High-resolution closed-loop seismic inversion network in time-frequency phase mixed domain

TL;DR

This paper presents a novel deep learning-based seismic inversion network that integrates time, frequency, and phase domain information to enhance the detection of thin layers and reservoirs in seismic data.

Contribution

The introduction of a time-frequency-phase mixed-domain inversion network (TFP-CSIN) that combines Bi-GRU and CNN architectures with frequency and phase constraints for improved seismic inversion.

Findings

Outperforms traditional supervised learning methods in synthetic data tests.

Enhances identification of weak reflection regions and thin layers in field data.

Utilizes Fourier and Hilbert transforms for comprehensive frequency and phase learning.

Abstract

Thin layers and reservoirs may be concealed in areas of low seismic reflection amplitude, making them difficult to recognize. Deep learning (DL) techniques provide new opportunities for accurate impedance prediction by establishing a nonlinear mapping between seismic data and impedance. However, existing methods primarily use time domain seismic data, which limits the capture of frequency bands, thus leading to insufficient resolution of the inversion results. To address these problems, we introduce a new time-frequency-phase (TFP) mixed-domain closed-loop seismic inversion network (TFP-CSIN) to improve the identification of thin layers and reservoirs. First, the inversion network and closed-loop network are constructed by using bidirectional gated recurrent units (Bi-GRU) and convolutional neural network (CNN) architectures, enabling bidirectional mapping between seismic data and impedance data. Next, to comprehensive learning across the entire frequency spectrum, the Fourier transform is used to capture frequency information and establish frequency domain constraints. At the same time, the phase domain constraint is introduced through Hilbert transformation, which improves the method's ability to recognize the weak reflection region features. Both experiments on the synthetic data show that TFP-CSIN outperforms the traditional supervised learning method and time domain semi-supervised learning methods in seismic inversion. The field data further verify that the proposed method improves the identification ability of weak reflection areas and thin layers.