Delft University of Technology
Dirk J. (Eric) Verschuur (born in 1964) received his M.Sc. degree in 1986 and his Ph.D degree (honors) in 1991 from Delft University of Technology (DUT), both in applied physics.
His Ph.D. thesis focused on the surface-related multiple elimination (SRME) methodology. Currently, he is an associate professor at the DUT, at the section “Computational Imaging” within the ImPhys department. Since 2016 he is the Program director of the Delphi research consortium, which is currently sponsored by 26 companies that are mostly active within the energy market. Within Delphi research is carried in the area of geo-imaging since the early 1980’s. His main interests are wavefield modeling, data processing, imaging and inversion techniques.
In 1997 he received SEG’s J. Clarence Karcher award and in 2006 he was awarded with the Virgil Kauffman Gold medal from the SEG. He has been selected as the EAGE lecturer for the Education tour 2006 with a one-day course on multiple removal.
The popularity of the use of Machine Learning (ML) algorithms, such as neural networks, in geophysics has been increased hugely in recent years. This is due to access to faster computers, ready-to-use ML software and better machine learning approaches. The big question is: what will finally be the future of such ML algorithms? Will ML algorithms be able to derive the high-resolution subsurface parameters directly from the raw data? Should we replace all imaging and inversion methodologies by a huge amount of forward modeling exercises and use the ML approach to find the answer? I personally don’t think this will happen soon and also is probably not smart too. Often we see that when we replace deterministic approaches by ML algorithms, we basically start from scratch again, throw away all developed methodologies and finally hope that the ML will outperform the deterministic version, either in quality or speed or both. Therefore, I think it is better to embark as much as possible on deterministic methodologies, and try to improve them by ML methods. So they should augment the current approach and fill in their limitations. E.g. ML may not to be good enough to replace full blown 3D FWI, but it may provide a good initial model or improve its gradient, enabling better or faster convergence. It may not replace surface-related multiple prediction, but it can help fill in the missing data or guide the adaptive subtraction, as shown by examples. The use of ML can become even more exciting if we combine it with new data acquisition approaches: e.g. acquire one part of the survey in high-resolution mode, such it can serve as a learning data for the rest of the survey! Thus, I believe that - in combination with good geophysical domain knowledge - ML will play an increasingly prominent role to fill in those gaps that current deterministic methods or physical models cannot.