The oil hydrocarbon industry faces many new challenges regarding the depletion of the conventional oil and gas reservoirs including tight sand, gas and oil shales, fractured reservoirs, etc. Thereby, the development and exploration of the unconventional oil and gas reservoirs and the high water cut conventional reservoirs are in need to new mathematical and experimental methodologies for reducing the uncertainty level and exploration cost. Artificial intelligence technologies such as machine learning have been widely applied to solve the problems in oil and gas reservoirs, such as automatic identification for lithology and microfacies, monitoring the well drilling, matching the production history, predicting the optimum production rates, etc. Meanwhile, for the unconventional oil and gas reservoirs and mature oil reservoirs with high water-cut, advanced experimental equipment and methods are needed to characterize the spatial pore structures in the tight matrix, study the mechanism of single or multiphase flow in porous media, and explore the most effective way to enhance the oil and gas recovery.
In this concern, the purpose of this research topic is to provide a platform for the researchers to share their recent new methodologies of mathematical modelling and experimental studies in both conventional and unconventional oil and gas reservoirs.
Potential topics of interest include, but are not limited to:
• Application of machine learning in reservoir geology and petroleum engineering
• Digital rock and flow in porous media
• Enhanced oil recovery
• Reservoir characterization
• Unconventional oil and gas reservoirs
The oil hydrocarbon industry faces many new challenges regarding the depletion of the conventional oil and gas reservoirs including tight sand, gas and oil shales, fractured reservoirs, etc. Thereby, the development and exploration of the unconventional oil and gas reservoirs and the high water cut conventional reservoirs are in need to new mathematical and experimental methodologies for reducing the uncertainty level and exploration cost. Artificial intelligence technologies such as machine learning have been widely applied to solve the problems in oil and gas reservoirs, such as automatic identification for lithology and microfacies, monitoring the well drilling, matching the production history, predicting the optimum production rates, etc. Meanwhile, for the unconventional oil and gas reservoirs and mature oil reservoirs with high water-cut, advanced experimental equipment and methods are needed to characterize the spatial pore structures in the tight matrix, study the mechanism of single or multiphase flow in porous media, and explore the most effective way to enhance the oil and gas recovery.
In this concern, the purpose of this research topic is to provide a platform for the researchers to share their recent new methodologies of mathematical modelling and experimental studies in both conventional and unconventional oil and gas reservoirs.
Potential topics of interest include, but are not limited to:
• Application of machine learning in reservoir geology and petroleum engineering
• Digital rock and flow in porous media
• Enhanced oil recovery
• Reservoir characterization
• Unconventional oil and gas reservoirs