Leveraging Deep Operator Networks (DeepONet) for Acoustic Full Waveform Inversion (FWI)

2025-04-14

AI Summary

Full-waveform inversion (FWI) suffers from high computational cost and non-unique solutions due to limited seismic data. Method: This paper introduces DeepONet—the first application of operator learning to acoustic FWI—proposing an end-to-end, physics-constrained framework that directly maps surface seismic data to subsurface velocity fields. The approach integrates PDE-based forward modeling with supervised operator learning and incorporates a noise-robust training strategy to ensure both generalization and physical consistency. Contributions/Results: Experiments demonstrate superior inversion accuracy over state-of-the-art machine learning methods across diverse velocity models; the predicted initial velocity models significantly accelerate conventional FWI convergence compared to uniform initializations; and the model maintains robust performance under noisy data and out-of-distribution test cases. This work establishes a novel paradigm for efficient, robust seismic inversion.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning on the Edge & Model Compression
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Full Waveform Inversion (FWI) is an important geophysical technique considered in subsurface property prediction. It solves the inverse problem of predicting high-resolution Earth interior models from seismic data. Traditional FWI methods are computationally demanding. Inverse problems in geophysics often face challenges of non-uniqueness due to limited data, as data are often collected only on the surface. In this study, we introduce a novel methodology that leverages Deep Operator Networks (DeepONet) to attempt to improve both the efficiency and accuracy of FWI. The proposed DeepONet methodology inverts seismic waveforms for the subsurface velocity field. This approach is able to capture some key features of the subsurface velocity field. We have shown that the architecture can be applied to noisy seismic data with an accuracy that is better than some other machine learning methods. We also test our proposed method with out-of-distribution prediction for different velocity models. The proposed DeepONet shows comparable and better accuracy in some velocity models than some other machine learning methods. To improve the FWI workflow, we propose using the DeepONet output as a starting model for conventional FWI and that it may improve FWI performance. While we have only shown that DeepONet facilitates faster convergence than starting with a homogeneous velocity field, it may have some benefits compared to other approaches to constructing starting models. This integration of DeepONet into FWI may accelerate the inversion process and may also enhance its robustness and reliability.

Problem

• Improves efficiency and accuracy of Full Waveform Inversion (FWI)
• Inverts seismic waveforms for subsurface velocity field
• Enhances FWI workflow with DeepONet as starting model

Innovation

• Uses DeepONet for seismic waveform inversion
• Improves efficiency and accuracy of FWI
• Integrates DeepONet output as FWI starting model