skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A physics-informed machine learning based dispersion curve estimation for non-homogeneous media
Modern machine learning has been on the rise in many scientific domains, such as acoustics. Many scientific problems face challenges with limited data, which prevent the use of the many powerful machine learning strategies. In response, the physics of wave-propagation can be exploited to reduce the amount of data necessary and improve performance of machine learning techniques. Based on this need, we present a physics-informed machine learning framework, known as wave-informed regression, to extract dispersion curves from a guided wave wavefield data from non-homogeneous media. Wave-informed regression blends matrix factorization with known wave-physics by borrowing results from optimization theory. We briefly derive the algorithm and discuss a signal processing-based interpretability aspect of it, which aids in extracting dispersion curves for non-homogenous media. We show our results on a non-homogeneous media, where the dispersion curves change as a function of space. We demonstrate our ability to use wave-informed regression to extract spatially local dispersion curves.  more » « less
Award ID(s):
1839704
PAR ID:
10396605
Author(s) / Creator(s):
;
Date Published:
Journal Name:
The Journal of the Acoustical Society of America
Volume:
152
Issue:
4
ISSN:
0001-4966
Page Range / eLocation ID:
A239 to A239
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Machine Learning and the Physical Sciences Workshop at the Conference on Neural Information Processing Systems (NeurIPS))
    This work discusses an optimization framework to embed dictionary learning frameworks with the wave equation as a strategy for incorporating prior scientific knowledge into a machine learning algorithm. We modify dictionary learning to study ultrasonic guided wave-based defect detection for non-destructive structural health monitoring systems. Specifically, this work involves altering the popular-SVD algorithm for dictionary learning by enforcing prior knowledge about the ultrasonic guided wave problem through a physics-based regularization derived from the wave equation. We confer it the name “wave-informed K-SVD.” Training dictionary on data simulated from a fixed string added with noise using both K-SVD and wave-informed K-SVD, we show an improved physical consistency of columns of dictionary matrix with the known modal behavior of different one-dimensional wave simulations is observed. 
    more » « less
  2. ; ; ; ; ; (, Geophysical Journal International)
    SUMMARY Ocean bottom distributed acoustic sensing (OBDAS) is emerging as a new measurement method providing dense, high-fidelity and broad-band seismic observations from fibre-optic cables deployed offshore. In this study, we focus on 35.7 km of a linear telecommunication cable located offshore the Sanriku region, Japan, and apply seismic interferometry to obtain a high-resolution 2-D shear wave velocity (VS) model below the cable. We first show that the processing steps applied to 13 d of continuous data prior to computing cross-correlation functions (CCFs) impact the modal content of surface waves. Continuous data pre-processed with 1-bit normalization allow us to retrieve dispersion images with high Scholte-wave energy between 0.5 and 5 Hz, whereas spatial aliasing dominates dispersion images above 3 Hz for non-1-bit CCFs. Moreover, the number of receiver channels considered to compute dispersion images also greatly affects the resolution of extracted surface-wave modes. To better understand the remarkably rich modal nature of OBDAS data (i.e. up to 30 higher modes in some regions), we simulate Scholte-wave dispersion curves for stepwise linear VS gradient media. For soft marine sediments, simulations confirm that a large number of modes can be generated in gradient media. Based on pre-processing and theoretical considerations, we extract surface wave dispersion curves from 1-bit CCFs spanning over 400 channels (i.e. ∼2 km) along the array and invert them to image the subsurface. The 2-D velocity profile generally exhibits slow shear wave velocities near the ocean floor that gradually increase with depth. Lateral variations are also observed. Flat bathymetry regions, where sediments tend to accumulate, reveal a larger number of Scholte-wave modes and lower shallow velocity layers than regions with steeper bathymetry. We also compare and discuss the velocity model with that from a previous study and finally discuss the combined effect of bathymetry and shallow VS layers on earthquake wavefields. Our results provide new constraints on the shallow submarine structure in the area and further demonstrate the potential of OBDAS for high-resolution offshore geophysical prospecting. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al (, Proceedings of the American Control Conference)
    Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, PIML models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, PIML models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of PIML is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in PIML for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of PIML models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities. 
    more » « less
  4. ; ; (, IEEE Transactions on Signal Processing)
    With the recent success of representation learning methods, which includes deep learning as a special case, there has been considerable interest in developing techniques that incorporate known physical constraints into the learned representation. As one example, in many applications that involve a signal propagating through physical media (e.g., optics, acoustics, fluid dynamics, etc.), it is known that the dynamics of the signal must satisfy constraints imposed by the wave equation. Here we propose a matrix factorization technique that decomposes such signals into a sum of components, where each component is regularized to ensure that it nearly satisfies wave equation constraints. Although our proposed formulation is non-convex, we prove that our model can be efficiently solved to global optimality. Through this line of work we establish theoretical connections between wave-informed learning and filtering theory in signal processing. We further demonstrate the application of this work on modal analysis problems commonly arising in structural diagnostics and prognostics. 
    more » « less
  5. ; (, Proc. of the Review of Quantitative Nondestructive Evaluation)
    Recent advancements in physics-informed machine learning have contributed to solving partial differential equations through means of a neural network. Following this, several physics-informed neural network works have followed to solve inverse problems arising in structural health monitoring. Other works involving physics-informed neural networks solve the wave equation with partial data and modeling wavefield data generator for efficient sound data generation. While a lot of work has been done to show that partial differential equations can be solved and identified using a neural network, little work has been done the same with more basic machine learning (ML) models. The advantage with basic ML models is that the parameters learned in a simpler model are both more interpretable and extensible. For applications such as ultrasonic nondestructive evaluation, this interpretability is essential for trustworthiness of the methods and characterization of the material system under test. In this work, we show an interpretable, physics-informed representation learning framework that can analyze data across multiple dimensions (e.g., two dimensions of space and one dimension of time). The algorithm comes with convergence guarantees. In addition, our algorithm provides interpretability of the learned model as the parameters correspond to the individual solutions extracted from data. We demonstrate how this algorithm functions with wavefield videos. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email