Traveltime computation using a supervised learning approach

Abstract
In real-time microseismic monitoring, the ability to efficientlycompute source-receiver traveltimes can help in significantlyspeeding up the model calibration and hypocenter determina-tion processes, thus ensuring timely information about the sub-surface fractures for use in effective decision making. Here,we present a supervised-learning based traveltime computationapproach for layered 1D velocity models. First, we generatenumerous synthetic traveltime examples from a combinationof source locations and layered subsurface models, coveringa broad range of realistic P-wave velocities (2500–5000 m/s).Next, we train a multi-layered feed-forward neural network us-ing the training set containing source locations and velocitiesas input and traveltimes as corresponding labels. By doing so,we aim for a neural-network model that is trained only onceand can be applied to a wide range of subsurface velocitiesas well as source-receiver positions to predict fast and accu-rate traveltimes. We apply the trained model on numeroustest examples to validate the accuracy and speed of the pro-posed method. Based on the comparisons with acoustic finite-difference modeling and a ray-shooting method, we show thatthe trained model can provide faster and reasonably accuratetraveltimes for any realistic model scenario within the trainedvelocity range.

Citation
Akram, J., Peter, D. B., Eaton, D. W., & Zhang, H. (2021). Traveltime computation using a supervised learning approach. First International Meeting for Applied Geoscience & Energy Expanded Abstracts. doi:10.1190/segam2021-3583890.1

Acknowledgements
This work was made possible in part through CFREF support for the Global Research Initiative at the University of Calgary.The authors would also like to thank King Abdullah University of Science and Technology (KAUST) for financial support.

Publisher
Society of Exploration Geophysicists

DOI
10.1190/segam2021-3583890.1

Additional Links
https://library.seg.org/doi/10.1190/segam2021-3583890.1

Permanent link to this record