Deep learning for low-frequency extrapolation from multioffset seismic data

Abstract

Low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties. However, it is challenging to acquire field data with an appropriate signal-to-noise ratio in the low-frequency part of the spectrum. We have extrapolated low-frequency data from the respective higher frequency components of the seismic wavefield by using deep learning. Through wavenumber analysis, we find that extrapolation per shot gather has broader applicability than per-trace extrapolation. We numerically simulate marine seismic surveys for random subsurface models and train a deep convolutional neural network to derive a mapping between high and low frequencies. The trained network is then tested on sections from the BP and SEAM Phase I benchmark models. Our results indicate that we are able to recover 0.25 Hz data from the 2 to 4.5 Hz frequencies. We also determine that the extrapolated data are accurate enough for FWI application.

Extrapolating low-frequency prestack land data with deep learning

“…Li and Demanet (2016) synthesized realistic lowfrequency waveforms by phase and amplitude extrapolation of individual body waves in seismogramms. Ovcharenko et al (2017) proposed and developed (Ovcharenko et al, 2018b(Ovcharenko et al, , 2019a a DL approach operating on data in the frequency-domain to derive low-frequency representations of full shot gathers. Alternative trace-by-trace approaches for bandwidth extrapolation in the time domain was pursued by Sun andDemanet (2018, 2019).…”

Cross-equalization of time-lapse seismic data using recurrent neural networks

“…Recently, deep learning (DL) models have been utilized in many geophysical applications such as seismic data pre-processing (e.g., Ovcharenko et al, 2017Ovcharenko et al, , 2019Kazei et al, 2019a;Sun and Demanet, 2019), and inversion (e.g., Araya-Polo et al, 2018;Sun and Alkhalifah, 2019;Plotnitskii et al, 2019;Kazei et al, 2019bKazei et al, , 2020Sun and Alkhalifah, 2020a,b). In the context of time-lapse, Yuan et al (2020) used a convolution neural network (CNN) to image the velocity changes in different vintages.…”

Wave Equation‐Based Local Traveltime Inversion

“…The Hilbert envelope of the seismic signal contains abundant low frequencies; under such circumstances, the envelope inversion is a promising method to reconstruct the low‐wave number components of the subsurface velocity models (Bozdağ et al, 2011; Chi et al, 2014; Gao et al, 2017; Chen et al, 2019). Similar to the envelope inversion, there are many other signal demodulation‐based low‐frequency retrieve methods that have been applied for seismic waveform inversion (Bharadwaj et al, 2016; Hu, 2014; Li & Demanet, 2016; Lian et al, 2018; Ovcharenko et al, 2019; Wang et al, 2019).…”