Preprints
https://doi.org/10.5194/gmd-2024-46
https://doi.org/10.5194/gmd-2024-46
Submitted as: model description paper
 | 
22 Mar 2024
Submitted as: model description paper |  | 22 Mar 2024
Status: this preprint is currently under review for the journal GMD.

A dynamic informed deep learning method for future estimation of laboratory stick-slip

Enjiang Yue, Mengjiao Qin, Linshu Hu, Sensen Wu, and Zhenhong Du

Abstract. Fault activities modelling holds vital importance for earthquake monitoring, risk management, and early alert. Studies on laboratory earthquakes are instrumental in the modelling of natural fault ruptures and in enhancing our grasp of natural earthquake dynamics. Recently, deep learning methods have been proven effective in predicting instantaneous fault stress in laboratory settings and slow slip events on Earth. However, these methods have struggled to conduct steady future prediction lacking grasping of the complex dynamics of highly nonlinear laboratory fault slip systems. Addressing this, we introduce the Hankel Koopman Auto-encoder (HKAE), a novel method inspired by dynamical system theories. HKAE performs dynamic modelling of laboratory fault system and provides a continuous estimation of the future state of the system. It has been deployed on experiments with different slip behaviours and shows superior ability to predict shear stress variation during a slip cycle and also slip activities in longer-term seismic cycles. The HKAE model surpasses conventional time series prediction deep learning methods, showing superior statistical evaluation metrics like RMSE and R2 with two prediction horizons. Meanwhile, we find that the HKAE can model the slip dynamics better than purely statistical modelling, as evidenced by its more accurate modelling of the slip timing, slip cycle intervals and its ability to summarize the quasi-periodic dynamics as an operator from a small number of samples to generate more robust beyond-horizon prediction. The capability of HKAE to decompose and model complex temporal dynamics highlights its potential in and sparse-observed geophysical system with quasi-periodic characteristics like natural fault activities.

Enjiang Yue, Mengjiao Qin, Linshu Hu, Sensen Wu, and Zhenhong Du

Status: open (until 23 May 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Enjiang Yue, Mengjiao Qin, Linshu Hu, Sensen Wu, and Zhenhong Du

Model code and software

Hankel Koopman Auto Encoder Enjiang Yue, Mengjiao Qin, Linshu Hu, Sensen Wu, and Zhenhong Du https://zenodo.org/records/10846361

Enjiang Yue, Mengjiao Qin, Linshu Hu, Sensen Wu, and Zhenhong Du

Viewed

Total article views: 204 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
166 22 16 204 18 6
  • HTML: 166
  • PDF: 22
  • XML: 16
  • Total: 204
  • BibTeX: 18
  • EndNote: 6
Views and downloads (calculated since 22 Mar 2024)
Cumulative views and downloads (calculated since 22 Mar 2024)

Viewed (geographical distribution)

Total article views: 200 (including HTML, PDF, and XML) Thereof 200 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 20 Apr 2024
Download
Short summary
Laboratory earthquakes is important means to understand natural earthquakes while previous work focused on transient prediction, lacking future prediction capability. We propose a method and evaluate on data from lab experiments with different slip behaviors. It outperforms state-of-the-art methods in modeling slip moments, intervals and predictions beyond trained horizons especially for challenging slip scenarios, which is crucial for quasi-periodic geophysical process like seismicity.