A New Workflow for Estimating Reservoir Properties With Gradient Boosting Modeland Joint Inversion Using MWD Measurements

Triple-combo logs are important measurements for estimating geological, petrophysical, and geomechanical properties. Unfortunately, wireline and advanced LWD logs are typically dropped from the formation evaluation plan for unconventional wells due to economic constraints or borehole instability risks. Available measurements are typically measurement-while-drilling (MWD) natural gamma ray (GR) logs, along with surface measurements such as weight on bit (WOB), rate of penetration (ROP), torque, revolutions per minute (RPM), and differential pressure. The development of a robust and rapid model for predicting reservoir properties using this limited data set would be of high value for geological evaluation. Estimating such properties is a challenging task due to the nonlinear relationship between the available log data and unknown reservoir properties. A novel workflow is presented that combines two sequential models. First is a machine-learning algorithm to predict triple-combo logs from drilling dynamic measurements and GR logs. To train the machine-learning algorithm, well logs obtained from multiple wells located in the Eagle Ford and Permian Basins are scrutinized to identify important features. This process includes depth shifting, outlier detection, and feature selection, which allows for strategic hyperparameter tuning. Several regression algorithms are investigated, and it is found that gradient boosting algorithms yield superior prediction performance. Unlike commonly used regressors such as random forest methods, boosting algorithms train predictors sequentially, each trying to correct its predecessor. After triple-combo logs are predicted from measurement-while-drilling (MWD) logs, a physics-based joint inversion model is applied to estimate reservoir properties such as total porosity, clay volume, water saturation, volumetric concentrations of lithology, permeability, rock type, and geomechanical parameters. The trained model is deployed on a blind test well, and the predicted logs show excellent agreement when compared to the corresponding triple-combo measurements. The multimineral inversion using predicted triple-combo logs yields a geologic model that is validated with both mud logs and ECS measurements. Therefore, real-time estimated geological, petrophysical, and geomechanical properties can reveal complex geologic information to mitigate uncertainty related to drilling optimization, reservoir characterization, development plan, and reserve estimate. Using the MWD logs to predict triple-combo logs followed by a joint inversion is an innovative approach for a geological evaluation with a limited data set. The developed workflow can successfully provide (1) geologic lithofacies identification and rock typing, (2) more confidence in real-time drilling operation, (3) reservoir properties prediction, (4) missing log imputations and pseudo-log generation with forward modeling, (5) guidance for future logging and perforation (6) reference for seismic QI and well tie, and (7) computation time saving from days to minutes.