Explicit and explainable artificial intelligent model for prediction of CO2 molecular diffusion coefficient in heavy crude oils and bitumen

• A Bayesian regularized neural network model for predicting CO 2 diffusivity in heavy crude oil and bitumen systems. • Developed model is explicitly expressed unlike most existing Machine Learning models. • The model has been physically validated using trend analysis. • The developed model outperformed existing AI models based on various statistical metrics. • Inference latency of the developed model has been established. Optimizing CO 2 injection for enhanced oil recovery (EOR) requires a precise estimation of the CO 2 -diffusivity coefficient in porous media. This study developed a predictive model for the molecular diffusivity coefficient of CO 2 in bitumen and heavy crude oils using a Bayesian regularized artificial neural network. The unique contributions of the developed model compared to existing models include: First, a simple and accurate mathematical correlation between inputs and CO 2 -diffusivity has been presented, making it easy to use particularly for individuals with limited understanding of machine learning. Secondly, the time it takes the model to make a prediction (its inference latency) has been established and the model has been physically validated using trend analysis. Fourthly, independent datasets were used to test for the model generalizability. The model was evaluated using 260 data points from the literature, with 70% for training and 30% for testing. Key performance metrics were calculated, including root mean square error (RMSE = 0.03), and coefficient of determination (R 2 = 0.996). Furthermore, an outlier detection analysis using the statistical leverage approach demonstrated that the data used was of high quality. A relevancy factor analysis revealed that pressure had the greatest impact on CO 2 diffusivity, followed by temperature, while CO 2 mass fraction had the least impact. The developed model operates within a temperature range of 295K – 363K and a pressure range of 1MPa – 8MPa. Overall, the outcomes of this study contribute to the efficient prediction of CO 2 diffusivity in heavy crude oil and bitumen.