1
|
Yu P, Mali A, Velaga T, Bi A, Yu J, Marone C, Shokouhi P, Elsworth D. Crustal permeability generated through microearthquakes is constrained by seismic moment. Nat Commun 2024; 15:2057. [PMID: 38448426 PMCID: PMC10918097 DOI: 10.1038/s41467-024-46238-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2023] [Accepted: 02/20/2024] [Indexed: 03/08/2024] Open
Abstract
We link changes in crustal permeability to informative features of microearthquakes (MEQs) using two field hydraulic stimulation experiments where both MEQs and permeability evolution are recorded simultaneously. The Bidirectional Long Short-Term Memory (Bi-LSTM) model effectively predicts permeability evolution and ultimate permeability increase. Our findings confirm the form of key features linking the MEQs to permeability, offering mechanistically consistent interpretations of this association. Transfer learning correctly predicts permeability evolution of one experiment from a model trained on an alternate dataset and locale, which further reinforces the innate interdependency of permeability-to-seismicity. Models representing permeability evolution on reactivated fractures in both shear and tension suggest scaling relationships in which changes in permeability ( Δ k ) are linearly related to the seismic moment ( M ) of individual MEQs as Δ k ∝ M . This scaling relation rationalizes our observation of the permeability-to-seismicity linkage, contributes to its predictive robustness and accentuates its potential in characterizing crustal permeability evolution using MEQs.
Collapse
Affiliation(s)
- Pengliang Yu
- EMS Energy Institute, G3 Center and Department of Geosciences, Pennsylvania State University, University Park, USA.
- EMS Energy Insititute, G3 Center and Department of Energy and Mineral Engineering, Pennsylvania State University, University Park, USA.
| | - Ankur Mali
- Department of Computer Science & Engineering, University of South Florida, Tampa, FL, USA
| | - Thejasvi Velaga
- Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA
| | - Alex Bi
- Pennsylvania State University, University Park, PA, USA
| | - Jiayi Yu
- EMS Energy Insititute, G3 Center and Department of Energy and Mineral Engineering, Pennsylvania State University, University Park, USA
| | - Chris Marone
- EMS Energy Institute, G3 Center and Department of Geosciences, Pennsylvania State University, University Park, USA
- Dipartimento di Scienze della Terra, La Sapienza Università di Roma, Roma, Italy
| | - Parisa Shokouhi
- Department of Engineering Science and Mechanics, Pennsylvania State University, University Park, PA, USA
| | - Derek Elsworth
- EMS Energy Institute, G3 Center and Department of Geosciences, Pennsylvania State University, University Park, USA.
- EMS Energy Insititute, G3 Center and Department of Energy and Mineral Engineering, Pennsylvania State University, University Park, USA.
| |
Collapse
|
2
|
Borate P, Rivière J, Marone C, Mali A, Kifer D, Shokouhi P. Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes. Nat Commun 2023; 14:3693. [PMID: 37344479 DOI: 10.1038/s41467-023-39377-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Accepted: 06/07/2023] [Indexed: 06/23/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Prabhav Borate
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, PA, 16802, USA
| | - Jacques Rivière
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, PA, 16802, USA
| | - Chris Marone
- Dipartimento di Scienze della Terra, La Sapienza Università di Roma, Roma, Italy
- Department of Geosciences, The Pennsylvania State University, University Park, PA, 16802, USA
| | - Ankur Mali
- Department of Computer Science and Engineering, University of South Florida, Tampa, FL, 33620, USA
| | - Daniel Kifer
- Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA
| | - Parisa Shokouhi
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, PA, 16802, USA.
| |
Collapse
|
3
|
Giraldo Guzman D, Pillarisetti LSS, Sridhar S, Lissenden CJ, Frecker M, Shokouhi P. Design of resonant elastodynamic metasurfaces to control S 0 Lamb waves using topology optimization. JASA Express Lett 2022; 2:115601. [PMID: 36456372 DOI: 10.1121/10.0015123] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
Control of guided waves has applications across length scales ranging from surface acoustic wave devices to seismic barriers. Resonant elastodynamic metasurfaces present attractive means of guided wave control by generating frequency stop-bandgaps using local resonators. This work addresses the systematic design of these resonators using a density-based topology optimization formulated as an eigenfrequency matching problem that tailors antiresonance eigenfrequencies. The effectiveness of our systematic design methodology is presented in a case study, where topologically optimized resonators are shown to prevent the propagation of the S0 wave mode in an aluminum plate.
