Multi-Task Learning for Low-Frequency Extrapolation and Elastic Model Building From Seismic Data

Abstract

Low-frequency signal content in seismic data as well as a realistic initial model are key ingredients for robust and efficient full-waveform inversions. However, acquiring low-frequency data is challenging in practice for active seismic surveys. Data-driven solutions show promise to extrapolate low-frequency data given a high-frequency counterpart. While being established for synthetic acoustic examples, the application of bandwidth extrapolation to field datasets remains non-trivial. Rather than aiming to reach superior accuracy in bandwidth extrapolation, we propose to jointly reconstruct low-frequency data and a smooth background subsurface model within a multi-task deep learning framework. We automatically balance data, model and trace-wise correlation loss terms in the objective functional and show that this approach improves the extrapolation capability of the network. We also design a pipeline for generating synthetic data suitable for field data applications. Finally, we apply the same trained network to synthetic and real marine streamer datasets and run an elastic full-waveform inversion from the extrapolated dataset.

MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning

“…The objective was to improve the FWI convergence for real marine data by adding low-frequency content into the data. The importance of such low frequencies for FWI convergence is demonstrated in Ovcharenko et al (2022). On the other hand, Fig.…”

“…One real data generalization example we use here to test the approach is an NN dedicated to locating microseismic sources directly from recorded waveform data. We also test the approach on an NN trained to predict low-frequency data from high-frequency ones to ultimately help full waveform inversion (FWI) converge better Ovcharenko et al (2022).…”

Well-Log Information-Assisted High-Resolution Waveform Inversion Based on Deep Learning

“…For supervised learning algorithms, the training dataset often influences the accuracy of the results and generalization. In this study, using the model generation method presented by Ovcharenko et al [16], a laterally homogeneous layered velocity model is generated from a sparse sequence of simulated impedances as a function of depth, and then an elastic transformation is applied to distort the model and rescale the velocities randomly. The size of generated models is set to 3.2 × 9.2 𝑘𝑚 with a grid size of 20 m and a velocity range of 1.5 to 5.5𝑘𝑚∕𝑠.…”

Building initial model for seismic inversion based on semi‐supervised learning

“…Deep learning is a data‐driven algorithm that can learn implicit nonlinear relations from label data and use it to solve nonlinear problems. Deep learning has been widely used in geophysical problems such as seismic facies analysis (Liu et al., 2021; Nishitsuji & Exley, 2019), first‐break picking (Wang et al., 2019; Yuan et al., 2018; Zwartjes & Yoo, 2022), fault identification (Huang et al., 2017; Wu et al., 2019; Zhou et al., 2021) and model building (Araya‐Polo et al., 2017; Fabien‐Ouellet & Sarkar, 2019; Ovcharenko et al., 2022). Recently, the application of deep neural networks in reservoir characterization has also been investigated (Chen & Saygin, 2021; Dhara et al., 2023; Di & Abubakar, 2021; Sun et al., 2021; Wu et al., 2021).…”