Application of Artificial Intelligence in Predicting Reservoir Properties for Enhanced Oil Recovery in Petroleum Engineering

Thesis Abstract

Abstract
This thesis explores the application of artificial intelligence (AI) in predicting reservoir properties to enhance oil recovery in the field of petroleum engineering. The use of AI technologies, such as machine learning algorithms and neural networks, has gained significant attention in the oil and gas industry due to their potential to optimize reservoir management and improve production efficiency. The study focuses on leveraging AI techniques to analyze complex reservoir data and predict key properties that influence oil recovery processes. The introduction provides a comprehensive overview of the research background, highlighting the importance of reservoir properties in oil recovery and the growing interest in AI applications within the petroleum industry. The background of the study delves into existing literature on reservoir characterization, AI technologies, and their integration in petroleum engineering practices. The problem statement identifies the challenges faced in traditional reservoir modeling methods and the need for advanced predictive tools to optimize oil recovery strategies. The objectives of the study are outlined to investigate the effectiveness of AI in predicting reservoir properties, enhance reservoir characterization accuracy, and improve decision-making processes for enhanced oil recovery projects. The limitations of the study are also discussed, acknowledging potential constraints such as data availability, computational resources, and model accuracy. The scope of the study defines the boundaries and extent of research activities, focusing on specific reservoir properties and AI techniques relevant to oil recovery applications. The significance of the study lies in its potential to advance reservoir engineering practices by integrating AI technologies for more accurate and efficient prediction of reservoir properties. The structure of the thesis outlines the organization of chapters and key sections, providing a roadmap for readers to navigate through the research findings. Definitions of terms are provided to clarify technical terminology and concepts used throughout the thesis. The literature review chapter critically examines existing studies on AI applications in reservoir engineering, highlighting key advancements, challenges, and opportunities for integrating AI in predicting reservoir properties. Ten key themes are explored, including machine learning algorithms, reservoir characterization techniques, and case studies of AI implementation in oil recovery projects. The research methodology chapter details the approach, data sources, and analytical tools used to develop AI models for predicting reservoir properties. Eight key components are discussed, covering data collection methods, model training procedures, validation techniques, and performance evaluation metrics. The chapter emphasizes the rigorous methodology employed to ensure the reliability and accuracy of the predictive models. The discussion of findings chapter presents the results of applying AI techniques to predict reservoir properties and evaluates the performance of the developed models. Detailed analyses of prediction accuracy, model robustness, and practical implications for oil recovery strategies are provided. The chapter synthesizes the research findings to draw meaningful conclusions and insights for the petroleum engineering field. In conclusion, this thesis highlights the potential of AI in revolutionizing reservoir engineering practices for enhanced oil recovery. The research demonstrates the efficacy of AI models in predicting reservoir properties and offers valuable insights for optimizing oil production processes. The summary encapsulates the key findings, implications, and recommendations for future research and industry applications in leveraging AI for enhanced oil recovery in petroleum engineering.