End-to-end neural network approach to 3D reservoir simulation and adaptation

Illarionov, Egor; Temirchev, Pavel; Voloskov, Dmitry; Kostoev, Ruslan; Simonov, Maksim; Pissarenko, Dimitri; Orlov, Denis; Koroteev, Dmitry

doi:10.1016/j.petrol.2021.109332

Cited by 14 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Illarionov E. et al [59] presented a unified approach to reservoir simulation and HM by using a single encoder-decoder ANN with commonly used gradient-based optimization methods for both processes. The authors used the geological parameters of a 3D reservoir model as input to the model and production rate predictions as output.…”

Section: Static Machine Learning Modelsmentioning

confidence: 99%

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Samnioti,

Gaganis

2023

Energies

View full text Add to dashboard Cite

In recent years, Machine Learning (ML) has become a buzzword in the petroleum industry, with numerous applications which guide engineers in better decision making. The most powerful tool that most production development decisions rely on is reservoir simulation with applications in multiple modeling procedures, such as individual simulation runs, history matching and production forecast and optimization. However, all of these applications lead to considerable computational time and computer resource-associated costs, rendering reservoir simulators as not fast and robust enough, and thus introducing the need for more time-efficient and intelligent tools, such as ML models which are able to adapt and provide fast and competent results that mimic the simulator’s performance within an acceptable error margin. In a recent paper, the developed ML applications in a subsurface reservoir simulation were reviewed, focusing on improving the speed and accuracy of individual reservoir simulation runs and history matching. This paper consists of the second part of that study, offering a detailed review of ML-based Production Forecast Optimization (PFO). This review can assist engineers as a complete source for applied ML techniques in reservoir simulation since, with the generation of large-scale data in everyday activities, ML is becoming a necessity for future and more efficient applications.

show abstract

Section: Static Machine Learning Modelsmentioning

confidence: 99%

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Samnioti,

Gaganis

2023

Energies

View full text Add to dashboard Cite

show abstract

“…Прокси-моделирование основывается на упрощенном подходе, в котором используется ограниченный набор наиболее важных данных, которые, как правило, определяются с большей достоверностью. Подобные модели могут быть как физически содержательными: супер элементы [3], CRM (Capacity-Resistance Model) [10], линии тока [4], характеристики вытеснения [6], так и чисто математическими или статистическими: нейросети [7], деревья решений [5]. Как правило, такие модели способны решать прикладные задачи быстрее, чем классическое гидродинамическое моделирование, что является очень важным преимуществом при решении ресурсоемких задач, к которым относятся задачи адаптации и оптимизации.…”

Section: ключевые словаunclassified

Applying proxy-modeling tools to estimate the effective injection factor for an oil field

Kosyakov

Musakaev

Gaydamak

2022

TSU Herald. Phys Math Model. Oil, Gas, Energy

View full text Add to dashboard Cite

This work is devoted to the joint use of physically based proxy models of different levels of complexity to determine the effective injection ratio factor. Effective injection factor is a parameter that reflects the proportion of injected fluid that enters the reservoir and does useful work to maintain reservoir pressure and displace oil from the reservoir. The selection of the effective injection factor when using a full-scale hydrodynamic simulator is difficult due to the high requirements for computational and time resources. Therefore, to calculate this coefficient, it is justified to use the simplified proxy modeling approach, which allows to evaluate the desired parameter in an acceptable time frame. The task of finding the effective injection ratio is related to inverse problems. The following were used as proxy models: a material balance model for the field as a whole and for a system of hydrodynamically connected blocks, a capacitance-resistance model (CRM) and a two-dimensional filtration model. The order of the models corresponds to the hierarchical principle "from simple to complex". Based on the history of oil field development (production, fluid injection, reservoir and bottomhole pressure), the effective injection coefficients were obtained, they were compared, and the analysis of the results was carried out.

show abstract

“…once all the geological factors (starting and boundary conditions) and control parameters are determined. A standard approach is based on the numerical evaluation of a system of hydrodynamic equations, ( Illarionov et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

A novel methodology for fast reservoir simulation of single-phase gas reservoirs using machine learning

Bhattacharyya

Vyas

2022

Heliyon

View full text Add to dashboard Cite

End-to-end neural network approach to 3D reservoir simulation and adaptation

Cited by 14 publications

References 6 publications

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Applying proxy-modeling tools to estimate the effective injection factor for an oil field

A novel methodology for fast reservoir simulation of single-phase gas reservoirs using machine learning

Contact Info

Product

Resources

About