FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362475145> ?p ?o ?g. }

• W4362475145 endingPage "T202" @default.
• W4362475145 startingPage "T185" @default.
• W4362475145 abstract "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." @default.
• W4362475145 created "2023-04-05" @default.
• W4362475145 creator A5013653335 @default.
• W4362475145 creator A5023993076 @default.
• W4362475145 creator A5075147171 @default.
• W4362475145 creator A5079625867 @default.
• W4362475145 date "2023-07-01" @default.
• W4362475145 modified "2023-10-15" @default.
• W4362475145 title "Helmholtz-equation solution in nonsmooth media by a physics-informed neural network incorporating quadratic terms and a perfectly matching layer condition" @default.
• W4362475145 cites W1780245888 @default.
• W4362475145 cites W1977341879 @default.
• W4362475145 cites W2003017040 @default.
• W4362475145 cites W2007930380 @default.
• W4362475145 cites W2009552164 @default.
• W4362475145 cites W2019840928 @default.
• W4362475145 cites W2026503114 @default.
• W4362475145 cites W2065538232 @default.
• W4362475145 cites W2080064193 @default.
• W4362475145 cites W2101615520 @default.
• W4362475145 cites W2120704348 @default.
• W4362475145 cites W2136247928 @default.
• W4362475145 cites W2144338873 @default.
• W4362475145 cites W2151983814 @default.
• W4362475145 cites W2166116275 @default.
• W4362475145 cites W2166525224 @default.
• W4362475145 cites W2517659069 @default.
• W4362475145 cites W2593378168 @default.
• W4362475145 cites W2749028154 @default.
• W4362475145 cites W2792590898 @default.
• W4362475145 cites W2796152264 @default.
• W4362475145 cites W2803629276 @default.
• W4362475145 cites W2889523591 @default.
• W4362475145 cites W2899283552 @default.
• W4362475145 cites W2903660960 @default.
• W4362475145 cites W2908541468 @default.
• W4362475145 cites W2919115771 @default.
• W4362475145 cites W2924428731 @default.
• W4362475145 cites W2948230027 @default.
• W4362475145 cites W2948551291 @default.
• W4362475145 cites W2952590710 @default.
• W4362475145 cites W2968494585 @default.
• W4362475145 cites W2969381807 @default.
• W4362475145 cites W2992007141 @default.
• W4362475145 cites W2997588930 @default.
• W4362475145 cites W2998366519 @default.
• W4362475145 cites W3011147100 @default.
• W4362475145 cites W3011806874 @default.
• W4362475145 cites W3035842227 @default.
• W4362475145 cites W3047011887 @default.
• W4362475145 cites W3047035577 @default.
• W4362475145 cites W3091352727 @default.
• W4362475145 cites W3091740281 @default.
• W4362475145 cites W3111914315 @default.
• W4362475145 cites W3157498305 @default.
• W4362475145 cites W3161445736 @default.
• W4362475145 cites W3163993681 @default.
• W4362475145 cites W3195240749 @default.
• W4362475145 cites W3196492281 @default.
• W4362475145 cites W3198022710 @default.
• W4362475145 cites W3204171709 @default.
• W4362475145 cites W3208869780 @default.
• W4362475145 cites W3209181423 @default.
• W4362475145 cites W3210297853 @default.
• W4362475145 cites W3211225070 @default.
• W4362475145 cites W4220717841 @default.
• W4362475145 cites W4226244456 @default.
• W4362475145 cites W4304588351 @default.
• W4362475145 doi "https://doi.org/10.1190/geo2022-0479.1" @default.
• W4362475145 hasPublicationYear "2023" @default.
• W4362475145 type Work @default.
• W4362475145 citedByCount "1" @default.
• W4362475145 countsByYear W43624751452023 @default.
• W4362475145 crossrefType "journal-article" @default.
• W4362475145 hasAuthorship W4362475145A5013653335 @default.
• W4362475145 hasAuthorship W4362475145A5023993076 @default.
• W4362475145 hasAuthorship W4362475145A5075147171 @default.
• W4362475145 hasAuthorship W4362475145A5079625867 @default.
• W4362475145 hasConcept C119857082 @default.
• W4362475145 hasConcept C121332964 @default.
• W4362475145 hasConcept C129844170 @default.
• W4362475145 hasConcept C134306372 @default.
• W4362475145 hasConcept C135252773 @default.
• W4362475145 hasConcept C14036430 @default.
• W4362475145 hasConcept C145589544 @default.
• W4362475145 hasConcept C16171025 @default.
• W4362475145 hasConcept C16895185 @default.
• W4362475145 hasConcept C182310444 @default.
• W4362475145 hasConcept C18591234 @default.
• W4362475145 hasConcept C204723758 @default.
• W4362475145 hasConcept C24890656 @default.
• W4362475145 hasConcept C2524010 @default.
• W4362475145 hasConcept C28826006 @default.
• W4362475145 hasConcept C33923547 @default.
• W4362475145 hasConcept C41008148 @default.
• W4362475145 hasConcept C50644808 @default.
• W4362475145 hasConcept C59696629 @default.
• W4362475145 hasConcept C78458016 @default.
• W4362475145 hasConcept C86803240 @default.

• next