A novel method for generating inland waterway vessel routes using AIS data

Abstract

The study presents a novel approach for generating inland waterway vessel routes based on Automatic Identification System (AIS) data. The trajectory partition algorithm categorizes trajectory data of the Yangtze River to establish round-trip routes. A turning point identification algorithm aids in identifying significant turning points, followed by clustering using the clustering method. Cluster centroids generated from these clusters serve as crucial waypoints for route planning. The Akima interpolation polynomial is judiciously applied to interpolate waypoints, resulting in meticulous route generation. Validation employs a dataset of 5,480,049 dynamic trajectory points from the Yangtze River, demonstrating the method's efficacy. Results indicate mean squared errors of 0.77% and 6.21%, symmetrical mean absolute percentage errors of 5.3% and 7.3%, and correlation coefficients of 99.62% and 97.14% with actual routes, respectively. In contrast to conventional inland waterway route generation methods relying on electronic river charts, the novel approach introduced in this paper for generating inland waterway vessel routes based on AIS data offers superior precision without necessitating route smoothing, thus demonstrating enhanced adaptability.