Bayesian Uncertainty Estimation for Deep Learning Inversion of Electromagnetic Data
Байесовская оценка неопределенности при обращении электромагнитных данных с использованием глубокого обучения
2021-04-22
SCID: 54.1/ehsfdrah
Discuss with AI
Bayesian uncertainty estimationdeep learning inversionelectromagnetic dataepistemic and aleatoric uncertaintiesout-of-distribution detection
Figures from the paper
Abstract (AI)
With the recent progress in deep learning (DL), DL inversion, which reconstructs subsurface physical properties from geophysical data using DL techniques, has been widely applied. For decision-making and risk management related to the application of DL inversion, assessing the reliability of a prediction is essential, and such assessment can be achieved through uncertainty estimation. However, most geophysical studies have focused on deterministic prediction that does not provide uncertainty estimates. In this letter, a practical uncertainty estimation method based on the Bayesian framework is introduced for DL inversion of electromagnetic data. More specifically, iterative estimation by a convolutional neural network with dropout provides epistemic and aleatoric uncertainties as well as a resistivity model. Using numerical tests, we observed that aleatoric uncertainty indicates the nonuniqueness of the inverse problem, showing which parts of the resistivity model are less sensitive to the data. In addition, we proposed an empirical criterion for determining whether new data are similar to training data using estimated epistemic and aleatoric uncertainties. Based on this criterion, out-of-distribution data were identified; these data showed larger data misfit, indicating that the predictions would be unreliable. The applicability of uncertainty estimation and the empirical criterion derived from uncertainties were demonstrated using field data. Bayesian uncertainty estimation and the criterion established here may help to achieve more reliable prediction via DL inversion.
Key Findings
1
A Bayesian framework using iterative dropout convolutional neural-network inference estimates resistivity models alongside epistemic and aleatoric uncertainties for electromagnetic-data inversion.
2
Aleatoric uncertainty reflects inverse-problem nonuniqueness by identifying resistivity-model regions that are less sensitive to the observed data.
3
An empirical criterion based on epistemic and aleatoric uncertainties identifies out-of-distribution data relative to the training set.
4
Out-of-distribution data exhibit larger data misfits, indicating that their deep-learning inversion predictions are likely unreliable.
5
The uncertainty-estimation method and empirical criterion were demonstrated on both numerical tests and field electromagnetic data, supporting more reliable inversion decisions.
Research Object
deep-learning inversion of electromagnetic geophysical data for subsurface resistivity-model reconstruction
Research Subject
Bayesian estimation of epistemic and aleatoric uncertainties, including prediction reliability, inverse-problem nonuniqueness, and out-of-distribution detection
Publication Details
Publication Date
2021-04-22
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF
Subscribe to digest