Diagnosing and Breaking Amplitude Suppression in Seismic Phase Picking Through Adversarial Shape Learning
This addresses a specific issue in seismic data analysis for geophysics, offering an incremental improvement over existing deep learning methods.
The paper tackled the problem of amplitude suppression in seismic phase picking, where S-wave predictions fail to detect subtle onsets due to biases in CNNs and loss functions, and by implementing a conditional GAN framework with shape constraints, it achieved a 64% increase in effective S-phase detections.
Deep learning has revolutionized seismic phase picking, yet a paradox persists: high signal-to-noise S-wave predictions consistently fail to cross detection thresholds, oscillating at suppressed amplitudes. We identify this previously unexplained phenomenon as amplitude suppression, which we diagnose through analyzing training histories and loss landscapes. Three interacting factors emerge: S-wave onsets exhibit high temporal uncertainty relative to high-amplitude boundaries; CNN's bias toward sharp amplitude changes anchors predictions to these boundaries rather than subtle onsets; and point-wise Binary Cross-Entropy (BCE) loss lacks lateral corrective forces, providing only vertical gradients that suppress amplitude while temporal gaps persist. This geometric trap points to a shape-then-align solution where stable geometric templates must precede temporal alignment. We implement this through a conditional GAN framework by augmenting conventional BCE training with a discriminator that enforces shape constraints. Training for 10,000 steps, this achieves a 64% increase in effective S-phase detections. Our framework autonomously discovers target geometry without a priori assumptions, offering a generalizable solution for segmentation tasks requiring precise alignment of subtle features near dominant structures.