Deep-learning-guided high-resolution subsurface reflectivity imaging with application to ground-penetrating radar data

• Published in: Geophysical journal international Vol. 233; no. 1; pp. 448 - 471
• Main Authors: Gao, Kai, Donahue, Carly, Henderson, Bradley G, Modrak, Ryan T
• Format: Journal Article
• Language: English
• Published: United States Oxford University Press 29-11-2023
• Subjects: earth sciences; GEOSCIENCES; ground-penetrating radar; image processing; least-squares reverse-time migration; machine learning; subsurface reflectivity imaging; Least-squares reverse-time migration; Ground penetrating radar; Image processing; Subsurface reflectivity imaging; Machine learning
• ISSN: 0956-540X; 1365-246X
• DOI: 10.1093/gji/ggac468

SUMMARY
Subsurface reflectivity imaging is one of the most important geophysical characterization methods for revealing subsurface structures. In many cases, accurate subsurface reflectivity imaging is challenging because of, for example, random or coherent noise in the data and sparse source–receiver observation geometry. We develop a deep-learning-guided iterative imaging method to improve subsurface structure imaging. Specifically, we train a supervised neural network to infer a noise-free, high-resolution image from a noisy, low-resolution image and use this estimated image as guidance to regularize least-squares imaging. We develop a systematic method to generate high-quality synthetic training data (data-label pairs) to train the guidance neural network. The trained neural network can provide high-fidelity predictions even for field-data images that are not in the training data. We validate our new imaging method using one synthetic and two field ground-penetrating radar data examples, and find that our method can produce clean, high-resolution subsurface reflectivity images where existing single-pass and least-squares imaging methods fail due to noise and insufficient data coverage.