Focal mechanism determination by location-constrained deep learning

What is it about?

Accurate and rapid determination of focal mechanism solutions is essential for real-time seismic monitoring. Our research introduces a new technique that employs a location-constrained deep learning algorithm to determine these solutions more effectively. By using aligned P-wave data, along with azimuth and take-off angle as inputs, we narrow the solution space and reduce reliance on detailed velocity models. The model, trained on synthetic data, was successfully applied to field data. Both tests on numerical datasets and real-world applications show that our method is effective, making it highly promising for real-time microseismic monitoring.

Featured Image

Photo by Zbynek Burival on Unsplash

Photo by Zbynek Burival on Unsplash

Why is it important?

Our findings show that by constraining known source locations, our model becomes less sensitive to velocity model errors, improving its reliability and effectiveness in applying to field data.