Abstract
This paper proposes a novel data-driven approach to estimate the navigable capacity of busy waterways, focusing on ships entering and leaving port, based on the structural characteristics of traffic flow driven by the Automatic Identification System (AIS) data. First, we collect the ship traffic flow in a busy waterway by processing the original AIS data and then identify the structural characteristics of the traffic flow using the K-means clustering algorithm. The clusters are constructed based on the spatiotemporal consumption of waterway resources of different ships and the waste of waterway resources caused by navigational mode conversion, taking ship domain into consideration. We apply the proposed approach to estimate the navigable capacity of the Dagusha Channel of Tianjin Port, China. The empirical results reveal that the maximum daily traffic capacity of the Dagusha Channel is about 109 ship times/day. A comparison of waterway capacity estimation methods demonstrates that our proposed approach is more accurate and able to quantify the waterway capacity of different types of ships in a busy waterway, taking the structural characteristics of traffic flow explicitly into account. The proposed approach provides support for the design of channel and determination of scheduling schemes for ships in busy waterways.