Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation

TL;DR

This paper introduces physics-informed data augmentation methods using CNNs to improve seismic inversion accuracy, demonstrating significant quality enhancements in subsurface imaging with synthetic CO₂ leakage data.

Contribution

The paper presents novel physics-aware data augmentation techniques for seismic inversion, integrating domain knowledge into generative models to produce more realistic training data.

Findings

Imaging quality improved by 15% with general-sized leakage.

Imaging quality improved by 17% with small-sized leakage.

Data augmentation significantly enhances seismic imaging performance.

Abstract

Deep learning and data-driven approaches have shown great potential in scientific domains. The promise of data-driven techniques relies on the availability of a large volume of high-quality training datasets. Due to the high cost of obtaining data through expensive physical experiments, instruments, and simulations, data augmentation techniques for scientific applications have emerged as a new direction for obtaining scientific data recently. However, existing data augmentation techniques originating from computer vision, yield physically unacceptable data samples that are not helpful for the domain problems that we are interested in. In this paper, we develop new data augmentation techniques based on convolutional neural networks. Specifically, our generative models leverage different physics knowledge (such as governing equations, observable perception, and physics phenomena) to improve the quality of the synthetic data. To validate the effectiveness of our data augmentation techniques, we apply them to solve a subsurface seismic full-waveform inversion using simulated CO$_2$ leakage data. Our interest is to invert for subsurface velocity models associated with very small CO$_2$ leakage. We validate the performance of our methods using comprehensive numerical tests. Via comparison and analysis, we show that data-driven seismic imaging can be significantly enhanced by using our data augmentation techniques. Particularly, the imaging quality has been improved by 15% in test scenarios of general-sized leakage and 17% in small-sized leakage when using an augmented training set obtained with our techniques.