It is necessary to establish effective communication between two horizontal wells during the preheating period of steam-assisted gravity-drainage (SAGD). However, the preheating time is usually very long, which results in high steam consumption and CO₂ emissions. There is little research on the effects of different wellbore fluids during the preheating period. The heat transfer and heating characteristics of different wellbore fluids–water, heat-conduction oil, and air–were explored by using physical experiments and numerical simulations. In this study, the results indicated that the heat-transfer performance of heat-conduction oil is the best. The numerical simulation’s results indicated that compared with the wellbore saturated with water, the heat-conduction oil reduced the viscosity of crude oil, and energy consumption was not obvious during the preheating stage. The super-heavy oil flowed into the wellbore due to the solubility of the heat-conduction oil and its own gravity. As a result, the super-heavy oil content in the wellbore gradually accumulated, increasing the risk of coking. Those experiments showed that the use of electrical heating provides good potential to improve SAGD efficiency during the preheating period, and water is the best injection fluid for wellbores during the electrical heating process.

Although heavy oil remains a crucial energy source, its high viscosity makes its utilization challenging. We have performed an interpretable analysis of the relationship between the molecular structure of digital oil and its viscosity using molecular dynamics simulations combined with machine learning. In this study, we developed three “digital oils” to represent light, medium, and heavy oils in consideration of their composition and molecular structure. Using molecular dynamics (MD) simulations, we calculated the density, self-diffusion coefficient, and viscosity of these digital oils at various temperatures (323–453 K). The accuracy of the simulation results was demonstrated by their good fit to the experimental data. We further explored the correlation between interaction energy and viscosity. As interaction energy increased, molecular attraction strengthened, resulting in greater friction between molecules and a higher viscosity of the digital oil. Cluster analysis revealed that, compared with the other two oils, the heavy oil contained rod-shaped molecular aggregates in greater quantity and larger clusters. Additionally, we computed the radial distribution functions of the SARA (saturates, aromatics, resins, and asphaltenes) components; among molecular pairs, aromatics and resins showed the largest interaction energy and were the most tightly bound, contributing to increased viscosity. To more effectively predict the viscosity of digital oils, we integrated four machine learning (ML) techniques: linear regression, random forest, extra trees, and gradient boosting. Post-hoc analysis coupled with SHapley Additive exPlanations (SHAP) was applied to interpret how macroscopic and microscopic features influence the viscosity and to identify the contributions of individual molecules. This work presents a novel and efficient method for estimating the viscosity of digital oils by combining MD simulations with ML approaches, offering a valuable tool for quick and cost-effective analysis.