Predicting total porosity and free fluid index is critical for the petroleum industry as it can aid in identifying the presence of hydrocarbons, determining the productivity of a reservoir, and evaluating the potential of a prospect. Machine learning techniques, such as the hybrid ensemble model developed in this study, can aid in achieving accurate predictions of total porosity and free fluid index by providing a robust fit for this problem. This study introduces a novel stacked ensemble algorithm, combining the strengths of two machine learning models to enhance the precision of estimating the total porosity and the free fluid index. The proposed hybrid ensemble model efficiently deals with the limitations of individual models by leveraging their diverse yet complementary characteristics, leading to more robust and reliable predictions. With the cost of running NMR logs not favourable and hence not always run, a custom hybrid ensemble model was used to establish a correlation between NMR-derived total porosity and free fluid volume and wireline logs. The hybrid ensemble developed used three ensemble models as base learners. The efficacy of three ensemble and deep learning models was evaluated in comparison to the hybrid ensemble. The hybrid ensemble considerably surpassed all other models based on the RMSE, R2, and MAE. This outcome implies that the hybrid ensemble can potentially estimate total porosity and the free fluid volume in the field using wireline logs. This can help improve hydrocarbon exploration and production efficiency, ultimately leading to increased productivity and reduced costs. © 2024 Daniel Asante Otchere.