Yanqi Wu

Yanqi Wu

Auto-generated profile, based on publicly available information

Yanqi Wu

Harbin Institute of Technology 1 , Department of Mathematics and Center of Geophysics, Harbin, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
31 March 2023 in Geophysics
Verified
Journal Article
Closed access
YWYanqi Wu
Yanqi Wu
HAHossein S. Aghamiry
Hossein S. Aghamiry
SOStephane Operto
Stephane Operto
JMJianwei Ma
Jianwei Ma
Frequency-domain simulation of seismic waves plays an important role in seismic inversion, but it remains challenging in large models. The recently proposed physics-informed neural network (PINN), as an effective deep-learning method, has achieved successful applications in solving a wide range of partial differential equations (PDEs), and there is still room for improvement on this front. For example, PINN can lead to inaccurate solutions when PDE coefficients are nonsmooth and describe structurally complex media. Thus, we solve the acoustic and visco-acoustic scattered-field (Lippmann-Schwinger) wave equation in the frequency domain with PINN instead of the wave equation to remove the source singularity. We first illustrate that nonsmooth velocity models lead to inaccurate wavefields when no boundary conditions are implemented in the loss function. Then, we add the perfectly matched layer (PML) conditions in the loss function to better couple the real and imaginary parts of the wavefield. Moreover, we design new neurons by replacing the classical affine function with a quadratic function in the argument of the activation function to better capture the nonsmooth features of the wavefields. We find that the PML condition and the quadratic functions improve the results including handling attenuation and discuss the reason for this improvement. We also illustrate that a network trained to predict a wavefield for a specific medium can be used as an initial model of the neural network for predicting other wavefields corresponding to PDE-coefficient alterations and improving the convergence speed accordingly. This pretraining strategy should find applications in iterative full-waveform inversion and time-lag target-oriented imaging when the model perturbation between two consecutive iterations or two consecutive experiments is small.

29 September 2021 in Geophysics
Verified
Journal Article
Closed access
YWYanqi Wu
Yanqi Wu
JMJianwei Ma
Jianwei Ma
In elastostatics, the scale effect is a phenomenon in which the elastic parameters of a medium vary with the specimen size when the specimen is sufficiently small. Linear elasticity cannot explain the scale effect because it assumes that the medium is a continuum and does not consider microscopic rotational interactions within the medium. In elastodynamics, wave-propagation equations are usually based on linear elasticity. Thus, nonlinear elasticity must be introduced to study the scale effect on wave propagation. We have developed one of the generalized continuum theories, a so-called couple-stress theory, into solid earth geophysics to build a more practical model of the underground medium. The first-order velocity-stress wave equation is derived to simulate the propagation of Rayleigh waves. Body and Rayleigh waves are compared using elastic theory and couple-stress theory in a homogeneous half-space and a layered space. The results indicate that couple stress causes the dispersion of surface waves and S-waves even in a homogeneous half-space. The effect is enhanced by increasing the source frequency and characteristic length, despite its insufficiently clear physical meaning. Rayleigh waves are more sensitive to the couple-stress effect than are body waves. Based on the phase-shifting method, it is determined that Rayleigh waves exhibit different dispersion characteristics in the couple-stress theory than in the conventional elastic theory. For the fundamental mode, dispersion curves tend to move to a lower frequency with an increase in characteristic length l. For the higher modes, the dispersion curve energy is stronger with a greater characteristic length l.