A5008295396- Seismic Imaging and Inversion Techniques
- Seismic Waves and Analysis
- Image and Signal Denoising Methods
- Drilling and Well Engineering
- Geophysical Methods and Applications
- Seismology and Earthquake Studies
- Blind Source Separation Techniques
- Hydraulic Fracturing and Reservoir Analysis
- AI in cancer detection
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Advanced Image Processing Techniques
- High-pressure geophysics and materials
- Image Processing Techniques and Applications
- Geophysical and Geoelectrical Methods
North China University of Science and Technology
2024
Chevron (United States)
2024
Rice University
2019-2022
Schlumberger (British Virgin Islands)
2020
Abstract Machine learning algorithm has been applied to shear wave velocity (Vs) inversion in surface tomography, where a set of starting 1‐D Vs profiles and their corresponding synthetic dispersion curves are used network training. Previous studies showed that the performance such trained is dependent on diversity training data set, which limits its application previously poorly understood regions. Here, we present an improved semi‐supervised algorithm‐based takes both model‐generated...
The convolutional neural networks (CNNs) have attracted great attentions in seismic exploration applications by their capability of learning the representations data with multiple level abstractions, given an adequate amount labeled data. In impedance inversion, however, availability data-impedance pairs is often limited. cycle-consistent generative adversarial (Cycle-GAN) proven as a powerful semi-supervised solution incorporating these unpaired into its training, but it suffers from...
We develop an early arrival waveform inversion (EAWI) technique for high-resolution near-surface velocity estimation by iteratively updating the P-wave model to minimize difference between observed and calculated seismic refraction data. Traditional EAWI uses a least-squares penalty function acoustic forward-modeling engine. Conventional error is sensitive data with low signal-to-noise ratio (S/N) iterations of stop at local-minimum misfit or preassigned maximum number iterations. These...
Full-waveform inversion (FWI) is a technique for high resolution subsurface velocity estimation. Normally least-squares error between observed and calculated waveform used as penalty function, which sensitive to outliers in the data. We propose noise-resistant inverse strategy by estimating incorporating data covariance matrix into time-domain seismic inversion, termed Data weighted full-waveform (DWFWI). The built from reciprocal errors or pre-first-arrival signal-to-noise ratio. There are...
Earth and Space Science Open Archive This preprint has been submitted to is under consideration at Journal of Geophysical Research - Solid Earth. ESSOAr a venue for early communication or feedback before peer review. Data may be preliminary.Learn more about preprints preprintOpen AccessYou are viewing the latest version by default [v1]Semi-supervised Surface Wave Tomography with Wasserstein Cycle-consistent GAN: Method Application on Southern California Plate Boundary...
Earth and Space Science Open Archive PosterOpen AccessYou are viewing the latest version by default [v1]Semi-supervised Data-driven Surface Wave Tomography using Wasserstein Cycle-consistent GAN: Application on Southern California Plate Boundary RegionAuthorsAoCaiiDHongruiQiuiDFenglinNiuiDSee all authors Ao CaiiDCorresponding Author• Submitting AuthorRice UniversityiDhttps://orcid.org/0000-0003-1406-0090view email addressThe was not providedcopy addressHongrui QiuiDRice...
Seismic waveform inversion (WI) has been applied to high- resolution velocity model building at all scales, but how truthful are the amplitudes of anomalies recovered in WI models? Previous sensitivity analysis focused on estimating uncertainties, understanding radiation patterns different geophysical parameters, and separating tomography migration mode wavenumber-domain. Few studies explore if is equally high low anomalies, whereas nonlinear traveltime (TT) known be more sensitive than...