EXTRACTION OF UNDERLYING GEOLOGICAL STRUCTURE FROM SEISMIC DATA USING DATA MINING TECHNIQUES

The development of seismic-imaging technology has substantially improved the exploration of subsurface deposits of crude oil, natural gas and minerals. Recent advances in data capture, processing power and storage capabilities have enabled us to analyze large volumes of seismic data. In this study we report on the implementation of machine learning and data mining techniques for analysis of seismic data to reveal salt deposits underneath the soil. Several seismic attributes have been extracted from these datasets. Using information gain, the best six attributes (homogeneity, contrast, energy, median, peaks and average energy) have been selected for further classification. Finally we compared the results obtained using four different clustering techniques: k-means algorithm, expectation maximization algorithm, min-cut algorithm and Euclidean clustering.