... history. To create the initial ensemble, all relevant uncertainty parameters are selected after sensitivity and included using a workflow, which can become very complex and time-consuming, inside a geo-modeler. More realizations are requested until the initial ensemble passes quality check analysis...

... the quality index map for each realization. To reduce the total number of simulations runs required to cover the same total number of sampled points, multi-well sweep was used instead of the single-well sweep by running multiple well positions per simulation. The well placement is then done by an external...

... Staff 2006; Kaleta et al. 2012 ). Intersect, or any other simulator, performs the numerical simulation, and MEPO performs parameterization, statistical analysis, and optimization. Then, Petrel is triggered to generate new geological realizations based on the parameter settings identified by MEPO...

... work consisted of several steps based on conditional denoising diffusion probabilistic models. First, we generated several thousands of geologic realizations covering a wide range of spatial subsurface uncertainties. Secondly, we added various amounts of gaussian noise to these realizations and trained...

..., forked multi-lateral and stacked lateral sections. Design of these lateral sections based on the reservoir parameters is a complex process. In order to achieve the optimum design, multiple parameters and scenarios need to be considered so that economic benefits of multi-lateral wells are fully realized...

... clastic rock complex reservoir shale gas artificial intelligence mudstone geologist oil shale hydraulic fracturing modeling & simulation production control prediction realization dataset mudrock production forecasting reservoir surveillance sedimentary rock reservoir...

... of the forecasting to cases with variable natural fracture spacing and natural fracture permeability using limited training data. Source dataset contained 2000 realizations, while the target dataset contained 20, 40, 60, 80, 100, 250, 500, or 1000 realizations to represent the scenarios of limited training-data...

... geologist artificial intelligence discriminator vector realization gan realization sequence Introduction The growth of our global population and economy presents a challenge for mitigating climate change and creates an urgent demand for sustainable management of essential resources...

... and testing surrogate model. We first compare the ‘vanilla’ transformer-based surrogate with non-stationary transformer-based surrogate model for single realization case. Next, we develop non-stationary transformer-based surrogate for ensemble of 10 random realizations. In the next few paragraphs, first we...

...Introduction Abstract Accurate estimation of oil recovery and optimization of reservoir performance requires realistic estimates of permeability distribution. This paper presents an approach to build different modeling realizations for testing possible reservoir behavior during miscible gas...

... juxtaposition upstream oil & gas europe government calibration gulf international petroleum technology conference workflow juxtaposition basin realization capillary pressure estimation central west prospect sgr probability Introduction The aim of fault-seal analysis in exploration...

... development, subsurface uncertainties are typically still very large due to limited data from exploration and appraisal wells. This study outlines our approach to perform well optimization with these governing uncertainties in order to support the decision-making process. First, multiple realizations...

... and M. Bacon [ 2014 ]: Seismic Amplitude , An Interpreter's Handbook . 3 – 7 The depth realizations from SDM allow for proper quantification of gross rock volume (GRV) uncertainty which impacts hydrocarbon in-place estimations. Each realization will produce a single GRV outcome. All GRV...

... Abstract Traditional two-phase relative permeability upscaling requires the fine-scale two-phase flow simulation over the target regions/blocks. It can be very computationally expensive especially for cases with multiple (hundreds of) geological realizations (as commonly used in subsurface...

... completion installation and operations reservoir simulation drilling operation artificial intelligence directional drilling estimates of resource in place upstream oil & gas completion interval workflow resource in place estimate python script well trajectory static realization...

... modeling software is coupled with the commercial full-physics reservoir simulator as well as the optimization software in order to produce different geological realizations to represent the geological uncertainty and run the simulation model with differing inputs of optimization and uncertainty in a loop...

... variability Artificial Intelligence reservoir simulation Mau�ec Upstream Oil & Gas simulation model iteration Fluid Dynamics stochastic optimization workflow calibration uncertainty quantification fractured reservoir discrete fracture network realization inversion Simulations...

..., honoring depositional patterns and well data. A nested Sequential Indicator Simulation conditioned by seismic is then performed to model reservoir internal architecture by distributing productive facies within Geo-bodies realizations. Seismic also drives modelling of porosity by facies. Petrophysical...

... Upstream Oil & Gas deep learning modeling computational time multiplier application full-physic flow simulator proxy flow model international petroleum technology conference prediction realization history matching neural network DNN optimization brugge reservoir reservoir reservoir...

... conference architecture well location machine learning gan realization deep learning well data contextual loss interpretation training image facies architecture References References Jef Caers and Tuanfeng Zhang . Multiple-point geostatistics: A quantitative vehicle...