A Sequential Iterative Deep Learning Seismic Blind High-Resolution Inversion

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 14; pp. 7817 - 7829
• Main Authors: Chen, Hongling, Gao, Jinghuai, Gao, Zhaoqi, Chen, Daoyu, Yang, Tao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Alternating direction method of multipliers (ADMM); Artificial neural networks; Computer applications; Convex functions; Data; Data models; Deep learning; High resolution; high-resolution inversion; Inversion; Iterative algorithms; iterative deep learning; Iterative methods; Machine learning; Neural networks; Parameters; Penalty function; Regularization; Resolution; seismic inversion; Seismic surveys; Stratigraphy; Training; Training data; Wavelet domain; Wavelet transforms
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2021.3100502

Seismic blind high-resolution inversion (BHRI) aims at retrieving the high-resolution data to characterize the stratigraphic structures in the case of an unknown seismic wavelet. However, the unknown wavelet and ill-posedness pose a great challenge to the high-resolution inversion. Regularization-based BHRI is an effective approach. However, it is sensitive to the sets of initial values, regularization terms, and regularization parameters and suffers from computational burden problems. To address these issues, we propose a sequential iterative deep learning method (SIDLM) to implement a BHRI in a fast computational speed, which incorporates three learned components to sequentially invert initial high-resolution data, seismic wavelet, and final high-resolution data in an end-to-end fashion. Specifically, to mitigate the influence of initial values, a data-driven network U-Net is adopted to learn an initial high-resolution data. Furthermore, the architecture makes use of prior information encoded in the forward operator to build a new general alternating direction method of multipliers (ADMM)-like iterative deep neural network, instead of the traditional alternating iterative inversion. The proposed ADMM-like network utilizes the convolutional neural networks to learn the proximal operators to solve each subproblems in alternating iterative inversion. Therefore, all parameters of BHRI, such as the regularization parameters and transform operator, can be implicitly learned from the training datasets in an end-to-end fashion, not limited to the form of the penalty function. Finally, the synthetic and field data examples are conducted to demonstrate the effectiveness of the proposed SIDLM.