Characterization of Acoustic Emissions From Analogue Rocks Using Sparse Regression‐DMDc

Moisture loss in rock is known to generate acoustic emissions (AE). Phenomena that result in AE during drying are related to the movement of fluids through the pores and induced‐cracks that arise from differential mineral shrinkage, especially in clay‐bearing rock. AE from the movement of fluids occurs from the reconfiguration of fluid interfaces during drying, while AE from mineral shrinkage involves the debonding within or between minerals. Here, analogue rock samples were used to examine the differences in the AE signatures when one or both AE source‐types are present. An unsupervised sparse regression model, Dynamic Mode Decomposition with control, that extends Dynamic Mode Decomposition is used to characterize the AE signals recorded during the drying of porous analogue rock samples fabricated with ordinary Portland cement, with and without clay. This method can effectively and accurately reconstruct acoustic signals emitted from samples that only experience moisture loss without cracking. However, the method struggles to reconstruct signals from samples with intricate crack networks that formed during drying because AE generating mechanisms can emit contemporaneously, and the resulting waves propagate through drying‐induced cracks that can lead to multiple internal reflections. Thus, the differential reconstruction accuracy of time series generated by different underlying physical processes provides a robust filter for reducing large data catalogs. In general, both dynamics and sparse initiating events are learned directly from data and this method exposes a data hierarchy based on the complexity of the intrinsic dynamics. Plain Language Summary Moisture loss from porous media, in particular clay‐rich rocks, can generate sound known as acoustic emissions (AE), as water moves through the pore structure and cracking caused by mineral shrinkage from dehydration occurs. Unique information about processes giving rise to these sounds and the changes in the material can be extracted from the AE data. To examine the differences in these signals, distinct sample types were fabricated with ordinary Portland cement, and in some instances with clay. A machine learning method requiring no prior information that is informed by the data was used to sort through and identify the AE signals. This method works best for AE signals emitted from samples that only experience movement of fluids with no cracking. When both processes occur, the AE signals contain overlapping