Parisa Shokouhi

Parisa Shokouhi

Auto-generated profile, based on publicly available information

Parisa Shokouhi

Department of Engineering Science and Mechanics Pennsylvania State University University Park Pa USA

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2021 in Journal of Contaminant Hydrology
Verified
Journal Article
Closed access
PSParisa Shokouhi
Parisa Shokouhi
VKVikas Kumar
Vikas Kumar
SPSumedha Prathipati
Sumedha Prathipati
SHSeyyed A. Hosseini
Seyyed A. Hosseini
CGClyde Lee Giles
Clyde Lee Giles
DKDaniel Kifer
Daniel Kifer

21 June 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
PBPrabhav Borate
Prabhav Borate
JRJacques Rivière
Jacques Rivière
CMChris Marone
Chris Marone
AMAnkur Mali
Ankur Mali
DKDaniel Kifer
Daniel Kifer
PSParisa Shokouhi
Parisa Shokouhi
Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and temporal evolution of fault zone elastic properties. Remarkably, these results come from purely data-driven models trained with large datasets. Such data are equivalent to centuries of fault motion rendering application to tectonic faulting unclear. In addition, the underlying physics of such predictions is poorly understood. Here, we address scalability using a novel Physics-Informed Neural Network (PINN). Our model encodes fault physics in the deep learning loss function using time-lapse ultrasonic data. PINN models outperform data-driven models and significantly improve transfer learning for small training datasets and conditions outside those used in training. Our work suggests that PINN offers a promising path for machine learning-based failure prediction and, ultimately for improving our understanding of earthquake physics and prediction.

18 December 2017 in Applied Physics Letters
Verified
Journal Article
Closed access
PSParisa Shokouhi
Parisa Shokouhi
JRJacques Rivière
Jacques Rivière
RGRobert A. Guyer
Robert A. Guyer
PJPaul A. Johnson
Paul A. Johnson
Dynamic acousto-elastic testing, a pump-probe scheme, is employed to investigate the recovery of consolidated granular media systems from the non-equilibrium steady state established by a pump strain field. This measurement scheme makes it possible to follow the recovery from the non-equilibrium steady state over many orders of magnitude in time. The recovery is described with a relaxation time spectrum that is found to be independent of the amplitude of the non-equilibrium steady state (pump amplitude) and of the environment in which samples reside. The non-equilibrium steady state and its slow recovery are the laboratory realization of phenomena that are found in many physical systems of practical importance.

6 March 2019 in Seismological Research Letters
Verified
Journal Article
Closed access
PDF file
DBDavid C. Bolton
David C. Bolton
PSParisa Shokouhi
Parisa Shokouhi
BRBertrand Rouet-Leduc
Bertrand Rouet-Leduc
CHClaudia Hulbert
Claudia Hulbert
JRJacques Rivière
Jacques Rivière
PJPaul A. Johnson
Paul A. Johnson
Recent work shows that machine learning (ML) can predict failure time and other aspects of laboratory earthquakes using the acoustic signal emanating from the fault zone. These approaches use supervised ML to construct a mapping between features of the acoustic signal and fault properties such as the instantaneous frictional state and time to failure. We build on this work by investigating the potential for unsupervised ML to identify patterns in the acoustic signal during the laboratory seismic cycle and precursors to labquakes. We use data from friction experiments showing repetitive stick‐slip failure (the lab equivalent of earthquakes) conducted at constant normal stress (2.0 MPa) and constant shearing velocity (⁠10  μm/s⁠). Acoustic emission signals are recorded continuously throughout the experiment at 4 MHz using broadband piezoceramic sensors. Statistical features of the acoustic signal are used with unsupervised ML clustering algorithms to identify patterns (clusters) within the data. We find consistent trends and systematic transitions in the ML clusters throughout the seismic cycle, including some evidence for precursors to labquakes. Further work is needed to connect the ML clustering patterns to physical mechanisms of failure and estimates of the time to failure.

30 May 2019 in Journal of Geophysical Research: Solid Earth
Verified
Journal Article
Open access
PDF file
LOLev A. Ostrovsky
Lev A. Ostrovsky
ALA. Lebedev
A. Lebedev
JRJ. Riviere
J. Riviere
PSParisa Shokouhi
Parisa Shokouhi
CWC. Wu
C. Wu
PJP. A. Johnson
P. A. Johnson
We present a theoretical model and experimental evidence of the long‐time relaxation process (slow dynamics) in rocks and other geomaterials following a dynamic wave excitation, at scales ranging from the laboratory to the Earth. The model is based on the slow recovery of an ensemble of grain contacts and asperities broken by a mechanical impact. It includes an Arrhenius‐type equation for recovery of the metastable, broken contacts. The model provides a characteristic size of the broken contacts (order 10−9 m) and predicts that their number increases with impact amplitude. Theoretical results are in good agreement with the laboratory and field data in that they predict both the logarithmic law of recovery rate and deviations from this law.

19 June 2021 in Geophysical Research Letters
Verified
Journal Article
Open access
PDF file
PSParisa Shokouhi
Parisa Shokouhi
VGVrushali Girkar
Vrushali Girkar
JRJacques Rivière
Jacques Rivière
SSSrisharan Shreedharan
Srisharan Shreedharan
CMChris Marone
Chris Marone
DKDaniel Kifer
Daniel Kifer
Small changes in seismic wave properties foretell frictional failure in laboratory experiments and in some cases on seismic faults. Such precursors include systematic changes in wave velocity and amplitude throughout the seismic cycle. However, the relationships between wave features and shear stress are complex. Here, we use data from lab friction experiments that include continuous measurement of elastic waves traversing the fault and build data‐driven models to learn these complex relations. We demonstrate that deep learning models accurately predict the timing and size of laboratory earthquakes based on wave features. Additionally, the transportability of models is explored by using data from different experiments. Our deep learning models transfer well to unseen datasets providing high‐fidelity models with much less training. These prediction methods can be potentially applied in the field for earthquake early warning in conjunction with long‐term time‐lapse seismic monitoring of crustal faults, CO2 storage sites and unconventional energy reservoirs.