Automatic identification system big data‑driven maritime traffic density prediction in surabaya port using PCA and k‑means clustering

Abstract

The management of maritime traffic directly determines the level of operational efficiency and safety achievable at major ports, including Tanjung Perak in Surabaya, which serves as a critical logistics node for eastern Indonesia. This study presents a comprehensive analysis of maritime traffic density prediction using Automatic Identification System (AIS) big data combined with Principal Component Analysis (PCA) and K-Means clustering techniques. The dataset comprises 1,173 vessel movements recorded in December 2025, encompassing various vessel types, port operations, and voyage characteristics. Through dimensionality reduction using PCA and unsupervised clustering with K-Means, we identified 10 distinct traffic patterns representing different operational profiles. The analysis revealed significant temporal patterns, with peak traffic occurring at 14:00 (79 vessels) and lowest traffic at 02:00 (18 vessels). The clustering results achieved a silhouette score of 0.3863, effectively segmenting vessels based on voyage distance, capacity, speed, draught, and temporal features. The results of this research offer practical guidance for port authorities seeking to improve resource allocation, traffic management, and operational efficiency based on empirical evidence.