Seismic image registration using multiscale convolutional neural networks

Abstract

<jats:p> Aligning seismic images is important in many areas of seismic processing such as time-lapse studies, tomography, and registration of compressional and shear-wave images. This problem is especially difficult when the misalignment is large and varies rapidly and when the images are not shifted versions of each other because they are either contaminated by noise or have different phase or frequency content. In addition, the images may be related by multidimensional vector-valued shift functions. We have developed a fast, scalable, and end-to-end trainable convolutional neural network (CNN) for seismic image registration. The concept of optical flow is widely applied to the problem of image registration using variational methods. Recent developments in the field of computer vision have shown that optical flow estimation can be formulated as a supervised machine learning task and can be successfully solved using CNNs. We train our CNN, SeisFlowNet, on images warped with known shifts and corrupted with noise, frequency, and phase perturbations. We evaluate the promising performance of the trained SeisFlowNet with synthetic data sets where the shift function is known and the images are contaminated with noise and other perturbations. The accuracy of the results obtained with SeisFlowNet is favorably compared with two other popular methods for seismic registration: windowed crosscorrelation and dynamic image warping. Further, we highlight the principles adopted to create training data sets and the advantages and disadvantages of the method. </jats:p>

Deep Learning for Geophysics: Current and Future Trends

“…A CNN is trained with two seismic images as inputs and the shift as output by learning from the concept of optical flow. The method outperforms traditional methods but is dependent on the training data set (Dhara and Bagaini, 2020).…”

Improvement and Application of Hale’s Dynamic Time Warping Algorithm

“…Venstad designed a regularisation method for the DTW algorithm to further improve its anti-noise performance [26]. Dhara and Bagaini developed a supervised machine learning problem based on optical flow estimation that can be solved using convolutional neural networks (CNNs), which achieved a higher accuracy than windowed cross-correlation (WCC) and dynamic image warping (DIW) [27].…”

Elastic Full Waveform Inversion using a Physics guided deep convolutional autoencoder

“…Chen et al [3] used a decomposed wavefield in order to reduce coupling effects and used a multiscale signed envelope loss function in order to recover low frequency components. In recent years, deep learning techniques have been studied for a wide variety of geophysical problems like automatic seismic interpretation [49]- [51], seismic image denoising and resolution enhancement [52], [53], seismic impedance inversion [47], [48] and seismic image registration [46]. Inspired by such developments, several researchers have applied deep learning to the problem of full-waveform inversion.…”