Collapse
Affiliation(s)
- Daniel Giraldo Guzman
- Department of Mechanical Engineering, The Pennsylvania State University, University Park, Pennsylvania 16801, USA
| | - Lalith Sai Srinivas Pillarisetti
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, Pennsylvania 16801, USA , , , , ,
| | - Sashank Sridhar
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, Pennsylvania 16801, USA , , , , ,
| | - Cliff J Lissenden
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, Pennsylvania 16801, USA , , , , ,
| | - Mary Frecker
- Department of Mechanical Engineering, The Pennsylvania State University, University Park, Pennsylvania 16801, USA
| | - Parisa Shokouhi
- Department of Engineering Science and Mechanics, The Pennsylvania State University, University Park, Pennsylvania 16801, USA , , , , ,
| |
Collapse
|
4
|
Bolton DC, Shreedharan S, McLaskey GC, Rivière J, Shokouhi P, Trugman DT, Marone C. The High-Frequency Signature of Slow and Fast Laboratory Earthquakes. J Geophys Res Solid Earth 2022; 127:e2022JB024170. [PMID: 35864884 PMCID: PMC9287021 DOI: 10.1029/2022jb024170] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/06/2022] [Revised: 05/20/2022] [Accepted: 05/23/2022] [Indexed: 06/15/2023]
Abstract
Tectonic faults fail through a spectrum of slip modes, ranging from slow aseismic creep to rapid slip during earthquakes. Understanding the seismic radiation emitted during these slip modes is key for advancing earthquake science and earthquake hazard assessment. In this work, we use laboratory friction experiments instrumented with ultrasonic sensors to document the seismic radiation properties of slow and fast laboratory earthquakes. Stick-slip experiments were conducted at a constant loading rate of 8 μm/s and the normal stress was systematically increased from 7 to 15 MPa. We produced a full spectrum of slip modes by modulating the loading stiffness in tandem with the fault zone normal stress. Acoustic emission data were recorded continuously at 5 MHz. We demonstrate that the full continuum of slip modes radiate measurable high-frequency energy between 100 and 500 kHz, including the slowest events that have peak fault slip rates <100 μm/s. The peak amplitude of the high-frequency time-domain signals scales systematically with fault slip velocity. Stable sliding experiments further support the connection between fault slip rate and high-frequency radiation. Experiments demonstrate that the origin of the high-frequency energy is fundamentally linked to changes in fault slip rate, shear strain, and breaking of contact junctions within the fault gouge. Our results suggest that having measurements close to the fault zone may be key for documenting seismic radiation properties and fully understanding the connection between different slip modes.
Collapse
Affiliation(s)
| | | | - Gregory C. McLaskey
- Department of Civil and Environmental EngineeringCornell UniversityIthacaNYUSA
| | - Jacques Rivière
- Department of Engineering Science and MechanicsPennsylvania State UniversityUniversity ParkPAUSA
| | - Parisa Shokouhi
- Department of Engineering Science and MechanicsPennsylvania State UniversityUniversity ParkPAUSA
| | | | - Chris Marone
- Department of GeosciencesPennsylvania State UniversityUniversity ParkPAUSA
- Dipartimento di Scienze della TerraLa Sapienza Università di RomaRomeItaly
| |
Collapse
|
5
|
Shokouhi P, Kumar V, Prathipati S, Hosseini SA, Giles CL, Kifer D. Physics-informed deep learning for prediction of CO 2 storage site response. J Contam Hydrol 2021; 241:103835. [PMID: 34091408 DOI: 10.1016/j.jconhyd.2021.103835] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/30/2020] [Revised: 05/12/2021] [Accepted: 05/17/2021] [Indexed: 06/12/2023]
Abstract
Accurate prediction of the CO2 plume migration and pressure is imperative for safe operation and economic management of carbon storage projects. Numerical reservoir simulations of CO2 flow could be used for this purpose allowing the operators and stakeholders to calculate the site response considering different operational scenarios and uncertainties in geological characterization. However, the computational toll of these high-fidelity simulations has motivated the recent development of data-driven models. Such models are less costly, but may overfit the data and produce predictions inconsistent with the underlying physical laws. Here, we propose a physics-informed deep learning method that uses deep neural networks but also incorporates flow equations to predict a carbon storage site response to CO2 injection. A 3D synthetic dataset is used to show the effectiveness of this modeling approach. The model approximates the temporal and spatial evolution of pressure and CO2 saturation and predicts water production rate over time (outputs), given the initial porosity, permeability and injection rate (inputs). First, we establish a baseline using data-driven deep learning models namely, Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM). To build a physics-informed model, the loss term is modified using the constraints defined by a simplified form of the governing partial differential equations (conservation of mass coupled with Darcy's law for a two-phase flow system). Our results indicate that incorporating the domain knowledge significantly improves the accuracy of predictions. The proposed modeling approach can be integrated in CO2 storage management to accurately predict the critical site response indicators for a range of relevant input parameters, even when limited training data is available.
