1 code implementation • 5 Sep 2023 • Alhasan Abdellatif, Ahmed H. Elsheikh
Existing texture synthesis techniques rely on generating large-scale textures using a single forward pass to the generative model; this approach limits the scalability and flexibility of the images produced.
no code implementations • 3 May 2023 • Mosayeb Shams, Ahmed H. Elsheikh
Active flow control (AFC) involves manipulating fluid flow over time to achieve a desired performance or efficiency.
1 code implementation • 7 Jul 2022 • Atish Dixit, Ahmed H. Elsheikh
For this problem, the system is partially observed since the data is only available at well locations.
1 code implementation • 7 Jul 2022 • Atish Dixit, Ahmed H. Elsheikh
RL control policies are initially learned using computationally efficient low fidelity simulations using coarse grid discretization of the underlying partial differential equations (PDEs).
no code implementations • 4 Jul 2022 • Sergey Alyaev, Jan Tveranger, Kristian Fossum, Ahmed H. Elsheikh
Probabilistic forecasts are generated using an ensemble of equiprobable model vector realizations.
1 code implementation • 11 May 2022 • Alhasan Abdellatif, Ahmed H. Elsheikh, Daniel Busby, Philippe Berthet
In this work, we investigate the problem of using Generative Adversarial Networks (GANs) models to generate non-stationary geological channelized patterns and examine the models generalization capability at new spatial modes that were never seen in the given training set.
1 code implementation • 17 Mar 2022 • Alhasan Abdellatif, Ahmed H. Elsheikh, Gavin Graham, Daniel Busby, Philippe Berthet
In this work, we investigate the capacity of Generative Adversarial Networks (GANs) in interpolating and extrapolating facies proportions in a geological dataset.
1 code implementation • 29 Nov 2021 • Sergey Alyaev, Ahmed H. Elsheikh
Geosteering of wells requires fast interpretation of geophysical logs, which is a non-unique inverse problem.
no code implementations • 10 Aug 2020 • Alexander Tarakanov, Ahmed H. Elsheikh
In other words, these techniques explore the space of possible observations and determine an experimental setup that produces maximum information about the system parameters on average.
no code implementations • 7 Apr 2019 • Shing Chan, Ahmed H. Elsheikh
The method is assessed in subsurface flow problems, where effective parametrization of underground properties such as permeability is important due to the high dimensionality and presence of high spatial correlations.
no code implementations • 20 Sep 2018 • Shing Chan, Ahmed H. Elsheikh
We synthesize new realizations such that the discrepancy in the patch distribution between the realizations and the exemplar image is minimized.
1 code implementation • 13 Jul 2018 • Shing Chan, Ahmed H. Elsheikh
This inference network is a neural network trained to sample a posterior distribution derived using a Bayesian formulation of the conditioning task.
no code implementations • 12 Nov 2017 • Shing Chan, Ahmed H. Elsheikh
Several multiscale methods account for sub-grid scale features using coarse scale basis functions.
1 code implementation • 5 Aug 2017 • Shing Chan, Ahmed H. Elsheikh
One of the main challenges in the parametrization of geological models is the ability to capture complex geological structures often observed in the subsurface.