... simulator commercial simulator commercial reservoir simulator objective function forward simulation implementation Introduction Abstract Efficient history matching of reservoir simulation models remains a paramount challenge in the oil and gas industry, as it is crucial for improving...

..., derivative-free optimization utilized to handle simulation-based objective functions required more than 100 independent control variables per trial. Advanced reservoir and well modeling addressed the high viscosity gradient of the fluid, and a robust algorithm was used to traverse the multidimensional...

... ) , where J ( u ) is the objective function, i.e. the performance metric quantifying the quality of solutions in terms of the goals of the optimization, and u is the control vector containing the optimization or control variables describing the solutions, i.e. the degrees of freedom that may be varied...

... Similarly to the previous works mentioned above, we employ a superposition principle and an optimization-based approach to compute a consistent stress field that honors the given measurements and equilibrium. We pose the compatibility problem by minimizing an objective function in the classical...

... Direct gradient-free methods employ the problem cost function directly as the objective function of the optimizer ( Redouane et al. 2018 ), within which the optimization is carried out by generating a population of individuals that search the space simultaneously without any derivative...

... in porous media realization onur machine learning case 10 100 geologist realization 1 well control production optimization neural network optimization spe10 model e2co prediction nonlinear state constraint realization 5 denote nguyen and onur pressure distribution objective function...

.... A comparative study of different optimization methods is conducted, using the Egg model, to find the optimal objective function value using a reasonable number of function evaluations. Derivative-free optimization algorithms, known for their searching robustness and flexibility, are selected for tackling...

... matrix adaptation evolution strategy (CMA-ES). Results show that IBO achieves competitive objective function value with over 60% less number of forward model evaluations. Furthermore, the Bayesian framework that BO builds upon allows uncertainty quantification and naturally extends to optimization under...

...-thread optimization method that distributes an ensemble of optimization tasks among multiple high-performance-computing nodes, and thus, it can locate multiple optima of the objective function in parallel within a single run. Simulation results computed from one DQN optimization task or thread are shared...

...) compositional simulation model with advanced Field Management (FM) logic was used to perform the study. Vertical conformance control was implemented in the model enabling completion control of 4 compartments per well. A model-based optimization workflow was defined to maximize recovery. Objective functions...

... it to be useful for engineers designing IOR pilot for brown fields with complex reservoir models. Artificial Intelligence objective function enhanced recovery Upstream Oil & Gas reservoir simulation posterior distribution machine learning history matching Effectiveness uncertainty reduction...

... provides a good match with production data. flow in porous media Artificial Intelligence machine learning Fluid Dynamics modeling training data compaction-dilation data Upstream Oil & Gas interpolation neural network parameter space objective function algorithm society of petroleum...

... development activities by obtaining optimization solutions that are robust against changes in future decisions, and (2) considerably reduces the performance losses that can result from field development when uncertainty is disregarded. optimization problem objective function asset and portfolio...

... Index (HMQI) with Moving Linear Regression Analysis to evaluate simulation results from history matching process. The HMQI provides normalized values for all objective functions having different magnitude and leads to a more consistent and robust approach to evaluate the updated models through model...

... the objective functions. The study demonstrates the potential impacts of reservoir heterogeneities on the WSI process. Models with different heterogeneity settings are examined. The results reveal that the impacts of shale barriers may be more/less evident under different circumstances. The proxy models can...

... significant increases between 5% and 20% in the expected value of the objective function were achieved. For the multi-objective optimization cases we show that non-trivial optimal strategies are obtained which significantly reduce (40% decrease) gas production with minimal loss (less than 1%) in the economic...

... by "twiddling the knobs" of software, as humans can be very good at comparing examples but unable to produce an optimal objective function ( Shahriari et al. , 2016 ). Third, an optimization opportunity never comes from nowhere. Understanding of its backing mechanism (e.g., physics) is the key to convince...

.... Like in history matching, production optimization under uncertainty is an iterative process that considers all history matched ensemble members. The goal in this step is to find a set of inputs that optimize an objective function derived from all ensemble outputs. Those outputs are computed scalar...

... & Gas error function gaussian component Gao fitting method normalized error function gmm fitting formulation formulation History algorithm uncertain parameter reservoir simulation training data Optimization Method gmm sample objective function gmm fitting method reduced-dof gmm fitting...

... of the history match and the quality of the forecast. So, the traditional belief that a good history matched model will also produce a good forecast is not always true. Artificial Intelligence Upstream Oil & Gas correlation Modeling & Simulation objective function reservoir simulation case...