Summary There is a great deal of interest in the oil and gas industry (OGI) in seeking ways to implement machine learning (ML) to provide valuable insights for increased profitability. With buzzwords such as data analytics, ML, artificial intelligence (AI), and so forth, the curiosity of typical drilling practitioners and researchers is piqued. While a few review papers summarize the application of ML in the OGI, such as Noshi and Schubert (2018), they only provide simple summaries of ML applications without detailed and practical steps that benefit OGI practitioners interested in incorporating ML into their workflow. This paper addresses this gap by systematically reviewing a variety of recent publications to identify the problems posed by oil and gas practitioners and researchers in drilling operations. Analyses are also performed to determine which algorithms are most widely used and in which area of oilwell-drilling operations these algorithms are being used. Deep dives are performed into representative case studies that use ML techniques to address the challenges of oilwell drilling. This study summarizes what ML techniques are used to resolve the challenges faced, and what input parameters are needed for these ML algorithms. The optimal size of the data set necessary is included, and in some cases where to obtain the data set for efficient implementation is also included. Thus, we break down the ML workflow into the three phases commonly used in the input/process/output model. Simplifying the ML applications into this model is expected to help define the appropriate tools to be used for different problems. In this work, data on the required input, appropriate ML method, and the desired output are extracted from representative case studies in the literature of the last decade. The results show that artificial neural networks (ANNs), support vector machines (SVMs), and regression are the most used ML algorithms in drilling, accounting for 18, 17, and 13%, respectively, of all the cases analyzed in this paper. Of the representative case studies, 60% implemented these and other ML techniques to predict the rate of penetration (ROP), differential pipe sticking (DPS), drillstring vibration, or other drilling events. Prediction of rheological properties of drilling fluids and estimation of the formation properties was performed in 22% of the publications reviewed. Some other aspects of drilling in which ML was applied were well planning (5%), pressure management (3%), and well placement (3%). From the results, the top ML algorithms used in the drilling industry are versatile algorithms that are easily applicable in almost any situation. The presentation of the ML workflow in different aspects of drilling is expected to help both drilling practitioners and researchers. Several step-by-step guidelines available in the publications reviewed here will guide the implementation of these algorithms in the resolution of drilling challenges.

No abstract

Summary This paper investigates the computational behaviors of simple-to-use, relatively fast, and versatile machine learning (ML) methods to predict apparent viscosity, a key rheological property of nanoparticle-surfactant-stabilized CO2 foam in unconventional reservoir fracturing. The first novelty of our study is the investigation of the predictive performance of ML approaches as viable alternatives for predicting the apparent viscosity of NP-Surf-CO2 foams. The predictive and computational performance of five nonlinear ML algorithms were first compared. Support vector regression (SVR), K-nearest neighbors (KNN), classification and regression trees (CART), feed-forward multilayer perceptron neural network (MLPNN), and multivariate polynomial regression (MPR) algorithms were used to create models. Temperature, foam quality, pressure, salinity, shear rate, nanoparticle size, nanoparticle concentration, and surfactant concentration were identified as relevant input parameters using principal component analysis (PCA). A data set containing 329 experimental data records was used in the study. In building the models, 80% of the data set was used for training and 20% of the data set for testing. Another unique aspect of this research is the examination of diverse ensemble learning techniques for improving computational performance. We developed meta-models of the generated models by implementing various ensemble learning algorithms (bagging, boosting, and stacking). This was done to explore and compare the computational and predictive performance enhancements of the base models (if any). To determine the relative significance of the input parameters on prediction accuracy, we used permutation feature importance (PFI). We also investigated how the SVR model made its predictions by utilizing the SHapely Additive exPlanations (SHAP) technique to quantify the influence of each input parameter on prediction. This work’s application of the SHAP approach in the interpretation of ML findings in predicting apparent viscosity is also novel. On the test data, the SVR model in this work had the best predictive performance of the single models, with an R2 of 0.979, root mean squared error (RMSE) of 0.885 cp, and mean absolute error (MAE) of 0.320 cp. Blending, a variant of the stacking ensemble technique, significantly improved this performance. With an R2 of 1.0, RMSE of 0.094 cp, and MAE of 0.087 cp, an SVR-based meta-model ensembled with blending outperformed all single and ensemble models in predicting apparent viscosity. However, in terms of computational time, the blended SVR-based meta-model did not outperform any of its constituent models. PCA and PFI ranked temperature as the most important factor in predicting the apparent viscosity of NP-Surf-CO2 foams. The ML approach used in this study provides a comprehensive understanding of the nonlinear relationship between the investigated factors and apparent viscosity. The workflow can be used to evaluate the apparent viscosity of NP-Surf-CO2 foam fracturing fluid efficiently and effectively.