Evaluating Machine Learning Techniques for Carbonate Formation Permeability Prediction Using Well Log Data

Machine learning has a significant advantage for many difficulties in the oil and gas industry, especially when it comes to resolving complex challenges reservoir characterization. Permeability is one of most difficult petrophysical parameters predict using conventional logging techniques. Clarifications work flow methodology are presented alongside comprehensive models this study. The purpose study provide more robust technique predicting permeability; previous studies on Bazirgan field have attempted do so, but their estimates been vague, methods they give obsolete not make any concessions real or rigid order solve permeability computation. To verify reliability training data zone-by-zone modeling, we split scenario into two scenarios applied them seven wells' worth data. Moreover, all wellbore intervals were processed, instance, five units Mishrif formation. According findings, information have, accurate our forecasting model becomes. Multi-resolution graph-based clustering demonstrated its stability instances by comparing other machine models.