← Back to Sessions

Automatic Speech Recognition Predicts Contemporaneous Earthquake Fault Displacement

Description: 

Significant progress has been made in probing the state of an earthquake fault by applying machine learning to continuous seismic waveforms. The breakthroughs were originally obtained from laboratory shear experiments and numerical simulations of fault shear, then successfully extended to slow-slipping faults. The elusive step is translating the laboratory analogy to seismogenic stick-slip fault motion associated with earthquakes on active fault systems that produce strong, damaging ground motions. Here we apply the Wav2Vec-2.0 self-supervised framework for automatic speech recognition to continuous seismic signals emanating from a sequence of moderate magnitude earthquakes during the 2018 caldera collapse at the Kīlauea volcano on the island of Hawai'i. This sequence of repeating moderate magnitude earthquakes offers an excellent case study to determine if the advancements developed in the lab are applicable to this tectonic environment. We pre-train the automatic speech recognition Wav2Vec-2.0 model using caldera seismic waveforms and augment the model architecture to predict contemporaneous surface displacement during the caldera collapse sequence, a proxy for fault displacement. We find the model displacement predictions to be excellent. The model is adapted for near-future prediction information and found hints of prediction capability, but the results are not robust. The results demonstrate that earthquake faults emit seismic signatures in a similar manner to laboratory and numerical simulation faults, and artificial intelligence models developed for encoding audio of speech may have important applications in studying active fault zones.

Session: Predictability of Seismic and Aseismic Slip: From Basic Science to Operational Forecasts - I

Type: Oral

Date: 4/16/2025

Presentation Time: 05:30 PM (local time)

Presenting Author: Christopher

Student Presenter: No

Invited Presentation: 

Poster Number:

Authors