Development and comparison of reduced-order models for CO2-enhanced oil recovery predictions

CO2-enhanced oil recovery (CO2-EOR) has been a mature and promising technology since the 1970s, offering a dual solution for energy production and carbon sequestration. Recent advances in reduced-order models (ROMs) using empirical analysis and artificial intelligence (AI) tools handle complex data efficiently. However, existing ROMs for CO2-EOR often lack validation due to data confidentiality or are too case-specific for broader application. This paper introduces a framework to close these gaps, enabling the development and consistent comparison of generalized ROMs for CO2-EOR with carbon capture and storage (CCS), even with traditional tools. A synthesis dataset (∼3000 runs) was established to develop ROMs, which were validated using field data from both EOR and CCS perspectives. Three key findings are revealed. First, normalizing outputs with respect to CO2 utilization illustrated a direct relationship between CCS and EOR. Second, generalized statistics-based ROMs reduced input complexity and validated field data but predicted fewer outputs. Machine learning-based ROMs predicted more outputs, supporting field operational decision-makings. Last, ROMs were particularly suitable for early-stage, large-scale CO2-EOR assessments. This study extended the boundaries of developing generalized ROMs for CO2-EOR and identified pros and cons across modeling approaches, contributing to net-zero goals and advancing sustainable and affordable energy future.