Elastic Full-Waveform Inversion Using a Physics-Guided Deep Convolutional Encoder–Decoder

Elastic full-waveform inversion (FWI) can construct high-resolution P-wave velocity, S-wave velocity, and density models in complex geological settings. However, several factors make the application of elastic FWI challenging. Elastic FWI is prone to the problem of the cycle-skipping phenomenon when low frequency in the data is unavailable and the starting model is inaccurate. Multiparameter FWI also suffers from crosstalk issues due to coupling between different model parameters. We extend our physics-guided deep convolutional encoder–decoder network to the problem of multiparameter elastic FWI. Our training is completely unsupervised. Our encoder–decoder that is composed of convolutional neural networks (CNNs) maps the multicomponent shot gathers to the target velocity models. The output from the network is given as input to partial differential equations (PDEs) which generate synthetic data. We compare the observed data against the synthetic data and then compute the misfit. We calculate the gradient of the misfit with respect to the model parameters and then use it to update the neural network weights. We note that the neural network generates velocity and density models that explain the observed data. A toy model, the Marmousi model, and the left part of the BP salt model are used to demonstrate the effectiveness of the proposed approach. Finally, we explain the proposed approach’s efficacy by examining the nature of the loss landscape of neural networks-based FWI.