Image of Use of AI tools to understand and model surface-interaction based EOR processes

Text

Use of AI tools to understand and model surface-interaction based EOR processes

Enhanced Oil Recovery (EOR) is as a key tertiary recovery strategy that aims at enhancing the oil recovery from the earth's subsurface of existing oilfields. One such EOR process that is dependent on multiple variables of complex surface interactions between the formation brine, injected brine, hydrocarbon and rock surface is different composition water flood. This specific EOR technique has been gaining wide focus in research due to its ease of implementation both in terms of logistic and cost albeit the complex interactions that leads to its success is still not clear. Due to the variables of the different phases playing a prominent role in the outcome of this EOR technique, the resulting complexity necessitates the need for Artificial Intelligence (AI) tools to be able to understand, model and screen this EOR technique. There are numerous AI tools based on supervised, unsupervised and reinforcement strategies that can be used in understanding the prominence of different parameters of this surface-interaction based EOR process. In this research work several data analysis methods followed by use of machine learning methods (a subset of AI) are used to analyse the different parameters and their impact on the outcome of the EOR process. Based on these AI tools the prominent parameters are discerned and their correlation with respect to the success of the EOR process is determined. This is followed by evaluation of the AI tools for screening of the EOR process prior to making investment decisions involving commitment to huge capital, resources, and time. This research determines that the key parameters of brine composition, salinity at initial and final conditions, oil API and initial recovery achieved which is a function of the wettability are key for the success of this EOR process. Through this work findings, the industry has a valuable tool to make early decisions that ensure greater probability of success of screening and selecting this EOR technology before commitment of resources for detailed design and implementation.

Availability
146551.136Perpustakaan BIG (Eksternal Harddisk)Available
Detail Information
Series Title
Applied Computing and Geoscience - Open Access
Call Number
551.136
Publisher
Amsterdam : Elsevier.,
Collation
9 hlm PDF, 3.900 KB
Language
Inggris
ISBN/ISSN
2590-1974
Classification
551.136
Content Type
text
Media Type
-
Carrier Type
-
Edition
Vol.17, March 2023
Subject(s)
-
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
  • Use of AI tools to understand and model surface-interaction based EOR processes
    Enhanced Oil Recovery (EOR) is as a key tertiary recovery strategy that aims at enhancing the oil recovery from the earth's subsurface of existing oilfields. One such EOR process that is dependent on multiple variables of complex surface interactions between the formation brine, injected brine, hydrocarbon and rock surface is different composition water flood. This specific EOR technique has been gaining wide focus in research due to its ease of implementation both in terms of logistic and cost albeit the complex interactions that leads to its success is still not clear. Due to the variables of the different phases playing a prominent role in the outcome of this EOR technique, the resulting complexity necessitates the need for Artificial Intelligence (AI) tools to be able to understand, model and screen this EOR technique. There are numerous AI tools based on supervised, unsupervised and reinforcement strategies that can be used in understanding the prominence of different parameters of this surface-interaction based EOR process. In this research work several data analysis methods followed by use of machine learning methods (a subset of AI) are used to analyse the different parameters and their impact on the outcome of the EOR process. Based on these AI tools the prominent parameters are discerned and their correlation with respect to the success of the EOR process is determined. This is followed by evaluation of the AI tools for screening of the EOR process prior to making investment decisions involving commitment to huge capital, resources, and time. This research determines that the key parameters of brine composition, salinity at initial and final conditions, oil API and initial recovery achieved which is a function of the wettability are key for the success of this EOR process. Through this work findings, the industry has a valuable tool to make early decisions that ensure greater probability of success of screening and selecting this EOR technology before commitment of resources for detailed design and implementation.
Comments
You must be logged in to post a comment