University of Cambridge > Talks.cam > Data Intensive Science Seminar Series > Subsurface imaging with deep learning

Subsurface imaging with deep learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact James Fergusson.

To see what is underneath the surface of the earth, we can drill a borehole, or perform what is called “seismic imaging”. Whereas boreholes give very localized information, seismic images can result in tens of thousands square kilometres being digitally imaged down to several kilometres, and analysed for rock strata, structures and fluids such as oil and gas. Such experiments use multi-sensor arrays to listen to the energy reflected from the earth’s interior much like a bat uses ultrasonic echo-location or a CT scanner uses X-rays to image inside our bodies. The physics of wave-propagation is well understood, in theory, and yet seismic imaging is a hard problem, computationally intensive, and often the solution is under-determined, despite TBytes of field data available for analysis. Could deep learning be a game changer?

This talk is part of the Data Intensive Science Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity