On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion

Abstract

The data-driven approach has been demonstrated as a promising technique to solve complicated scientific problems. Full Waveform Inversion (FWI) is commonly epitomized as an image-to-image translation task, which motivates the use of deep neural networks as an end-to-end solution. Despite being trained with synthetic data, the deep learning-driven FWI is expected to perform well when evaluated with sufficient real-world data. In this paper, we study such properties by asking: how robust are these deep neural networks and how do they generalize? For robustness, we prove the upper bounds of the deviation between the predictions from clean and noisy data. Moreover, we demonstrate an interplay between the noise level and the additional gain of loss. For generalization, we prove a norm-based generalization error upper bound via a stability-generalization framework. Experimental results on seismic FWI datasets corroborate with the theoretical results, shedding light on a better understanding of utilizing Deep Learning for complicated scientific applications.

References in corpus (11)

• Exploring Generalization in Deep Learning
• Spectral Norm Regularization for Improving the Generalizability of Deep Learning
• Spectrally-normalized margin bounds for neural networks
• Fantastic Generalization Measures and Where to Find Them
• Is the deconvolution layer the same as a convolutional layer?
• Norm-Based Capacity Control in Neural Networks
• Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques
• InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
• Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Generalization Bounds for Convolutional Neural Networks