Immense potential of shale gas to supplement domestic energy needs and the recent engineering strides in multi-staged fractures in long horizontal well laterals have inevitably increased interest in exploitation of such plays across the country. However, because of the continuous nature of these plays, the production potential can change significantly from one location to the other often within close proximity. For a project to be economically viable, under downward price pressures, large number of wells in multi-well drilling campaigns needs to produce commercial quantities of gas. Not surprisingly, numerous attempts are being made to type-cast mineralogy, organic contents, fracture design and completion optimization in order to reduce exploration and exploitation risks. Many uncertainties still remain, however. The proposed model (SGPM) is developed to mitigate some of these challenges. It is simple and easy-to use and unlike grid-based fine-grid models it focuses more on the flow around individual wells while conserving overall mass. First, the current status of modeling from fine grid dual-porosity/dual permeability simulations to analytical models for horizontal wells with multiple vertical fractures is explained. The assumptions, formulation and the need for SGPM are described next. The model is validated with vertical and horizontal well productions from various shale gas plays. Results of extensions to the model to account for multi-phase flow are displayed thereafter. This paper contributes in the following manner: Provides an alternate framework to history match and forecast shale gas production. This model is better suited for reservoir engineers’ routine reserves estimation work because of its quicker turnaround time. Provides a relatively simpler framework to incorporate specialized asset specific physics and geomechanics. Multi-phase flow feature enables accurate condensate production in plays like Marcellus and Eagle Ford.

No abstract

No abstract

No 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.