Physics-Informed Cross-Learning for Seismic Acoustic Impedance Inversion and Wavelet Extraction

TL;DR

This paper introduces a physics-informed deep learning framework for simultaneous seismic acoustic impedance inversion and wavelet extraction, addressing challenges of limited data and physical constraint integration, with improved accuracy demonstrated on synthetic and field datasets.

Contribution

The study presents a novel physics-informed cross-learning strategy that enhances seismic inversion and wavelet extraction, overcoming limitations of prior deep learning approaches.

Findings

Significant accuracy improvement over semi-supervised methods

Effective simultaneous inversion and wavelet extraction

Validated on synthetic and real datasets

Abstract

Seismic acoustic impedance inversion is one of the most challenging tasks in geophysical exploration. Many studies have proposed the use of deep learning for processing; however, most of them are limited by factors such as seismic wavelets and low-frequency initial models. Furthermore, self-supervised frameworks constructed entirely using deep learning models struggle to form direct and effective physical constraints to unlabeled outputs during the multi-model concatenation, which leads to instability in inversion. In this work, we introduced innovations in both the deep learning framework and training strategy. First, we designed a deep learning framework to perform acoustic impedance inversion and seismic wavelet extraction simultaneously. Building on this foundation, considering the scarcity of well data, we proposed a physics-informed cross-learning strategy to impose effective constraints on the framework. We conducted comparative experiments and ablation experiments on both synthetic datasets and field datasets. The results demonstrate that the proposed method achieves a significant improvement compared with semi-supervised learning methods and can extract seismic wavelets with relatively high accuracy. Finally, to ensure the reproducibility of this work, we have made the code open-source.