What question did this study set out to answer?

To improve the accuracy of microseismic source location using a physics-constrained deep learning approach.

Deep Learning-based Microseismic Source Location with Joint Constraints of Source Imaging and Traveltime Residuals

View Full Paper

Ask AI

Bookmark

To improve the accuracy of microseismic source location using a physics-constrained deep learning approach.
Developed a deep learning model integrating physical principles of CCS imaging.
Utilized a joint loss function for source imaging quality and traveltime consistency.
Conducted synthetic experiments on the Marmousi velocity model.
Reduced mean absolute error from 34.09 m to 27.91 m compared to purely data-driven methods.
Achieved a maximum error reduction from 280.18 m to 130.38 m, a 53.5% decrease.
Provided single-event imaging prediction in 0.04 s, 75-fold faster than conventional CCS at 3 s.

Authors

No takes yet. Share an insight, caveat, or question.

Randomized trial demonstrates improved accuracy in microseismic source location, highlighting deep learning's potential in real-time monitoring.

Li et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved accuracy in microseismic source location, highlighting deep learning's potential in real-time monitoring.