Collapse
Affiliation(s)
- Parisa Shokouhi
- Department of Engineering Science and Mechanics, The Pennsylvania State University, United States of America.
| | - Vikas Kumar
- Department of Computer Science, The Pennsylvania State University, United States of America
| | - Sumedha Prathipati
- Department of Computer Science, The Pennsylvania State University, United States of America
| | - Seyyed A Hosseini
- Jackson School of Geosciences, The University of Texas at Austin, United States of America
| | - Clyde Lee Giles
- Department of Computer Science, The Pennsylvania State University, United States of America
| | - Daniel Kifer
- Department of Computer Science, The Pennsylvania State University, United States of America
| |
Collapse
|
6
|
Guha A, Aynardi M, Shokouhi P, Lissenden CJ. Identification of long-range ultrasonic guided wave characteristics in cortical bone by modelling. Ultrasonics 2021; 114:106407. [PMID: 33667952 DOI: 10.1016/j.ultras.2021.106407] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/28/2020] [Revised: 12/14/2020] [Accepted: 02/15/2021] [Indexed: 06/12/2023]
Abstract
The propagation of ultrasonic guided waves in cortical bone has potential to inform medical caregivers about the condition of the bone structure. However, as waveguides, human long bones such as the tibia are complex in terms of their material behavior and their geometric features. They exhibit anisotropic elasticity and internal damping. For the first time, wave propagation is modelled in the irregular hollow tibial cross-section, which varies along its long axis. Semi-analytical, frequency domain, and time domain finite element analyses providing complimentary information about long-range wave propagation characteristics in such a waveguide are applied to the mid-diaphyseal region of a human tibia. Simulating the guided waves generated by a contact transducer, the signals received in axial transmission indicate the consistent presence of low phase velocity non-dispersive propagating modes. The guided waves capable of traveling long distances have strong potential for diagnosis of fracture healing.
Collapse
Affiliation(s)
- Anurup Guha
- Department of Engineering Science & Mechanics, Penn State, United States
| | - Michael Aynardi
- Department of Orthopedics & Rehabilitation, Hershey Medical Center, Penn State, United States
| | - Parisa Shokouhi
- Department of Engineering Science & Mechanics, Penn State, United States
| | - Cliff J Lissenden
- Department of Engineering Science & Mechanics, Penn State, United States.
| |
Collapse
|
7
|
Farhadifard H, Rezaei-Soufi L, Farhadian M, Shokouhi P. Effect of different surface treatments on shear bond strength of ceramic brackets to old composite. Biomater Res 2020; 24:20. [PMID: 33292632 PMCID: PMC7687813 DOI: 10.1186/s40824-020-00199-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Accepted: 11/10/2020] [Indexed: 11/10/2022] Open
Abstract
Background At present, the demand for orthodontic treatment is on the rise. On the other hand, evidence shows that the bond strength of composite resins to old composite restorations is often unreliable. Therefore, the aim of this in vitro study was to assess the effect of different surface treatments on shear bond strength (SBS) of ceramic brackets to old composite restorations. Methods In this in vitro experimental study, 60 nano-hybrid composite discs were fabricated. For aging, the discs were incubated in deionized water at 37 °C for 1 month. Next, they underwent 4 different surface treatments namely acid etching with 37% phosphoric acid, sandblasting, grinding, and Er,Cr:YSGG laser irradiation. Ceramic brackets were then bonded to the discs and underwent SBS testing. Results The maximum mean SBS value was obtained in the grinding group (9.16 ± 2.49 MPa), followed by the sandblasting (8.13 ± 2.58 MPa) and laser (6.57 ± 1.45 MPa) groups. The minimum mean SBS value was noted in the control group (5.07 ± 2.14 MPa). Conclusion All groups except for the control group showed clinically acceptable SBS. Therefore, grinding, sandblasting, and Er,Cr:YSGG laser are suggested as effective surface treatments for bonding of ceramic orthodontic brackets to aged composite.
