A General Approach to Seismic Inversion with Automatic Differentiation

Abstract

Imaging Earth structure or seismic sources from seismic data involves minimizing a target misfit function, and is commonly solved through gradient-based optimization. The adjoint-state method has been developed to compute the gradient efficiently; however, its implementation can be time-consuming and difficult. We develop a general seismic inversion framework to calculate gradients using reverse-mode automatic differentiation. The central idea is that adjoint-state methods and reverse-mode automatic differentiation are mathematically equivalent. The mapping between numerical PDE simulation and deep learning allows us to build a seismic inverse modeling library, ADSeismic, based on deep learning frameworks, which supports high performance reverse-mode automatic differentiation on CPUs and GPUs. We demonstrate the performance of ADSeismic on inverse problems related to velocity model estimation, rupture imaging, earthquake location, and source time function retrieval. ADSeismic has the potential to solve a wide variety of inverse modeling applications within a unified framework.

References in corpus (2)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques

Cited by in corpus (13)

• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• Rapid Seismic Waveform Modeling and Inversion with Neural Operators
• Deep Neural Helmholtz Operators for 3D Elastic Wave Propagation and Inversion
• Seismic Inversion by Hybrid Machine Learning
• ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows
• Point Neuron Learning: A New Physics-Informed Neural Network Architecture
• Machine Learning in Acoustics: A Review and Open-Source Repository
• Ambient Noise Full Waveform Inversion with Neural Operators
• Seismic wave propagation and inversion with Neural Operators
• Distributed Machine Learning for Computational Engineering using MPI
• Forward and Inverse Mantle Convection with Neural Operators