Enhancing machine learning based seismic inversion with noise-augmented training datasets
Open Access
- 27 October 2025
- journal article
- Published by Oxford University Press (OUP) in Geophysical Journal International
- Vol. 244 (1)
Abstract
SUMMARY: An 18-layer, U-shaped convolutional neural network was trained to predict Vs models and identify near-surface void locations. To enhance seismic inversion accuracy for real world applications, the model is trained on synthetic data sets augmented with field noise. While models trained on noise-augmented data showed poorer performance on synthetic testing data sets, they achieved lower root-mean-square error values and the best results on field data. The velocity model resulting from full-waveform inversion based on noise-augmented model accurately detected a void-like low-velocity zone near the known void location. This approach shows that training with field-noise-augmented data allows machine learning models to generalize better to real-world conditions, increasing their reliability for velocity inversion in noisy environments. The results highlight the strong potential of this strategy, particularly if a diverse range of real noise samples is incorporated during training.Keywords
This publication has 39 references indexed in Scilit:
- Seismic Shot Gather Denoising by Using a Supervised-Deep-Learning Method with Weak Dependence on Real Noise Data: A Solution to the Lack of Real Noise DataSurveys in Geophysics, 2022
- 4D seismic history matchingJournal of Petroleum Science and Engineering, 2021
- Crustal and Upper Mantle Structure Beneath the Southeastern United States From Joint Inversion of Receiver Functions and Rayleigh Wave DispersionJournal of Geophysical Research: Solid Earth, 2021
- Performance of Different Transformation Techniques for MASW Data Processing Considering Various Site Conditions, Near-Field Effects, and Modal SeparationSurveys in Geophysics, 2021
- Seismic Inversion by Hybrid Machine LearningJournal of Geophysical Research: Solid Earth, 2021
- Time-lapse full waveform inversion based on curvelet transform: Case study of CO2 storage monitoringInternational Journal of Greenhouse Gas Control, 2021
- An open-source Matlab code package for improved rank-reduction 3D seismic data denoising and reconstructionComputers & Geosciences, 2016
- Using near-surface seismic refraction tomography and multichannel analysis of surface waves to detect shallow tunnels: A feasibility studyJournal of Applied Geophysics, 2013
- Robust smoothing of gridded data in one and higher dimensions with missing valuesComputational Statistics & Data Analysis, 2010
- The Inverse Problem of Refraction Travel Times, Part II: Quantifying Refraction Nonuniqueness Using a Three-layer ModelPure and Applied Geophysics, 2005