This paper presents a data mining-then-predict method for proactive maritime traffic management using machine learning. The study focuses on traffic dynamics within convergent areas of inland waterways, leveraging Automatic Identification System (AIS) data to extract and predict traffic patterns. The method involves processing AIS data to reconstruct ship trajectories, grouping them into trajectory sets based on shared origin, destination, and route. A stop detection model is applied to identify nodes within maritime traffic networks, and a decision tree algorithm is used to train a classifier for predicting traffic patterns. The method was validated in the convergent area of the Yangtze River and the Hanjiang River, achieving a 96.7% accuracy rate and 80.9% precision in predicting single ship trajectories. The findings suggest that the proposed method effectively extracts and predicts traffic patterns, identifies congestion in convergent waters, and supports traffic management strategies. The study also highlights the importance of considering both ship destination uncertainties and temporary stops during navigation, which are crucial for intelligent maritime traffic management.This paper presents a data mining-then-predict method for proactive maritime traffic management using machine learning. The study focuses on traffic dynamics within convergent areas of inland waterways, leveraging Automatic Identification System (AIS) data to extract and predict traffic patterns. The method involves processing AIS data to reconstruct ship trajectories, grouping them into trajectory sets based on shared origin, destination, and route. A stop detection model is applied to identify nodes within maritime traffic networks, and a decision tree algorithm is used to train a classifier for predicting traffic patterns. The method was validated in the convergent area of the Yangtze River and the Hanjiang River, achieving a 96.7% accuracy rate and 80.9% precision in predicting single ship trajectories. The findings suggest that the proposed method effectively extracts and predicts traffic patterns, identifies congestion in convergent waters, and supports traffic management strategies. The study also highlights the importance of considering both ship destination uncertainties and temporary stops during navigation, which are crucial for intelligent maritime traffic management.