Chain-based machine learning for full PVT data prediction

Ghorayeb, Kassem; Mawlod, Arwa; Maarouf, Alaa; Sami, Qazi; Droubi, Nour El; Merrill, R.; Jundi, Obeida El; Mustapha, Hussein

doi:10.1016/j.petrol.2021.109658

Cited by 14 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is significant for calculating reservoir fluid phase properties and evaluating surface production and surface separation facilities. The advantage is that the same equations can be used to simulate all phase behavior changes, ensuring consistency in phase equilibrium calculations. , As PVT databases of shale oil reservoirs are often incomplete, and it is difficult to obtain them accurately, various EOS, machine learning (ML), or combinations of these methods have recently gained a lot of attention. − This work briefly introduces some critical EOSs and their modification, making them more suitable for phase behavior studies in unconventional reservoirs, specifically oil shales. Due to the limitation of the applicability of the EOS, scholars have continuously tried to develop and improve them.…”

Section: Phase Behavior Of Shale Oilmentioning

confidence: 99%

Comprehensive Outlook into Critical Roles of Pressure, Volume, and Temperature (PVT) and Phase Behavior on the Exploration and Development of Shale Oil

et al. 2022

View full text Add to dashboard Cite

Shale oil has received increasing attention as an essential replacement for conventional oil resources. Shale oil recovery is a complex process controlled by interactions of many factors whose impact could be significantly different from conventional reservoirs. This study hence aims to fill the gaps in the literature by studying various aspects of the phase behavior of shale oil and their significance in different aspects of the recovery from oil shale. In the first part of this study, the standard practices, including experimental and theoretical methods for calculating the pressure, volume, temperature (PVT), and phase behavior of shale oil, is discussed in detail. Next, the effects of factors such as the composition of fluids, pore structure, and capillary forces on the phase behavior of hydrocarbon fluids are explained. The third part focuses on applying phase behavior for oil shale development. Moreover, the geological and geochemical processes that lead to the maturity of kerogen, the formation of shale oil, and the experimental methods by which those processes are currently studied are scrutinized. By studying the thermal and burial history of the hydrocarbon-generating strata and hydrocarbon-generating kinetics, the shale formation's oil and gas phase distribution can be predicted. Consequently, the sweet spots for the recovery of light condensate oil can be more accurately determined. The application of enhanced oil recovery methods is an inevitable part of recovery from conventional and unconventional formations. Therefore, the last part of this study analyses the changes in the phase behavior of shale oil when an external component, i.e., CO 2 or CH 4 , is injected into the reservoir. Reviewing the literature revealed that a more accurate prediction of hydrocarbon phase behavior can be made by combining different disciplines of science to achieve optimized plans for efficient shale oil development, making shale oil a more economically viable energy resource.

show abstract

Section: Phase Behavior Of Shale Oilmentioning

confidence: 99%

Comprehensive Outlook into Critical Roles of Pressure, Volume, and Temperature (PVT) and Phase Behavior on the Exploration and Development of Shale Oil

et al. 2022

View full text Add to dashboard Cite

show abstract

“…El uso de modelos de aprendizaje automático en la industria petrolera se ha incrementado substancialmente a raíz de que la cantidad de datos que tienen que manejar, procesar y analizar es cada vez mayor. En este sentido, se deben destacar los esfuerzos dedicados desde finales de los años 1990 para utilizar el aprendizaje automático en la predicción de las propiedades obtenidas de los análisis PVT [3].…”

Section: Introductionunclassified

Predicción de la presión de burbujeo utilizando aprendizaje automático

Gil

2023

Innov. softw.

View full text Add to dashboard Cite

En el presente estudio se utilizó la colección de algoritmos de aprendizaje automático del programa Weka para predecir la presión de burbujeo de 36 muestras de petróleo, determinando la precisión de sus resultados con el método de prueba validación cruzada de 10 pliegues. Posteriormente, para efectos de comparación, se calcularon las presiones de burbujeo con la correlación generada en el trabajo del cual se tomaron las muestras y sus resultados fueron más precisos que los obtenidos por los algoritmos en 4 de las 7 métricas de rendimiento utilizadas. En virtud de esta situación, y considerando que la correlación fue evaluada con los mismos datos con los que fue generada, se cambió el método de prueba a validación con los datos de entrenamiento y se volvieron a predecir las presiones de burbujeo. En igualdad de condiciones, el aprendizaje automático obtuvo mayor precisión que la correlación en todas las métricas de rendimiento.

show abstract

“…The accuracy of PVT experiment results is significant for the study of the phase characteristics of formation fluids [37][38][39]. However, the current methods are all aimed at reservoirs at normal temperature.…”

Section: Introductionmentioning

confidence: 99%

Consistency Checks for Pressure-Volume-Temperature Experiment of Formation Oil and Gas at High Temperature

Zhao,

Zhang,

et al. 2023

Processes

View full text Add to dashboard Cite

The oil and gas phase behavior of high temperature is complex and changeable, which is usually obtained by PVT experiments. The accuracy of the experiment data plays a crucial role in the reserve evaluation and development plan of oil and gas reservoirs. However, the current PVT experiment consistency checks are not suitable for high-temperature reservoir conditions. This paper proposes a systematic check method for the PVT experiment data consistency at high temperature. These checks revise the material balance method, Hoffman method, and equilibrium constant method by using the equilibrium constant calculation method at high temperature. The consistency check of component data and constant volume depletion experiment data is carried out by combining the three improved methods with the component check method, so as to judge the experiment data accurately. In this paper, two high-temperature reservoir fluids—gas condensate sample fluid X and volatile oil sample fluid Y—are selected to carry out consistency checks with component data and constant volume depletion data. This check method is of great significance to study the phase behavior of formation oil and gas at high temperature, especially for volatile oil and gas condensate fluid.

show abstract

Chain-based machine learning for full PVT data prediction

Cited by 14 publications

References 43 publications

Comprehensive Outlook into Critical Roles of Pressure, Volume, and Temperature (PVT) and Phase Behavior on the Exploration and Development of Shale Oil

Comprehensive Outlook into Critical Roles of Pressure, Volume, and Temperature (PVT) and Phase Behavior on the Exploration and Development of Shale Oil

Predicción de la presión de burbujeo utilizando aprendizaje automático

Consistency Checks for Pressure-Volume-Temperature Experiment of Formation Oil and Gas at High Temperature

Contact Info

Product

Resources

About