Enhanced petrophysical evaluation through machine learning and well logging data in an Iranian oil field

Reservoir petrophysical assessments are essential for determining hydrocarbon reserves, production, and characterizing reservoir layers. Advanced logging technology identifies crucial petrophysical parameters, including porosity type, rock pore size and type, and static/dynamic properties. The aim of this study is to present a petrophysical evaluation of the studied reservoir and to identify the reservoir layers by calculating and determining petrophysical indicators using well logging data. Additionally, various machine learning methods, including Adaptive Neuro-Fuzzy Inference System, Extreme Learning Machine, Multi Gene Genetic Programming, Decision Tree, and Adaptive Boosting, were compared to model the water saturation data according to different logs. The investigated depth ranged from 4050.6 to 4560 m, with each image containing over 3000 data at the desired depth. The main lithology of the formation was limestone with some shale. By conducting a petrophysical evaluation and applying parameter cutoffs, productive zones within the reservoir were identified. Layer 3 had the highest average net porosity (18%) and net water saturation (17%), with secondary porosity observed in most layers. Among the machine learning models tested the AdaBoost model demonstrated the lowest error value for estimating water saturation, with an RMSE of 0.0152 and an AARE% of 3.1610, establishing it as the most effective model in this study. Furthermore, the GP model provided a correlation between the input parameters and predicted water saturation, demonstrating good accuracy with an RMSE of 0.0231 and an AARE of 4.3597.