prediction model based on deep learning can achieve excellent prediction results and provide technical support for intelligent transportation at sea.