KAUST DepartmentComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Earth Science and Engineering Program
Physical Science and Engineering (PSE) Division
Seismic Wave Analysis Group
Permanent link to this recordhttp://hdl.handle.net/10754/666644
MetadataShow full item record
AbstractIn salt-affected regions, conventional full-waveform inversion (FWI) is doomed to fail if there is no prior information of the salt body. Recent studies suggested regularizing the inversion by implementing an automatic flooding using total variation (TV) and Hinge loss functions. We generalize this approach and introduce a family of functions known as activation functions in the machine learning discipline that can be used to implement automatic flooding in a similar way. In particular, we investigate the automatic flooding using a sigmoid, tanh and exponential linear unit (Elu) functions and apply them for salt body reconstruction on the BP model and report their performance.
CitationAlali, A., Kazei, V., Altaf, B., Zhang, X., & Alkhalifah, T. (2020). Time-Lapse Cross-Equalization by Deep Learning. EAGE 2020 Annual Conference & Exhibition Online. doi:10.3997/2214-4609.202011720
SponsorsWe would like to extend our appreciation to Saudi Aramco for sponsoring this project especially Philippe Nivlet and Robert Smith for the helpful discussion. We also thank King Abdullah University of Science & Technology (KAUST) and the members of Seismic Wave Analysis Group (SWAG) for their support.
Conference/Event nameEAGE 2020 Annual Conference & Exhibition Online