Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method

TL;DR

This paper introduces a fast, end-to-end seismic inversion method using Conditional Rectified Flow that improves accuracy and efficiency, reduces initial model dependence, and demonstrates practical value on benchmark and real data.

Contribution

It proposes a novel Conditional Rectified Flow-based seismic inversion approach with a dedicated encoder and control strategy, enhancing accuracy and sampling speed over existing methods.

Findings

Achieves high inversion accuracy on OpenFWI dataset.

Provides faster sampling compared to diffusion-based methods.

Generates high-quality initial models in zero-shot scenarios.

Abstract

Seismic inversion is a core problem in geophysical exploration, where traditional methods suffer from high computational costs and are susceptible to initial model dependence. In recent years, deep generative model-based seismic inversion methods have achieved remarkable progress, but existing generative models struggle to balance sampling efficiency and inversion accuracy. This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow[1], which designs a dedicated seismic encoder to extract multi-scale seismic features and adopts a layer-by-layer injection control strategy to achieve fine-grained conditional control. Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI[2] benchmark dataset. Compared with Diffusion[3,4] methods, it achieves sampling acceleration; compared with InversionNet[5,6,7] methods, it achieves higher accuracy in generation. Our zero-shot generalization experiments on Marmousi[8,9] real data further verify the practical value of the method. Experimental results show that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset; compared with Diffusion methods, it achieves sampling acceleration while maintaining higher accuracy than InversionNet methods; experiments based on the Marmousi standard model further verify that this method can generate high-quality initial velocity models in a zero-shot manner, effectively alleviating the initial model dependency problem in traditional Full Waveform Inversion (FWI), and possesses industrial practical value.