TY - GEN
T1 - Comparison of seismic traces clustering efficiency of different unsupervised machine learning algorithms in forward seismic models
AU - Churochkin, I.
AU - Volkova, A.
AU - Gavrilova, E.
AU - Bukhanov, N.
AU - Butorin, A.
AU - Rukavishnikov, V.
PY - 2019/6/3
Y1 - 2019/6/3
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85073632095&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073632095&partnerID=8YFLogxK
M3 - Conference contribution
T3 - 81st EAGE Conference and Exhibition 2019
BT - 81st EAGE Conference and Exhibition 2019
PB - EAGE Publishing BV
T2 - 81st EAGE Conference and Exhibition 2019
Y2 - 3 June 2019 through 6 June 2019
ER -