Predicting the proximity to macroscopic failure using local strain populations from dynamic in situ X-ray tomography triaxial compression experiments on rocks

Journal Article · Fri May 22 00:00:00 EDT 2020 · Earth and Planetary Science Letters

DOI:https://doi.org/10.1016/j.epsl.2020.116344· OSTI ID:1803015

McBeck, Jessica ^[1]; Aiken, John Mark ^[2]; Ben-Zion, Yehuda ^[3]; Renard, Francois ^[4]

---

1. Univ. of Oslo (Norway); OSTI
2. Univ. of Oslo (Norway); Michigan State Univ., East Lansing, MI (United States)
3. Univ. of Southern California, Los Angeles, CA (United States)
4. Univ. of Oslo (Norway); Univ. of Grenoble Alpes, Saint-Martin-d-Heres (France)

Predicting the proximity of large-scale dynamic failure is a critical concern in the engineering and geophysical sciences. Here we use evolving contractive, dilatational, and shear strain deformation preceding failure in dynamic X-ray tomography experiments to examine which strain components best predict the proximity to failure. We develop machine learning models to predict the proximity to failure using time series of three-dimensional local incremental strain tensor fields acquired in rock deformation experiments under stress conditions of the upper crust. Three-dimensional scans acquired in situ throughout triaxial compression experiments provide a distribution of density contrasts from which we estimate the three-dimensional incremental strain that accumulates between each scan acquisition. Training machine learning models on multiple experiments of six rock types provides suites of feature importance that indicate the predictive power of each feature. Comparing the average importance of groups of features that include information about each strain component quantifies the ability of the contractive, dilatational and shear strain to predict the proximity of macroscopic failure. A total of 24 models of four machine learning algorithms with six rock types indicate that 1) the dilatational strain provides the best predictive power of the strain components, and 2) the intermediate values (25th-75th percentile) of the strain population provide the best predictive power of the statistics of the strain populations. In addition, the success of the predictions of models trained on one rock type and tested on other rock types quantifies the similarities and differences of the precursory strain accumulation process in the six rock types. These similarities suggest the potential existence of a unified theory of brittle rock deformation for a range of rock types.

• Research Organization: University of Southern California, Los Angeles, CA (United States)
• Sponsoring Organization: USDOE; USDOE Office of Science (SC)
• Grant/Contract Number: SC0016520
• OSTI ID: 1803015
• Alternate ID(s): OSTI ID: 1630449
• Journal Information: Earth and Planetary Science Letters, Journal Name: Earth and Planetary Science Letters Journal Issue: C Vol. 543; ISSN 0012-821X
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

58 GEOSCIENCES
geochemistry & geophysics
machine learning
strain localization
tomography
triaxial compression