• Geophysics and Geophysical Exploration
• /
• v.9 no.1
• /
• pp.86-92
• /
• 2006

The full-waveform inversion algorithm using normalised seismic wavefields can avoid potential inversion errors due to source estimation required in conventional full-waveform inversion methods. In this paper, we have modified the inversion scheme to install a weighted smoothness constraint for better resolution, and to implement a staged approach using normalised wavefields in order of increasing frequency instead of inverting all frequency components simultaneously. The newly developed scheme is verified by using a simple two-dimensional fault model. One of the most significant improvements is based on introducing weights in model parameters, which can be derived from integrated sensitivities. The model-parameter weighting matrix is effective in selectively relaxing the smoothness constraint and in reducing artefacts in the reconstructed image. Simultaneous multiple-frequency inversion can almost be replicated by multiple single-frequency inversions. In particular, consecutively ordered single-frequency inversion, in which lower frequencies are used first, is useful for computation efficiency.

• Geophysics and Geophysical Exploration
• /
• v.14 no.3
• /
• pp.214-219
• /
• 2011

We perform the frequency-domain waveform inversion based on the residual-selection strategy. In the residual-selection strategy, we classify time-domain residual wavefields into several groups according to the order of absolute amplitudes. Because the residual wavefields are normalized after regularization of the gradient directions within each group, the residual-selection strategy plays a role in enhancing the small-amplitude wavefields, which contributes to improving the deep parts of inverted subsurface images. After classifying residuals in the time domain, they are transformed to the frequency domain. Waveform inversion is performed in the frequency domain using the back-propagation technique which has been popularly used in reverse-time migration. The residual-selection strategy is applied to the SEG/EAGE salt and IFP Marmousi models. Numerical results show that the residual-selection strategy yields better results than the conventional frequency-domain waveform inversion.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.114-125
• /
• 2023

The physics-informed neural network (PINN) has been proposed to overcome the limitations of various numerical methods used to solve partial differential equations (PDEs) and the drawbacks of purely data-driven machine learning. The PINN directly applies PDEs to the construction of the loss function, introducing physical constraints to machine learning training. This technique can also be applied to wave equation modeling. However, to solve the wave equation using the PINN, second-order differentiations with respect to input data must be performed during neural network training, and the resulting wavefields contain complex dynamical phenomena, requiring careful strategies. This tutorial elucidates the fundamental concepts of the PINN and discusses considerations for wave equation modeling using the PINN approach. These considerations include spatial coordinate normalization, the selection of activation functions, and strategies for incorporating physics loss. Our experimental results demonstrated that normalizing the spatial coordinates of the training data leads to a more accurate reflection of initial conditions in neural network training for wave equation modeling. Furthermore, the characteristics of various functions were compared to select an appropriate activation function for wavefield prediction using neural networks. These comparisons focused on their differentiation with respect to input data and their convergence properties. Finally, the results of two scenarios for incorporating physics loss into the loss function during neural network training were compared. Through numerical experiments, a curriculum-based learning strategy, applying physics loss after the initial training steps, was more effective than utilizing physics loss from the early training steps. In addition, the effectiveness of the PINN technique was confirmed by comparing these results with those of training without any use of physics loss.