During the design phase of oil and gas well drilling plans, predicting geomechanical parameters is an indispensable job. Accurate estimation of the Poisson's ratio and the maximum horizontal stress is essential where inaccurate estimation may result in wellbore instability and casing collapse increasing the drilling cost. Obtaining mechanical rock properties using mechanical tests on cores is expensive and time-consuming. Machine learning algorithms may be utilized to get a reliable estimate for Poisson's ratio and the maximum horizontal stress. This research aims to estimate the static Poisson's ratio and the maximum horizontal stress based on influencing factors from well-log input data through an Extreme gradient boosting algorithm (XGBoost). In addition, the XGBoost model was also compared with Random Forest. A real data set comprised of 22,325 data points was collected from the literature representing influencing variables which are compressional wave velocity, share wave velocity, bulk density, and pore pressure. The data set was split into 70% for training, and 30% for testing the model. XGBoost and random forest were used for training and testing the model. Mean absolute percentage error (MAPE), root mean squared error (RMSE), and coefficient of determination (R2) were assessed in the error metrics to obtain the optimum model. XGBoost and random forest were implemented using the k-fold cross-validation method integrated with grid search. The proposed XGBoost model shows an effective correlation between the geomechanical parameters (static Poisson's ratio and the maximum horizontal stress) with the input variables. The performance of the XGBoost model was found better than that of the random forest. The evaluation estimates more than 90% of R2 and approximately 4% of MAPE for the training and testing data. The key contribution of this work is the proposal of an intelligent model that estimates the geomechanical parameters without the need for destructive mechanical core testing. A reliable XGBoost model to predict the static Poisson's ratio and the maximum horizontal stress will allow improved wellbore stability analysis which significantly introduces efficiency gains.

During the past decades, several research studies have been made to unfold the immense and diversified benefits of the innovative applications of machine learning (ML) techniques in the petroleum industry. For instance, machine learning algorithms were applied to estimate the various physical properties of natural gas. Natural gas density is considered an indispensable metric that influences the determination of several variables necessary for analyzing natural gas systems. In this work, the Artificial neural network (ANN), a machine learning technique, was applied to estimate natural gas density incorporating the influencing factors. The ANN model was also compared with another ML technique, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS). A mathematical form has been also presented using ANN. A real data set was taken from the literature, comprised of about 4500 data points assimilating three influencing input variables, including pseudo-reduced pressure (PPr), pseudo-reduced temperature (TPr), and molecular weight (Mw). The PPr and TPr are obtained by calculating the averages of the sample gas critical pressures and critical temperatures. A complicated nonlinear relationship exists between the three influencing variables and the gas density. The data set was divided into a 70:30 ratio for training and testing the model, respectively. Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN) were applied to train and test the model. Absolute average percentage error (AAPE), coefficient of determination (R2), and root mean squared error (RMSE) were considered in the error metrics to acquire the best possible model. Levenberg–Marquardt backpropagation algorithm was employed for ANN, while subtractive clustering was used for ANFIS. Results showed that natural gas density can be well correlated with numerous inputs using machine learning tools (ANN and ANFIS). The input parameters include Ppr, Tpr, and Mw, as mentioned above. ANN performed better than ANFIS. The network was adjusted against the training sub-set to set-up weights and biases covering each node. R2 for both testing and training data was more than 99%, while AAPE was around 4% for both cases. Moreover, a detailed mathematical scheme for the ANN model is also provided in this paper.