<p>Given the escalating concerns surrounding climate change and global warming, reducing anthropogenic carbon dioxide emissions has become more urgent than ever. CO₂ enhanced oil recovery emerges as a promising scenario for growing carbon capture, utilization, and storage efforts. However, the success of CO₂ injection is highly dependent on the distinctive characteristics of reservoirs. Within this context, the minimum miscibility pressure is a pivotal parameter for effectively screening and evaluating the viability of CO₂ flooding projects. Previous studies have proposed a range of models to estimate the minimum miscibility pressure. However, these models need to be revised to meet the desired levels of accuracy. Similarly, machine learning methods have been explored, given the advancements achieved in previous research. However, the inherent black-box nature of these approaches may limit their practical applicability. The current study introduces an innovative grey-box machine learning modeling method to bridge this gap. Through this approach, precise and user-friendly equations are developed to facilitate accurate minimum miscibility pressure estimation. The investigation reveals that grey-box methods yield remarkable levels of accuracy and are highly suitable for precise minimum miscibility pressure estimation. The findings of this study highlight the potential of grey-box machine learning modeling as a valuable tool in the field of CO₂ flooding and contribute to the ongoing endeavors in carbon capture, utilization, and storage.</p>