Physics-guided data-driven seismic inversion: Recent progress and future opportunities in full-waveform inversion
The goal of seismic inversion is to obtain subsurface properties from surface measurements.
Seismic images have proven valuable, even crucial, for a variety of applications, including …
Seismic images have proven valuable, even crucial, for a variety of applications, including …
Applications of deep neural networks in exploration seismology: A technical survey
Exploration seismology uses reflected and refracted seismic waves, emitted from a
controlled (active) source into the ground, and recorded by an array of seismic sensors …
controlled (active) source into the ground, and recorded by an array of seismic sensors …
Gacnet: Generate adversarial-driven cross-aware network for hyperspectral wheat variety identification
Wheat variety identification from hyperspectral images holds significant importance in both
fine breeding and intelligent agriculture. However, the discriminatory accuracy of some …
fine breeding and intelligent agriculture. However, the discriminatory accuracy of some …
Unsupervised learning of full-waveform inversion: Connecting CNN and partial differential equation in a loop
This paper investigates unsupervised learning of Full-Waveform Inversion (FWI), which has
been widely used in geophysics to estimate subsurface velocity maps from seismic data …
been widely used in geophysics to estimate subsurface velocity maps from seismic data …
Multiscale data-driven seismic full-waveform inversion with field data study
Seismic full-waveform inversion (FWI), which uses iterative methods to estimate high-
resolution subsurface models from seismograms, is a powerful imaging technique in …
resolution subsurface models from seismograms, is a powerful imaging technique in …
Efficient progressive transfer learning for full-waveform inversion with extrapolated low-frequency reflection seismic data
The low-frequency seismic data provide crucial information for guiding the full-waveform
inversion (FWI), especially when strong reflectors exist in the velocity model. However …
inversion (FWI), especially when strong reflectors exist in the velocity model. However …
Deep Bayesian inference for seismic imaging with tasks
We use techniques from Bayesian inference and deep neural networks to translate
uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as …
uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as …
Making invisible visible: Data-driven seismic inversion with spatio-temporally constrained data augmentation
Deep learning and data-driven approaches have shown great potential in scientific
domains. The promise of data-driven techniques relies on the availability of a large volume …
domains. The promise of data-driven techniques relies on the availability of a large volume …
Deep-learning-based seismic variable-size velocity model building
M Du, S Cheng, W Mao - IEEE Geoscience and Remote …, 2022 - ieeexplore.ieee.org
Current data-driven inversion methods based on deep learning (DL) use an end-to-end
learning to obtain a mapping relationship from seismic data to the velocity model. These …
learning to obtain a mapping relationship from seismic data to the velocity model. These …
Seismic waveform inversion capability on resource-constrained edge devices
Seismic full wave inversion (FWI) is a widely used non-linear seismic imaging method used
to reconstruct subsurface velocity images, however it is time consuming, has high …
to reconstruct subsurface velocity images, however it is time consuming, has high …