Collapse
Affiliation(s)
- Homa Farhadifard
- Department of Orthodontics, School of Dentistry, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Loghman Rezaei-Soufi
- Department of Restorative Dentistry, School of Dentistry, Dental Research Center, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Maryam Farhadian
- Department of Biostatistics, School of Public Health and Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Parisa Shokouhi
- School of Dentistry, Hamadan University of Medical Sciences, 6517838677 Shahid Fahmideh Street, Hamadan City, Hamadan, Iran.
| |
Collapse
|
8
|
Farhadian M, Shokouhi P, Torkzaban P. A decision support system based on support vector machine for diagnosis of periodontal disease. BMC Res Notes 2020; 13:337. [PMID: 32660549 PMCID: PMC7359226 DOI: 10.1186/s13104-020-05180-5] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2020] [Accepted: 07/08/2020] [Indexed: 01/22/2023] Open
Abstract
Objective Early diagnosis of many diseases is essential for their treatment. Furthermore, the existence of abundant and unknown variables makes more complicated decision making. For this reason, the diagnosis and classification of diseases using machine learning algorithms have attracted a lot of attention. Therefore, this study aimed to design a support vector machine (SVM) based decision-making support system to diagnosis various periodontal diseases. Data were collected from 300 patients referring to Periodontics department of Hamadan University of Medical Sciences, west of Iran. Among these patients, 160 were Gingivitis, 60 were localized periodontitis and 80 were generalized periodontitis. In the designed classification model, 11 variables such as age, sex, smoking, gingival index, plaque index and so on used as input and output variable show the individual’s status as a periodontal disease. Results Using different kernel functions in the design of the SVM classification model showed that the radial kernel function with an overall correct classification accuracy of 88.7% and the overall hypervolume under the manifold (HUM) value was to 0.912 has the best performance. The results of the present study show that the designed classification model has an acceptable performance in predicting periodontitis.
Collapse
Affiliation(s)
- Maryam Farhadian
- Department of Biostatistics, School of Public Health and Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Parisa Shokouhi
- Dental School, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Parviz Torkzaban
- Department of Periodontics, Dental School, Dental Research Center, Hamadan University of Medical Sciences, P.O. Box 4171-65175, Hamadan, Iran.
| |
Collapse
|
9
|
Shokouhi P, Rivière J, Lake CR, Le Bas PY, Ulrich TJ. Dynamic acousto-elastic testing of concrete with a coda-wave probe: comparison with standard linear and nonlinear ultrasonic techniques. Ultrasonics 2017; 81:59-65. [PMID: 28578221 DOI: 10.1016/j.ultras.2017.05.010] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/27/2016] [Revised: 04/10/2017] [Accepted: 05/17/2017] [Indexed: 06/07/2023]
Abstract
The use of nonlinear acoustic techniques in solids consists in measuring wave distortion arising from compliant features such as cracks, soft intergrain bonds and dislocations. As such, they provide very powerful nondestructive tools to monitor the onset of damage within materials. In particular, a recent technique called dynamic acousto-elasticity testing (DAET) gives unprecedented details on the nonlinear elastic response of materials (classical and non-classical nonlinear features including hysteresis, transient elastic softening and slow relaxation). Here, we provide a comprehensive set of linear and nonlinear acoustic responses on two prismatic concrete specimens; one intact and one pre-compressed to about 70% of its ultimate strength. The two linear techniques used are Ultrasonic Pulse Velocity (UPV) and Resonance Ultrasound Spectroscopy (RUS), while the nonlinear ones include DAET (fast and slow dynamics) as well as Nonlinear Resonance Ultrasound Spectroscopy (NRUS). In addition, the DAET results correspond to a configuration where the (incoherent) coda portion of the ultrasonic record is used to probe the samples, as opposed to a (coherent) first arrival wave in standard DAET tests. We find that the two visually identical specimens are indistinguishable based on parameters measured by linear techniques (UPV and RUS). On the contrary, the extracted nonlinear parameters from NRUS and DAET are consistent and orders of magnitude greater for the damaged specimen than those for the intact one. This compiled set of linear and nonlinear ultrasonic testing data including the most advanced technique (DAET) provides a benchmark comparison for their use in the field of material characterization.
Collapse
Affiliation(s)
- Parisa Shokouhi
- Civil and Environmental Engineering Department, Pennsylvania State University, University Park, PA 16802, United States.
| | - Jacques Rivière
- Department of Geosciences, Pennsylvania State University, University Park, PA 16802, United States.
| | - Colton R Lake
- EA Engineering, Science, and Technology, Inc., PBC, Los Alamos, NM 87545, United States.
| | - Pierre-Yves Le Bas
- Detonator Technology, Los Alamos National Laboratory, Los Alamos, NM 87545, United States.
| | - T J Ulrich
- Detonator Technology, Los Alamos National Laboratory, Los Alamos, NM 87545, United States.
| |
Collapse
|