Automatic Extraction of a Generalized Physics‐Based Feature From Time‐Lapse Active Source Ultrasonic Waveforms for Prediction of Shear Stress in Laboratory Friction Experiments
- 1Department of Engineering Science and Mechanics The Pennsylvania State University University Park PA USA
- 2Department of Computer Science and Engineering The Pennsylvania State University University Park PA USA
Abstract
Physics‐based handcrafted features, such as P‐wave amplitude derived from early parts of active source ultrasonic waveforms, successfully predict shear stress evolution. This study investigates whether feature extraction can be automated by leveraging full active source ultrasonic waveforms recorded during a laboratory friction experiment. We compare four models: handcrafted feature‐driven model (reference), convolutional neural network (CNN) model, explainable data‐driven (XDD) model, and a model with an explainable generalized physics‐based (XPG) feature. The reference model uses the spectral amplitude of the P‐wave packet calculated at center frequency, while the CNN relies on convolutional and pooling layers for feature extraction. The XDD model combines CNN feature extraction with long short‐term memory units and an attention layer to capture feature time history and significance. The novel XPG extracts a generalized spectral amplitude feature through a custom multilayer perceptron designed to learn linear combination of signals' spectral amplitudes without prescribing specific frequencies. Although CNN‐extracted features resemble handcrafted ones, both the CNN and XDD models underperform compared to the reference, while the XPG model outperforms all others. The attention mechanism in the XDD model highlights the importance of first P‐wave packet, whereas the XPG model also identifies later‐arriving shear wave packet as significant. The prediction improvement by inclusion of shear waves is physically intuitive; S‐waves have particle motion polarized in the direction of fault shear and are likely more sensitive to frictional state than P‐waves. This work demonstrates the value of incorporating domain knowledge into automatic feature extraction with potential applications in seismic data analysis.
Related
- Relative dispersion and eddy diffusivity in laboratory experiments of β-plane turbulence
- Do laboratory acclimation experiments predict field responses? Cold tolerance and metabolomic divergence in Drosophila suzukii
- Laboratory Experiments Identify Meteoritic Organic Precursors for Chlorinated Compounds Detected by the Sample Analysis at Mars (SAM) Instrument at Gale Crater
- Mobility of dry granular flows over contrasting erodible bed materials in laboratory experiments
- Towards generalized hydrological forecasting using transformer models for 120 h streamflow prediction
BibTeX
@article{borate2026automatic,
title = {{Automatic Extraction of a Generalized Physics‐Based Feature From Time‐Lapse Active Source Ultrasonic Waveforms for Prediction of Shear Stress in Laboratory Friction Experiments}},
author = {Prabhav Borate and Jacques Rivière and Daniel Kifer and Parisa Shokouhi},
journal = {Journal of Geophysical Research: Machine Learning and Computation},
year = {2026},
month = oct,
doi = {10.1029/2026jh001256},
url = {https://doi.org/10.1029/2026jh001256},
note = {CC BY},
}
RIS
TY - JOUR
TI - Automatic Extraction of a Generalized Physics‐Based Feature From Time‐Lapse Active Source Ultrasonic Waveforms for Prediction of Shear Stress in Laboratory Friction Experiments
AU - Prabhav Borate
AU - Jacques Rivière
AU - Daniel Kifer
AU - Parisa Shokouhi
PY - 2026
DA - 2026/10/28
JO - Journal of Geophysical Research: Machine Learning and Computation
DO - 10.1029/2026jh001256
UR - https://doi.org/10.1029/2026jh001256
AB - Physics‐based handcrafted features, such as P‐wave amplitude derived from early parts of active source ultrasonic waveforms, successfully predict shear stress evolution. This study investigates whether feature extraction can be automated by leveraging full active source ultrasonic waveforms recorded during a laboratory friction experiment. We compare four models: handcrafted feature‐driven model (reference), convolutional neural network (CNN) model, explainable data‐driven (XDD) model, and a model with an explainable generalized physics‐based (XPG) feature. The reference model uses the spectral amplitude of the P‐wave packet calculated at center frequency, while the CNN relies on convolutional and pooling layers for feature extraction. The XDD model combines CNN feature extraction with long short‐term memory units and an attention layer to capture feature time history and significance. The novel XPG extracts a generalized spectral amplitude feature through a custom multilayer perceptron designed to learn linear combination of signals' spectral amplitudes without prescribing specific frequencies. Although CNN‐extracted features resemble handcrafted ones, both the CNN and XDD models underperform compared to the reference, while the XPG model outperforms all others. The attention mechanism in the XDD model highlights the importance of first P‐wave packet, whereas the XPG model also identifies later‐arriving shear wave packet as significant. The prediction improvement by inclusion of shear waves is physically intuitive; S‐waves have particle motion polarized in the direction of fault shear and are likely more sensitive to frictional state than P‐waves. This work demonstrates the value of incorporating domain knowledge into automatic feature extraction with potential applications in seismic data analysis.
SN - 2993-5210
ER -