Figure - uploaded by Mohammadreza Azad
Content may be subject to copyright.
Source publication
In this paper, two methods of kernel bandwidth and wavelet transform are used for simultaneous upscaling of two features of hydrocarbon reservoir. In the bandwidth method, the criterion for upscaling is the cell variability, and by calculating the optimal bandwidth and determining the distance matrix, the upscaling process is performed in a complet...
Context in source publication
Similar publications
Electrical issues such as old wires and faulty connections are the most common causes of arc faults. Arc faults cause electrical fires by generating high temperatures and discharging molten metal. Every year, such fires cause a considerable deal of destruction and loss. This paper proposes a new method for detecting residential series and parallel...
Citations
... This procedure should be performed in a way that the two models act as closely as possible to each other. For example, kernel bandwidth and wavelet transformation techniques were used to simultaneously scale up the porosity and permeability of a synthetic reservoir model by (Azad et al., 2021). Under the same circumstances, the simulation runs demonstrated that the upscaling error of the bandwidth method was much smaller than that of the wavelet method. ...
In multiscale modeling of subsurface fluid flow in heterogeneous porous media, standard polynomial basis functions are replaced by multiscale basis functions. For instance, to produce such functions in the mixed Generalized Multiscale Finite Element Method (mixed GMsFEM), a number of Partial Differential Equations (PDEs) must be solved, which requires a considerable overhead. Thus, it makes sense to replace PDE solvers with data-driven methods, given their great capabilities and general acceptance in the recent decades. Convolutional Neural Networks (CNNs) automatically perform feature engineering, and they also need fewer parameters via defining two-dimensional convolutional filters without reducing the quality of models. This is why four distinct CNN models were developed to predict four different multiscale basis functions for the mixed GMsFEM in the present study. These models were applied to 249,375 samples, with the permeability field as the only input. The statistical results indicate that the AMSGrad optimization algorithm with a coefficient of determination (R²) of 0.8434–0.9165 and Mean Squared Error (MSE) of 0.0078–0.0206 performs slightly better than Adam with an R² of 0.8328–0.9049 and MSE of 0.0109–0.0261. Graphically, all models precisely follow the observed trend in each coarse block. This work could contribute to the distribution of pressure and velocity in the development of oil/gas fields. Looking at this work as an image (matrix)-to-image (matrix) regression problem, the constructed data-driven-based models may have applications beyond reservoir engineering, such as hydrogeology and rock mechanics.
