Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques

Abstract

I demonstrate that the conventional seismic full-waveform inversion algorithm can be constructed as a recurrent neural network and so implemented using deep learning software such as TensorFlow. Applying another deep learning concept, the Adam optimizer with minibatches of data, produces quicker convergence toward the true wave speed model on a 2D dataset than Stochastic Gradient Descent and than the L-BFGS-B optimizer with the cost function and gradient computed using the entire training dataset. I also show that the cost function gradient calculation using reverse-mode automatic differentiation is the same as that used in the adjoint state method.

18 pages, 5 figures

References in corpus (1)

• Adam: A Method for Stochastic Optimization

Cited by in corpus (11)

• A General Approach to Seismic Inversion with Automatic Differentiation
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
• Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning
• DuRIN: A Deep-unfolded Sparse Seismic Reflectivity Inversion Network
• Acceleration of Non-Linear Minimisation with PyTorch
• Accelerating Least Squares Imaging Using Deep Learning Techniques
• On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion
• NuSPAN: A Proximal Average Network for Nonuniform Sparse Model -- Application to Seismic Reflectivity Inversion
• A Linear Algebraic Approach to Model Parallelism in Deep Learning
• Full waveform inversion with random shot selection using adaptive gradient descent