Insights to fracture stimulation design in unconventional reservoirs based on machine learning modeling

Data-driven modeling provides an attractive alternative to predict SAGD recovery.The modeling approach is applied successfully for heterogeneous reservoirs.Arps parameters are proposed to parameterize production time-series data.A normalized shale indicator is used as a pertinent input attribute.Accuracy of the prediction is greatly enhanced when cluster analyses are performed. Evaluation of steam-assisted gravity drainage (SAGD) performance that involves detailed compositional simulations is usually deterministic, cumbersome, expensive (manpower and time consuming), and not quite suitable for practical decision making and forecasting, particularly when dealing with high-dimensional data space consisting of large number of operational and geological parameters. Data-driven modeling techniques, which entail comprehensive data analysis and implementation of machine learning methods for system forecast, provide an attractive alternative.In this paper, artificial neural network (ANN) is employed to predict SAGD production in heterogeneous reservoirs, an important application that is lacking in existing literature. Numerical flow simulations are performed to construct a training data set consists of various attributes describing characteristics associated with reservoir heterogeneities and other relevant operating parameters. Empirical Arps decline parameters are tested successfully for parameterization of cumulative production profile and considered as outputs of the ANN models. Sensitivity studies on network configurations are also investigated. Principal components analysis (PCA) is performed to reduce the dimensionality of the input vector, improve prediction quality, and limit over-fitting. In a case study, reservoirs with distinct heterogeneity distributions are fed to the model. It is shown that robustness and accuracy of the prediction capability are greatly enhanced when cluster analysis are performed to identify internal data structures and groupings prior to ANN modeling. Both deterministic and fuzzy-based clustering techniques are compared, and separate ANN model is constructed for each cluster. The model is then tested using a validation data set (cases that have not been used during the training stage).The proposed approach can be integrated directly into most existing reservoir management routines. In addition, incorporating techniques for dimensionality reduction and clustering with ANN demonstrates the viability of this approach for analyzing large field data set. Given that quantitative ranking of operating areas, robust forecasting, and optimization of heavy oil recovery processes are major challenges faced by the industry, the proposed research highlights the significant potential of applying effective data-driven modeling approaches in analyzing other solvent-additive steam injection projects.

Integrated cluster analysis and artificial neural network modeling for steam-assisted gravity drainage performance prediction in heterogeneous reservoirs

To investigate the impact of fluid viscosity and rock heterogeneity on the characteristics (such as geometric complexity, roughness, and micro-morphology) of hydraulic fractures (HFs), laboratory triaxial fracturing experiments were conducted on homogeneous and layered tight sandstones using water- and carbon dioxide (CO2)-based fluids. The fractal dimension of HFs (Df) and the stimulated fracture area were quantitatively analyzed based on computerized tomography scanning and three-dimensional reconstruction methods. The surface roughness and micro-characteristics of HFs were then evaluated. Experimental results showed that CO2-based fracturing tended to create more HFs with a higher degree of geometric complexity (Df ranging 2.1113–2.2271) than that of HFs created by water-based fracturing (Df ranging 2.0952–2.1081) in a homogeneous tight sandstone. A complex HF network (Df = 2.4092) was generated in the layered tight sandstone using supercritical CO2 (SC-CO2) fracturing. The SC-CO2-induced fracture area in the layered tight sandstone was approximately three times larger than that of the homogeneous tight sandstone. Both the fluid viscosity and particle size of the host rock have a great effect on the roughness of the HF surface. CO2-based fracturing tends to generate curved HFs with uneven and cracked HF surfaces and massive microfractures, whereas water-based fracturing is more likely to induce straightforward HFs with smooth and clean HF surfaces and few microfractures. These induced microfractures enhance the micro-complexity of HFs, which may contribute to additional conductivity in the production stage. The obtained results provide a laboratory research basis for fracturing fluid selection and fracturing treatment design in tight sandstone reservoirs.

Hydraulic Fractures Induced by Water-/Carbon Dioxide-Based Fluids in Tight Sandstones

Predicting the drilling rate of penetration (ROP) is one approach to optimizing drilling performance. However, as ROP behavior is unique to specific geological conditions its application is not straightforward. Moreover, ROP is typically affected by various operational factors (e.g. bit type, weight-on-bit, rotation rate, etc.) as well as the geological characteristics of the rocks being penetrated. This makes ROP prediction an intricate and multi-faceted problem. Here we compare data mining methods with several machine learning algorithms to evaluate their accuracy and effectiveness in predicting ROP. The algorithms considered are: artificial neural networks (ANN) applying a multi-layer perceptron (MLP); ANN applying a radial basis function (RBF); support vector regression (SVR), and an hybrid MLP trained using a particle swarm optimization algorithm (MLP-PSO). Data preparation prior to executing the algorithms involves applying a Savitzky–Golay (SG) smoothing filter to remove noise from petrophysical well-logs and drilling data from the mud-logs. A genetic algorithm is applied to tune the machine learning algorithms by identifying and ranking the most influential input variables on ROP. This tuning routine identified and selected eight input variables which have the greatest impact on ROP. These are: weight on bit, bit rotational speed, pump flow rate, pump pressure, pore pressure, gamma ray, density log and sonic wave velocity. Results showed that the machine learning algorithms evaluated all predicted ROP accurately. Their performance was improved when applied to filtered data rather than raw well-log data. The MLP-PSO model as a hybrid ANN demonstrated superior accuracy and effectiveness compared to the other ROP-prediction algorithms evaluated, but its performance is rivalled by the SVR model.

A machine learning approach to predict drilling rate using petrophysical and mud logging data

Perforating cluster space optimization method of horizontal well multi-stage fracturing in extremely thick unconventional gas reservoir

Comprehensive Optimization Methodology for Stimulation Design of Low-Permeability Unconventional Gas Reservoirs

Analysis of Production History for Unconventional Gas Reservoirs With Statistical Methods

Optimal Fracture Spacing and Stimulation Design for Horizontal Wells in Unconventional Gas Reservoirs

Unified Fracture Design for very low permeability reservoirs

Multivariate Analysis and Data Mining of Well-Stimulation Data by Use of Classification-and-Regression Tree with Enhanced Interpretation and Prediction Capabilities

Srimoyee Bhattacharya

Papers

Comprehensive Optimization Methodology for Stimulation Design of Low-Permeability Unconventional Gas Reservoirs

Analysis of Production History for Unconventional Gas Reservoirs With Statistical Methods

Optimal Fracture Spacing and Stimulation Design for Horizontal Wells in Unconventional Gas Reservoirs

Unified Fracture Design for very low permeability reservoirs

Multivariate Analysis and Data Mining of Well-Stimulation Data by Use of Classification-and-Regression Tree with Enhanced Interpretation and Prediction Capabilities