... conference neural information processing system r-dp dataset algorithm machine learning interpolation zhang approximation international conference noise limitation reconstruction validation (5) =   α - t x 0   +   1 - α - t ϵ...

... reservoir enhanced recovery cmg-star 11-component history match cisc operation reaction sagd carbon dioxide injection hansen solubility parameter carbon dioxide ga steam-assisted gravity drainage heavy oil play pleito creek mpa 0 composition api gravity viscosity approximation Background...

..., I used supervised learning for approximating and compressing the traveltime tables by artificial neural networks. Second, I used unsupervised learning for solving the eikonal equation. I used fully-connected neural networks for solving both problems. For the first problem, I used traveltimes...

... the recorded force displacement data are used to obtain the dimensionless stress-strain curve. Both the crack lengths and the dimensionless stress strain curve are then used as the input to the phase field model developed to approximate the fracture toughness of the rock tested. Scratch tests are performed...

... process we utilize a trained Deep Recurrent Neural Network (RNN) to approximate the reservoir simulator flows, which are subsequently used to compute the economic performance of a drilling policy through its discounted cash flows. The RNN is trained and tested on a set of reservoir simulator runs over...

... characterization lwd discontinuity inversion drilling data acquisition approximation inversion mismatch drilling measurement upstream oil & gas inversion result logging while drilling inverted alignment angle deep directional resistivity measurement reservoir map society of petroleum engineers...

... and spatial distribution of rock components, divergence in mechanical properties of minerals, and pore structure on variations in effective elastic properties of rock components. For instance, the deformation of clay minerals dispersed in between the quartz minerals was approximately 60% less than...

...-dependent permeability coefficients. A perturbation technique is applied to mathematically treat the described nonlinearity to solve for the coupled equations of pore fluid flow and rock stress under steady-state flow. The good match between the obtained analytical approximations for productivity index...

... to approximate the BHP of any given well on any given producing day. The resulting correlation could be incorporated in my workflow and—after combined with other input data—my software could determine, with sufficient accuracy, the critical rate of any given well on any given producing day. An engineer can use...

... obtained from other approaches. Multiple local maximum-a-posteriori (MAP) estimates are located with the local-search DGN optimization method. A GMM is constructed to approximate the posterior probability density function, by fitting simulation results generated during the DGN minimization process...

... as a design reference. It is also observed that the outer string in a dual-string system tends to withstand more moments because of greater stiffness. Proper application of this new dual-string buckling model design can help reduce costs. Artificial Intelligence approximation length change potential...

... Abstract It is crucially important for decision making and an extremely challenging task to properly quantify uncertainty of model parameters and production forecasts after conditioning to production data. A novel approach is proposed to generate approximate conditional realizations using...

... anomalous diffusion saturation distribution fracture diffusion oil water flow Drillstem Testing multiphase flow anomalous diffusion model Fluid Dynamics approximation boundary derivative equation Introduction Modeling fluid flow in unconventional reservoirs poses many difficulties...

... Oil & Gas Thomsen practical application characteristic modeling effective medium theory mathematical model aspect ratio Reservoir Characterization approximation tensor Applicability effective elastic property Artificial Intelligence comparison body porous rock porosity elastic...

... the full-order state solution such as pressure and saturation, evaluate the full-order nonlinear term before projecting it onto a reduced subspace. Therefore, we developed a reduced-order reservoir model based on a discrete empirical interpolation method (DEIM) to approximate nonlinear phase potential...

... the downside effects for a chemical EOR process. The method is a stochastic approximate dynamic programming approach to decision making. It is based on a forward simulation coupled with a recursive algorithm which produces the near-optimal policy. It relies on Monte Carlo simulation to produce convergent...

... Diffusivity Approximation Development The 1D radial flow diffusivity equation for the flow of a single-phase (gas) fluid in the presence of a desorbing phase can be written as: Equation A-1 − 1 r ∂ ∂ r ( r ρ v ) = ∂ ∂ t ( ϕ f ρ ) + ∂ ∂ t ( ρ s c...

... against several analytical solutions and also demonstrate the approach's ability to predict complex fracture systems with example of multiple interacting fractures. artificial intelligence approximation numerical simulation expression upstream oil & gas simulation francfort variational...

... may result in significant error. The new method enables petroleum engineers to calculate the average reservoir pressure accurately for every reservoir type by integrating transient, production, and static data. Our technique calculates a robust approximation of the drainage area based...

... Abstract Flow of Bingham fluids in plane Couette-Poiseuille flow is studied. We present a set of analytically flow equations for flow between parallel plates/slots in a most compact form, and use this set as a basis for developing simpler flow equations. The new equations approximate the full...