TY - GEN

T1 - Traveltime Computation for qSV Waves in TI Media Using Physics-Informed Neural Networks

AU - Waheed, U.B.

AU - Alkhalifah, Tariq Ali

AU - Li, B.

AU - Haghighat, E.

AU - Stovas, A.

AU - Virieux, J.

N1 - KAUST Repository Item: Exported on 2021-10-05

PY - 2021

Y1 - 2021

N2 - Traveltimes corresponding to both compressional and shear waves are needed for many applications in seismology ranging from seismic imaging to earthquake localization. Since the behavior of shear waves in anisotropic media is considerably more complicated than the isotropic case, accurate traveltime computation for shear waves in anisotropic media remains a challenge. Ray tracing methods are often used to compute qSV wave traveltimes but they become unstable around triplication points and, therefore, we often use the weak anisotropy approximation. Here, we employ the emerging paradigm of physics-informed neural networks to solve transversely isotropic eikonal equation for the qSV wave that otherwise are not easily solvable using conventional finite difference methods. By minimizing a loss function formed by imposing the validity of eikonal equation, we train a neural network to produce traveltime solutions that are consistent with the underlying equation. Through tests on synthetic models, we show that the method is capable of producing accurate qSV wave traveltimes even at triplication points and works for arbitrary strength of medium anisotropy.

AB - Traveltimes corresponding to both compressional and shear waves are needed for many applications in seismology ranging from seismic imaging to earthquake localization. Since the behavior of shear waves in anisotropic media is considerably more complicated than the isotropic case, accurate traveltime computation for shear waves in anisotropic media remains a challenge. Ray tracing methods are often used to compute qSV wave traveltimes but they become unstable around triplication points and, therefore, we often use the weak anisotropy approximation. Here, we employ the emerging paradigm of physics-informed neural networks to solve transversely isotropic eikonal equation for the qSV wave that otherwise are not easily solvable using conventional finite difference methods. By minimizing a loss function formed by imposing the validity of eikonal equation, we train a neural network to produce traveltime solutions that are consistent with the underlying equation. Through tests on synthetic models, we show that the method is capable of producing accurate qSV wave traveltimes even at triplication points and works for arbitrary strength of medium anisotropy.

UR - http://hdl.handle.net/10754/672093

UR - https://www.earthdoc.org/content/papers/10.3997/2214-4609.202112541

U2 - 10.3997/2214-4609.202112541

DO - 10.3997/2214-4609.202112541

M3 - Conference contribution

BT - 82nd EAGE Annual Conference & Exhibition

PB - European Association of Geoscientists & Engineers

ER -