Quality control of deep generator priors for statistical seismic inverse problems
Name
segam2020-3428013.1.pdf
Description
Published version
Size
1.57 MB
Format
Adobe PDF
Checksum (MD5)
4da10c8fe325b4fb317ab06dedd30672
Author(s)
Fang, Zhilong
Fang, Hongjian
Demanet, Laurent
Date Issued
September 30, 2020
Journal
SEG Technical Program Expanded Abstracts 2020
Publisher
Society of Exploration Geophysicists
Citation
Zhilong Fang, Hongjian Fang, Laurent Demanet; September 1, 2020. "Quality control of deep generator priors for statistical seismic inverse problems." Proceedings of the SEG Technical Program Expanded Abstracts 2020. SEG Technical Program Expanded Abstracts 2020. (pp. pp. 1715-1719). ASME.
Version
Final published version
Abstract
Prior information is essential for statistical seismic inverse problems to quantify uncertainties of unknown subsurface parameters. Conventional prior knowledge is based on empirical observations of subsurface structures like the smoothness of the subsurface image. However, such hand-designed prior knowledge is too generic to describe detailed subsurface structures. Deep generator priors are a recent encouraging development, where a high-quality prior can be crafted solely from existing data and a deep neural network. Such deep generators can create detailed subsurface models from Gaussian vectors in a low-dimensional latent space. Alongside this potential advantage, comes the major risk that the prior might be too restrictive to give physically meaningful solutions a high enough likelihood. In this work, we attempt to mitigate this risk by presenting a measure to evaluate the quality of the learned deep generator prior, which can then be leveraged to tune its hyperparameters. Given a testing model and a generator, we first find the best generated model that minimizes the `2-norm misfit between the generated and testing models. To measure the quality of the generator, we suggest two criteria: (1) the `2-norm model error should be small; and (2) the `2-norm of the corresponding latent vector should be bounded and within a pre-defined reference range. Numerical examples show that a good prior generator in the sense of the proposed measure can help produce more accurate results for statistical seismic inverse problems.
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1190/segam2020-3428013.1
