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

2026-03-16

AI Summary

This work proposes an end-to-end fast seismic inversion method based on conditional rectified flows to address the high computational cost and strong dependence on initial models in traditional inversion approaches, as well as the trade-off between sampling efficiency and accuracy in existing generative models. For the first time, conditional rectified flows are introduced into seismic inversion, integrated with a multi-scale seismic feature encoder and a layer-wise conditional injection mechanism to enable efficient, high-fidelity conditional generation with zero-shot generalization capability. Evaluated on the OpenFWI dataset, the method achieves higher inversion accuracy than InversionNet and significantly faster sampling than diffusion models. Furthermore, it successfully generates high-quality initial velocity models on the real Marmousi data, demonstrating its potential for industrial applications.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• seismic inversion
• initial model dependence
• computational cost
• sampling efficiency
• inversion accuracy

Innovation

• Conditional Rectified Flow
• Seismic Inversion
• End-to-End Learning
• Zero-Shot Generalization
• Multi-scale Feature Encoding