no code implementations • 9 Feb 2024 • Fu Wang, Xinquan Huang, Tariq Alkhalifah
Accurate seismic velocity estimations are vital to understanding Earth's subsurface structures, assessing natural resources, and evaluating seismic hazards.
no code implementations • 16 Oct 2023 • Tariq Alkhalifah, Xinquan Huang
Specifically, for the Helmholtz equation, we augment the fully connected neural network model with an adaptable Gabor layer constituting the final hidden layer, employing a weighted summation of these Gabor neurons to compute the predictions (output).
no code implementations • 10 Aug 2023 • Xinquan Huang, Tariq Alkhalifah
The computation of the seismic wavefield by solving the Helmholtz equation is crucial to many practical applications, e. g., full waveform inversion.
no code implementations • 9 Aug 2023 • Randy Harsuko, Tariq Alkhalifah
StorSeismic is a recently introduced model based on the Transformer to adapt to various seismic processing tasks through its pretraining and fine-tuning training strategy.
no code implementations • 16 Jul 2023 • Yuanyuan Yang, Claire Birnie, Tariq Alkhalifah
Microseismic event detection and location are two primary components in microseismic monitoring, which offers us invaluable insights into the subsurface during reservoir stimulation and evolution.
no code implementations • 22 Jun 2023 • Fu Wang, Xinquan Huang, Tariq Alkhalifah
Specifically, we pre-train a diffusion model in a fully unsupervised manner on a prior velocity model distribution that represents our expectations of the subsurface and then adapt it to the seismic observations by incorporating the FWI into the sampling process of the generative diffusion models.
no code implementations • 25 May 2023 • Francesco Brandolin, Matteo Ravasi, Tariq Alkhalifah
Interpolation of aliased seismic data constitutes a key step in a seismic processing workflow to obtain high quality velocity models and seismic images.
no code implementations • 11 May 2023 • Mohammad H. Taufik, Tariq Alkhalifah
We use a two-stage training scheme in which the first stage, we learn the latent representations for the distribution of PDE parameters.
no code implementations • 9 Apr 2023 • Xinquan Huang, Tariq Alkhalifah
To be more specific, we modify the representation of the frequency-domain wavefield to inherently satisfy the boundary conditions (the measured data on the surface) by means of a hard constraint, which helps to avoid the difficulty in balancing the data and PDE losses in PINNs.
no code implementations • 26 Feb 2023 • Xinquan Huang, Tariq Alkhalifah
Physics-informed neural networks (PINNs) have attracted a lot of attention in scientific computing as their functional representation of partial differential equation (PDE) solutions offers flexibility and accuracy features.
no code implementations • 30 Dec 2022 • Muhammad Izzatullah, Tariq Alkhalifah, Juan Romero, Miguel Corrales, Nick Luiken, Matteo Ravasi
However, selecting appropriate prior information in a probabilistic inversion is crucial, yet non-trivial, as it influences the ability of a sampling-based inference in providing geological realism in the posterior samples.
no code implementations • 25 Sep 2022 • Claire Birnie, Tariq Alkhalifah
To preempt the network's ability to predict the signal and reduce its opportunity to learn the noise properties, we propose an initial, supervised training of the network on a frugally-generated synthetic dataset prior to fine-tuning in a self-supervised manner on the field dataset of interest.
no code implementations • 28 May 2022 • Muhammad Izzatullah, Isa Eren Yildirim, Umair bin Waheed, Tariq Alkhalifah
This work focuses on predicting the hypocenter locations using HypoPINN and investigates the propagation of uncertainties from the random realizations of HypoPINN's weights and biases using the Laplace approximation.
1 code implementation • 30 Apr 2022 • Randy Harsuko, Tariq Alkhalifah
We present StorSeismic, as a framework for seismic data processing, which consists of neural network pre-training and fine-tuning procedures.
no code implementations • 29 Sep 2021 • Xinquan Huang, Tariq Alkhalifah
Solving for the frequency-domain scattered wavefield via physics-informed neural network (PINN) has great potential in seismic modeling and inversion.
no code implementations • NeurIPS Workshop AI4Scien 2021 • Xinquan Huang, Tariq Alkhalifah
However, the neural network (NN) training can be costly and the cost dramatically increases as we train for multi-frequency wavefields by adding frequency to the NN multidimensional function, as the variation of the wavefield with frequency adds more complexity to the NN training.
no code implementations • 15 Sep 2021 • Claire Birnie, Matteo Ravasi, Tariq Alkhalifah, Sixiu Liu
Illustrated on synthetic examples, the blind-spot network is shown to be an efficient denoiser of seismic data contaminated by random noise with minimal damage to the signal; therefore, providing improvements in both the image domain and down-the-line tasks, such as inversion.
no code implementations • 11 Sep 2021 • Tariq Alkhalifah, Hanchen Wang, Oleg Ovcharenko
This is accomplished by applying two operations on the input data to the NN model: 1) The crosscorrelation of the input data (i. e., shot gather, seismic image, etc.)
1 code implementation • 17 Aug 2021 • Tariq Alkhalifah, Oleg Ovcharenko
In the training stage, as expected, the input images are from the source domain, and the mean of auto-correlated images are evaluated from the target domain.
no code implementations • 8 Feb 2020 • Bingbing Sun, Tariq Alkhalifah
In the workflow of Full-Waveform Inversion (FWI), we often tune the parameters of the inversion to help us avoid cycle skipping and obtain high resolution models.
no code implementations • 8 Feb 2020 • Bingbing Sun, Tariq Alkhalifah
Most of the available advanced misfit functions for full waveform inversion (FWI) are hand-crafted, and the performance of those misfit functions is data-dependent.