IN RECENT YEARS, DUE TO INCREASING IN THE SIZE OF 3D SEISMIC DATA VOLUMES AND THE NUMBER OF SEISMIC ATTRIBUTES, UNSUPERVISED PATTERN RECOGNITION TECHNIQUES AS A FIRST-HAND INTERPRETATION METHOD HAVE BEEN USED TO BOTH ADDRESS THIS PROBLEM AND TO PROVIDE INITIAL GUIDANCE WHEN WORKING ON A NEW SEISMIC DATA WHERE PREVIOUS STUDIES AND DATA ARE LIMITED. THESE UNSUPERVISED PATTERN RECOGNITION TECHNIQUES ARE K-MEANS, SELF-ORGANIZING MAP, GENERATIVE TOPOGRAPHIC MAPPING, AND PRINCIPAL COMPONENT ANALYSIS. IN THIS STUDY, THE K-MEANS AND PCA ARE APPLIED TO A 3D SEISMIC DATA VOLUME ACQUIRED OVER THE STRAIT OF HORMUZ TO DETECT THE BURIED CHANNELS IN THIS AREA. NOT SURPRISINGLY, THE MOST IMPORTANT PARAMETER IN THIS STUDY WAS THE CHOICE OF CORRECT SEISMIC ATTRIBUTES. ALTHOUGH THE PRINCIPAL COMPONENT ANALYSIS METHOD IS NOT A CLUSTERING TECHNIQUE, IT CAN DETECT CHANNELS IN 3D SEISMIC DATA MORE EFFICIENT THAN THE KMEANS CLUSTERING METHOD.