... production forecasting geologist optimization problem asset and portfolio management production control ensemble bayesian inference production monitoring iteration geology converge flow in porous media em-evd-tl algorithm em-cd algorithm reservoir surveillance em algorithm configuration two...

... reservoir simulation accuracy dnn-hm workflow ssim workflow noise optimization history matching cg-hm neural network iteration reservoir simulator permeability scenario Introduction In the realm of reservoir engineering and petroleum geosciences, history matching is a fundamental...

... In this work, we present a tightly-coupled approach that combines the use of surrogate AI models and ensemble-based iterative optimization algorithms to enhance the history matching process. The efficiency of the hybrid approach is demonstrated on modified NORNE and BRUGGE benchmark models...

... has been developed that can provide similar results in a fraction of the time. The new approach utilizes a direct integration scheme of forces, moments, rotations, and deflections along the drillstring. Contact forces are then determined iteratively over the length of the drillstring. This results...

... to correctly identify relevant information with its capability to find all pertinent data. An iterative fine-tuning process allowed us to address specific challenges in oil and gas data extraction, such as distinguishing between active and production wells. We developed a novel LLM framework that conducts...

... Abstract Reliable and efficient modeling of subsea production systems is critical for predicting performance of offshore reservoirs. Iterative numerical procedures are typically required if the production system includes flow networks where wells may compete and interact with each other...

..., and are obtained from the training set. Since during the ISR process, the training set changes, J min and J max may change from iteration to iteration. Due to the min-max scaling defined by Eq. 13 , all scaled bound constraints are between zero and one: (15) 0 ≤ u ¯ k ≤ 1...

... Abstract Previous implementation of distributed Gauss-Newton (DGN) optimization algorithm runs multiple optimization threads in parallel, employing a synchronous running mode (S-DGN). As a result, it waits for all simulations submitted in each iteration to complete, which may significantly...

... , where J min and J max represent minimum and maximum values of the NPV, respectively, and are obtained from the training set. Since during the iterative-sampling-refinement optimization process, the training set changes, J min and J max may change from iteration to iteration. Optimization...

... integrity subsurface corrosion riser corrosion upstream oil & gas neural network corrosion machine learning modeling artificial intelligence flowline corrosion co 2 iteration tsai spe annual technical conference pipeline corrosion application predictive modeling materials and corrosion...

... iteration drilling window directional drilling trajectory exhibition oclc cost function well path particle swarm optimization curve segment Introduction During the well construction process, DDs are required to follow a predetermined well path. This path is created to ensure the well...

... multiple local optima of highly nonlinear optimization problems. However, its performance has neither been validated by realistic applications nor compared to other DFO methods. We have integrated DQN into a versatile field-development optimization platform designed specifically for iterative workflows...

... automated approach applied oil recovery fluid dynamics optimization optimization algorithm full field model artificial intelligence reservoir simulation constraint iteration well location optimized location Introduction Identifying optimal well configurations is crucial for maximizing...

...) techniques to reduce the number of simulations for optimizing long-term well control strategy while preserving the quality of the solution. We proposed a methodology, denoted as IDLHC–ML, which combines many ML techniques with iterative discrete Latin hypercube (IDLHC) – a gradient-free optimization...

... GOR and WOR. The pressure at the elbow turning point of two uphill and downhill sections is assumed to be the same to ensure the pressure continuity. Then, by the given surface or bottom (reservoir) pressure, the gas/oil and oil/water interfaces are calculated with iterations with a numerical method...

... requires multiple iterations where the compositions of the phases are adjusted with each iteration. Under bulk conditions, the vapor and liquid phase pressures are considered to be equal and therefore cancel out in Eq. (7) . However, in this work the vapor and liquid phase pressures are retained...

... Intelligence Upstream Oil & Gas machine learning history matching spe annual technical conference uncertainty parameter application workflow algorithm rejection society of petroleum engineers forecast ensemble smoother iteration uncertainty quantification probabilistic history History...

.... It is an iterative process, which yields the correct initial gas in place, whereas the use of real time does not. The algorithm is validated with a two gas well synthetic example, and successfully applied to a field case with four gas producers. Novel/Additive Information The paper extends the application...

... matching reservoir simulation hydraulic fracturing Upstream Oil & Gas fracture height simulation result prediction optimization problem objective function model parameter application iterative ensemble smoother Optimization Method Scenario complex reservoir iteration Reynolds society...

... examples from the Barnett shale are illustrated using mechanisms previously proposed in the literature as well as the method presented in this paper. The later provided consistent ISIP values after multiple iterations. Subsequently, the reservoir characteristics and calculated parameters were uniform...