This paper aims to investigate the U-turn made by ships far away from their destination docks (called off-destination-dock U-turns) in the narrow waterway using automatic identification system (AIS) data. Such U-turns are time-consuming and would occupy a long section of channel, causing the travel delay for other vessels. The Houston Ship Channel (HSC) was used as the case study. The purpose of the study was two-folded. First, for each cargo or tanker having trips in the channel, we aimed to build a methodological framework and corresponding solution algorithms to capture significant directional changes of a ship's trajectory so that the calculation could be based on much fewer points for U-turn analysis. Second, the proposed algorithms were applied to the HSC to identify the sections frequently used by those off-destination-dock U-turns. In a narrow busy waterway, cargos and tankers, may be forced to wait or make the U-turn at predetermined sections of channel due to their larger length and/or width. Identifying such sections (i.e., “hotspots”) can be useful for future channel developments and daily traffic management. The proposed methods and algorithms are generalized, so that they can be also applied to other narrow waterways in the same or similar situations. • A novel model was proposed to identify vessels' U-turn behavior based on AIS data. • The solution algorithm was proposed and tested efficiently using real AIS data of 6 months. • Hot spots for U-turn in the Houston Ship Channel (HSC) were identified and analyzed.