Comparison of Seismic Traces Clustering Efficiency of Different Unsupervised Machine Learning Algorithms in Forward Seismic Models
I. Churochkin, A. Volkova, E. Gavrilova, N. Bukhanov, A. Butorin and V. Rukavishnikov
Event name: 81st EAGE Conference and Exhibition 2019
Session: Poster: AI/Digitalization for Interpretation - Various Application
Publication date: 03 June 2019
Info: Extended abstract, PDF ( 744.68Kb )
Price: € 20
In this study, it is proposed to build geological model based on proportions of fluvial deposits outcrop. Then forward seismic model is constructed and clustering of seismic traces by using different unsupervised algorithms (k-means, DBSCAN and Agglomerative clustering) is performed. Results are compared with ground truth, which in our case is NTG map of interval of interest in geological model. Finally the optimal settings of the algorithms and the most accurate clustering method are identified.