Oruç, Muhammet FurkanAltan, Yiğit Can2023-08-172023-08-172023-07-010957-4174http://hdl.handle.net/10679/8709https://doi.org/10.1016/j.eswa.2023.119728As the maritime traffic is getting denser, the number of encounters is increasing. The aim of this study is to develop a prediction model to classify encounters as risky or non-risky when two ships encounter in a certain buffer zone. A novel methodology is proposed to integrate three-dimensional clustering in the algorithm training process. K-means clustering, and ensemble machine learning algorithms-based prediction framework is developed to overcome class imbalance. The methodology is tested in the Strait of Istanbul (SOI) and parameters are generated from a long-term AIS dataset. Framework is validated via cross validation techniques. Precision, Recall, Accuracy and ROC-AUC Score are used as measures to evaluate models. Benchmark models are generated, and the most advanced model successfully predicts each 4 out of 5 risky encounters without the knowledge of distance between two ships. Eliminating distance from decision factors provides an action period before risky encounters. Therefore, proposed framework can be a guide for autonomous vessels for safe navigation and maritime authorities to improve maritime safety.engrestrictedAccessarticle22100095331730000110.1016/j.eswa.2023.119728Autonomous VesselsClusteringMachine LearningMaritime RiskRisky EncounterStrait of Istanbul2-s2.0-85150765105