A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs

Accurately measuring wettability is of the utmost importance because it influences several reservoir parameters while also impacting potential, recovery, development, and management plan. As such, this study proposes a new formulated mathematical model based on correlation between Amott-USBM measurement field NMR T2LM log. The exponential relationship existence immiscible fluids in pore space had coefficient 0.95. Earlier studies laboratory core measurements using T2 distribution as function increasing water saturation were modified to include data. Based trends observed, water-wet oil-wet conditions qualitatively identified. Using mean for intervals interest formula, various wetting quantitatively measured. Results agreed with used develop equation. results expressed validity equation characterise at scale. With cost running logs not favourable, hence always run, deep ensemble super learner was employed establish wireline logs. This architecture learning theoretical background models due their reported superiority. developed nine base learners. performance compared learner. RMSE, R2, MAE, MAPD MPD greatly outperformed indicates that can be predict field. By applying methodology formula proposed study, reservoirs accurately characterised illustrated deployment.