|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Abstract In the last few years there is an increasing interest in the industry to apply Machine Learning (ML) algorithms to improve business decisions and operational efficiencies. The driver behind are the 3V's (velocity, variety and volume) of data acquisition and synthesis. The enormity of making sense out of this data pile is either too cumbersome for direct human interpretability or insurmountably time consuming (and often impractical) for physics-based models. The Machine Learning techniques systematically unravel the underlying trends and interrelationships between the driver and response variables. However, the application of these data science techniques are still relatively new in the petroleum industry and needs careful selection and adaptability to improve their forecasting success. This paper contributes in applying some of these techniques, especially deep and shallow learning algorithms, in a systematic manner, traversing step-by-step methodology of data preparation, exploratory data analysis, model selection, model validation, model parameter tuning, selection of variable of importance and model application. In particular, data sets are prepared for both Supervised Regression (continuous) and Classification (categorical) methods. Post exploratory data analysis, multivariate regression along with Multicollinearity/Variation Inflation Factor and outlier tests are applied to reduce the predictor variable list. Thereafter, classification models e.g. Gradient Boosting, Support Vector Machine, k-Nearest neighbors, Decision Trees, Random Forest etc. are progressively disciplined on training data sets to be tested on the hold-out data sets. Accuracy of predictability is compared against standard goodness-of-fit metrics. Finally, stratified k-fold cross validation methodology is applied to tune model parameters and list variables of importance. First the Shallow and Deep Learning process flow is applied to a large Delaware basin data set comprising of 5716 horizontal wells scattered in the various members of Wolfcamp formations. The original database contains a total of 131 predictor variables containing 26 reservoir, 21 completion, 22 well architecture. 53 production and 9 reservoir fluid related. The dataset is mined for individual Wolfcamp members. Results are provided to demonstrate model's predictive accuracy, applicability to a new dataset and potential pitfalls in forecasting if certain statistical metrics are ignored. The important variables of interest (in the statistically reduced dataset) which are assigned more weights in the predictive process are also enlisted. Next, as a second case study, a different Deep Learning methods (Long Short Term Memory, LSTM) is applied to history match and forecast an Eagle Ford well decline curve, to demonstrate the viability of this method in forecasting production. The paper contributes towards better understanding of some of the ubiquitous black-box ML algorithms, define an appropriate process flow to analyze large datasets and help petroleum engineers and geoscientists to apply them more rigorously and robustly in their own applications.
Drilling problems such as stick slip vibration/hole cleaning, pipe failures, loss of circulation, BHA whirl, stuck pipe incidents, excessive torque and drag, low ROP, bit wear, formation damage and borehole instability, and the drilling of highly tortuous wells have only been tackled using physics-based models. Despite the mammoth generation of real-time metadata, there is a tremendous gap between statistical based models and empirical, mathematical, and physical-based models. Data mining techniques have made prominent contributions across a broad spectrum of industries. Its value is widely appreciated in a variety of applications, but its potential has not been fully tapped in the oil and gas industry. This paper presents a review compiling several years of Data Analytics applications in the drilling operations. This review discusses the benefits, deficiencies of the present practices, challenges, and novel applications under development to overcome industry deficiencies. This study encompasses a comprehensive compilation of data mining algorithms and industry applications from a predictive analytics standpoint using supervised and unsupervised advanced analytics algorithms to identify hidden patterns and help mitigate drilling challenges.
Traditional data preparation and analysis methods are not sufficiently capable of rapid information extraction and clear visualization of big complicated data sets. Due to the petroleum industry's unfulfilled demand, Machine Learning (ML)-assisted industry workflow in the fields of drilling optimization and real time parameter analysis and mitigation is presented.
This paper summarizes data analytics case studies, workflows, and lessons learnt that would allow field personnel, engineers, and management to quickly interpret trends, detect failure patterns in operations, diagnose problems, and execute remedial actions to monitor and safeguard operations. The presence of such a comprehensive workflow can minimize tool failure, save millions in replacement costs and maintenance, NPV, lost production, minimize industry bias, and drive intelligent business decisions. This study will identify areas of improvement and opportunities to mitigate malpractices. Data exploitation via the proposed platform is based on well-established ML and data mining algorithms in computer sciences and statistical literature. This approach enables safe operations and handling of extremely large data bases, hence, facilitating tough decision-making processes.
