AI-ENABLED TAILORING OF SURFACTANT–POLYMER INJECTION SCHEMES THROUGH RESERVOIR-DEPENDENT INTERFACIAL BEHAVIOR AND ADSORPTION MODELING

Read full text Summarise with VIRAT
Authors: Nnaji Chinedu G
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Enhanced oil recovery (EOR) remains critical for maximizing hydrocarbon extraction from mature reservoirs,with surfactant–polymer (SP) flooding emerging as a promising technique due to its ability to reduce interfacialtension and improve sweep efficiency. However, the effectiveness of SP injection is highly dependent on complexreservoir-specific factors, including mineralogy, salinity, temperature, and wettability, which influence interfacialbehavior and chemical adsorption. Traditional design approaches often rely on empirical correlations andlaboratory-scale experiments, limiting their scalability and adaptability to heterogeneous reservoir conditions. Inthis context, artificial intelligence (AI) offers a transformative pathway for optimizing SP injection strategies byintegrating data-driven modeling with physicochemical insights. This study presents an AI-enabled frameworkthat tailors surfactant–polymer formulations and injection schemes based on reservoir-dependent interfacialdynamics and adsorption characteristics. Machine learning models are employed to predict interfacial tensionreduction and adsorption losses under varying reservoir conditions, enabling dynamic adjustment of injectionparameters such as concentration, slug size, and sequencing. The framework incorporates multi-source data,including core flooding experiments and field-scale observations, to enhance predictive accuracy andgeneralizability. Results demonstrate improved oil recovery efficiency, reduced chemical consumption, andenhanced economic viability. This approach underscores the potential of AI-driven optimization in advancingintelligent, reservoir-specific EOR strategies

Fields of Study & Subjects

Enhanced Oil Recovery Techniques Reservoir Engineering and Simulation Methods Surfactants and Colloidal Systems

Publication details

Journal / source
International Journal of Engineering Technology Research & Management
Publication date
22 March 2026
Language
EN