Deep Neural Networks: Ready for a Day to Day Use in Seismic Interpretation?
S. Guillon, F. Joncour, P. Goutorbe and L. Castanie
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 ( 3.83Mb )
Price: € 20
Seismic interpretation is a complex and tedious task requiring intensive time-consuming manual interpretation. In the last recent years Convolutional Neural Networks (CNNs) have been introduced to solve several interpretation challenges. Promising results have been already presented for salt, horizons or faults interpretation. The main purpose is to transform long manual interpretation tasks to a few hours of machine learning computation. Hence, geoscientists will have more time to focus on high added value tasks that will help to better understand the subsurface. In this paper, we highlight the criticality of data diversity during the training to get a robust and flexible model. Then we investigate the potential gains for the seismic interpreters in term of quality and object extraction.