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

Yue, Enjiang; Qin, Mengjiao; Hu, Linshu; Bryan, Riel; Wu, Sensen; Du, Zhenhong

doi:https://doi.org/10.5194/gmd-18-6275-2025

Articles | Volume 18, issue 18

https://doi.org/10.5194/gmd-18-6275-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-18-6275-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 18

Model description paper

|

24 Sep 2025

Model description paper |

| 24 Sep 2025

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

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

Supplement

https://doi.org/10.5194/gmd-18-6275-2025-supplement

Data sets

Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress Laurenti et al. https://doi.org/10.1016/j.epsl.2022.117825

Bifurcations at the stability transition of earthquake faulting Mele Veedu https://doi.org/10.17605/OSF.IO/9DQH7

Deterministic and stochastic chaos characterize laboratory earthquakes Gualandi et al. https://doi.org/10.1016/j.epsl.2023.117995

Model code and software

INGVLab Yue https://doi.org/10.5281/zenodo.13123381

Short summary

Laboratory earthquakes are an 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 laboratory experiments with different slip behaviours. It shows stable predictions in modelling slip moments, intervals, and predictions beyond trained horizons, especially for challenging slip scenarios, which is crucial for cyclic geophysical process such as seismicity.