Balaji, Karthik (University of North Dakota) | Rabiei, Minou (University of North Dakota) | Suicmez, Vural (QRI Analytics) | Canbaz, Celal Hakan (Schlumberger) | Agharzeyva, Zinyat (Texas A & M University) | Tek, Suleyman (University of the Incarnate Word) | Bulut, Ummugul (Texas A&M University-San Antonio) | Temizel, Cenk (Aera Energy LLC)
Abstract Data-driven methods serve as robust tools to turn data into knowledge. Historical data generally has not been used in an effective way in analyzing processes due to lack of a well-organized data, where there is a huge potential of turning terabytes of data into knowledge. With the advances and implementation of data-driven methods data-driven models have become more widely-used in analysis, predictive modeling, control and optimization of several processes. Yet, the industry overall is still skeptical on the use of data-driven methods, since they are data-based solutions rather than traditional physics-based approaches; even though physics and geology are often part of this methodology. This study comprehensively evaluates the status of data-driven methods in oil and gas industry along with the recent advances and applications. This study outlines the development of these methods from the fundamentals, theory and applications perspective along with their historical acceptance and use in the industry. Major challenges in the process of implementation of these methods are reviewed for different areas of applications. The major advantages and drawbacks of data-driven methods over the traditional methods are discussed. Limitations and areas of opportunities are outlined. Recent advancements along with the latest applications, the associated results and value of the methods are provided. It is observed that the successful use of data-driven methods requires strong understanding of petroleum engineering processes and the physics-based conventional methods together with a good grasp of traditional statistics, data mining, artificial intelligence and machine learning. Data-driven methods start with a data-based approach to identify the issues and their solutions. Even though data-driven methods provide great solutions on some challenging and complex processes, that are new and/or hard to define with existing conventional methods, there is still skepticism in the industry on the use of these methods. This is strongly tied to the delicacy and sensitive nature of the processes and on the usage of the data. Organization and refinement of the data turn out to be important components of an efficient data-driven process. Data-driven methods offer great advantages in the industry over that of conventional methods under certain conditions. However, the image of these methods for most of the industry professionals is still fuzzy. This study serves to bridge the gap between successful implementation and more widely use and acceptance of data-driven methods, and the fuzziness and reservations on the understanding of these methods in the industry. Significant components of these methods along with clarification of definitions, theory, application and concerns are also outlined in this study.
Abstract Petrophysics is a pivotal discipline that bridges engineering and geosciences for reservoir characterization and development. New sensor technologies have enabled real-time streaming of large-volume, multi-scale, and high-dimensional petrophysical data into our databases. Petrophysical data types are extremely diverse, and include numeric curves, arrays, waveforms, images, maps, 3-D volumes, and texts. All data can be indexed with depth (continuous or discrete) or time. Petrophysical data exhibits all the "7V" characteristics of big data, i.e., volume, velocity, variety, variability, veracity, visualization, and value. This paper will give an overview of both theories and applications of machine learning methods as applicable to petrophysical big data analysis. Recent publications indicate that petrophysical data-driven analytics (PDDA) has been emerging as an active sub-discipline of petrophysics. Field examples from the petrophysics literature will be used to illustrate the advantages of machine learning in the following technical areas: (1) Geological facies classification or petrophysical rock typing; (2) Seismic rock properties or rock physics modeling; (3) Petrophysical/geochemical/geomechanical properties prediction; (3) Fast physical modeling of logging tools; (4) Well and reservoir surveillance; (6) Automated data quality control; (7) Pseudo data generation; and (8) Logging or coring operation guidance. The paper will also review the major challenges that need to be overcome before the potentially game-changing value of machine learning for petrophysics discipline can be realized. First, a robust theoretical foundation to support the application of machine leaning to petrophysical interpretation should be established; second, the utility of existing machine learning algorithms must be evaluated and tested in different petrophysical tasks with different data scenarios; third, procedures to control the quality of data used in machine leaning algorithms need to be implemented and the associated uncertainties need to be appropriately addressed. The paper will outlook the future opportunities of enabling advanced data analytics to solve challenging oilfield problems in the era of the 4 industrial revolution (IR4.0).
Gupta, Ishank (University of Oklahoma) | Devegowda, Deepak (University of Oklahoma) | Jayaram, Vikram (Pioneer Natural Resources) | Rai, Chandra (University of Oklahoma) | Sondergeld, Carl (University of Oklahoma)
Abstract Planning and optimizing completion design for hydraulic fracturing require a quantifiable understanding of the spatial distribution of the brittleness of the rock and other geomechanical properties. Eventually, the goal is to maximize the SRV (Stimulated Reservoir Volume) with minimal cost overhead. The compressional and shear velocities (Vp and Vs respectively) can be used to calculate Young’s modulus, Poisson’s ratio and other mechanical properties. In the field, sonic logs are not commonly acquired and operators often resort to regression to predict synthetic sonic logs. We have compared several machine learning regression techniques for their predictive ability to generate synthetic sonic (Vp and Vs) and a brittleness indicator, namely hardness, using the laboratory core data. We used techniques like multi-linear regression, lasso regression, support vector regression, random forest, gradient boosting and alternating conditional expectation. We found that the commonly used multi-linear regression is sub-optimal with less-than-satisfactory predictive accuracies. Other techniques particularly random forest and gradient boosting have greater predictive capabilities based on several error metrics such as R2 (Correlation Coefficient) and RMSE (Root Mean Square Error). We also used Gaussian process simulation for uncertainty quantification as it provides uncertainty estimates on the predicted values for a wide range of inputs. Random Forest and Extreme Gradient Boosting techniques also gave low uncertainties in prediction.