... control variable evolutionary algorithm input parameter optimization problem simulation result machine learning upstream oil & gas co 2 pareto front hyperparameter iteration numerical model dataset training database workflow knowledgebase ampomah optimization workflow petroleum...

... subsurface storage climate change bayesian inference evolutionary algorithm sequestration wheeler probabilistic surrogate acquisition function optimization problem bayesian optimization optimization application gaussian process upstream oil & gas simulation function evaluation carbon...

.... In addition, it is also an automatic process that fits well with iterative optimization algorithms. machine learning reservoir characterization production monitoring risk management reservoir simulation drillstem/well testing drill sequence evolutionary algorithm enhanced recovery asset...

...: core scale, pilot scale, and field scale. History matching and optimization are two key steps to achieve this goal. For history matching chemical floods, we propose a general workflow for multi-stage model calibration using an Evolutionary Algorithm. A comprehensive chemical flooding simulator is used...

... volume. CMA-ES outperforms GA in that it is more robust, and it achieves higher objective function value in less simulation runs. The optimized SAG process achieves 27.55% more CO 2 storage volume and reduces water and surfactant consumption by 54.84%. evolutionary algorithm machine learning...

... Artificial Intelligence information evolutionary algorithm Upstream Oil & Gas History development well production assimilation workflow well location saturation assimilation data assimilation production data simulation saturation map ensemble acquisition seismic data development...

... fractures as shown in Fig. 1b , both of these natural fractures will be activated. Methods Geomechanical Analysis machine learning Upstream Oil & Gas scale fracture hydraulic fracturing natural fracture model parameter fracture network evolutionary algorithm fracture pattern CFN...

... trajectory simultaneous optimization potential location drilling order NPV optimal npv optimization producer Upstream Oil & Gas drilling order optimization sequential optimization algorithm joint optimization machine learning configuration gradient evolutionary algorithm optimal solution...

... is to calibrate the geologic model of the test site by reducing the discrepancy between observed and simulated Fourier parameters and assess uncertainties associated with the compositional brine-CO 2 flow. An assisted history matching tool that mounts global- and multi-objective evolutionary algorithms...

... robust estimates of uncertainty when predicting field-scale recovery compared to simulations that only consider uncertainty in the reservoir model. evolutionary algorithm reservoir simulation History enhanced recovery Upstream Oil & Gas experiment Artificial Intelligence surfactant foam...

... reservoir simulation gridpoint snapshot evolutionary algorithm deim point Model Reduction reduction interpolation method spe 163 pressure field physics physics model machine learning Upstream Oil & Gas time step bsim saturation model reduction technique surrogate equation...

... trade-off as the extreme choices of using of all the cores by the simulator or limiting each simulation to a single core and using each core for a separate history matching run may not be optimal. reservoir simulation multiplier simulator evolutionary algorithm Upstream Oil & Gas...

.... The problem is particularly severe if the objectives are conflicting. In this paper we propose to use a Pareto-based multi-objective evolutionary algorithm (MOEA) focusing on finding a set of optimal solutions called Pareto optima. The MOEA makes direct use of the dominance relation for fitness assignment...

... of flexible rules in history matching and optimization that honor engineering knowledge. evolutionary algorithm machine learning reservoir simulation fuzzy logic Artificial Intelligence optimization problem constraint Differential Evolution penalty penalty function optimization Upstream Oil...

... , k = 1 , 2 , … , K } machine learning reservoir simulation evolutionary algorithm upstream oil & gas optimization problem objective-sum approach multiobjective optimization uncertainty estimate history uncertainty quantification history matching misfit value...

... and, by allowing the search to move towards worse solutions occasionally, gain the ability to seek out the global optimum. Stochastic algorithms vary in sophistication and complexity, ranging from random search to hill-climbing and population based evolutionary algorithms. Population based algorithms have been...

... concepts have the potential to be effective tools in uncertainty quantification in the oil industry. Bayesian Inference History evolutionary algorithm machine learning Upstream Oil & Gas reservoir simulation iteration parameter space multiple history HMC misfit reservoir model...

... kernel spe 119177 kenkf realization evolutionary algorithm history matching random field geologic modeling Reservoir Characterization Upstream Oil & Gas true permeability field EnKF matrix kernel initial ensemble final ensemble marginal distribution equation permeability field...

... Abstract Evolutionary Algorithms and local optimization methods are applied to the problem of history matching in reservoir engineering. Application of global optimization methods to history matching of complex reservoir models is generally limited by the convergence behavior. In this paper...

... engineering problems 12 - 15 . In this work the application of Evolution Strategies to the problem of history matching in reservoir engineering is presented. The methodology is introduced and the implementation of Evolutionary Algorithms on parallel processors is addressed. Results are discussed...