Data-Driven In-Situ Geomechanical Characterization in Shale Reservoirs

Abstract

Compressional and shear travel time logs (DTC and DTS) acquired using sonic logging tools are crucial for subsurface geomechanical characterization. In this study, 13 ‘easy-to-acquire’ conventional logs were processed using 6 shallow learning models, namely ordinary least squares (OLS), partial least squares (PLS), elastic net (EN), LASSO, multivariate adaptive regression splines (MARS), and artificial neural network (ANN), to successfully synthesize DTC and DTS logs. Among the 6 models, ANN outperforms other models with R2 of 0.87 and 0.85 for the syntheses of DTC and DTS logs, respectively. The 6 shallow learning models are trained and tested with 8481 data points acquired from a 4240-feet depth interval of a shale reservoir in Well 1, and the trained models are deployed in Well 2 for purposes of blind testing against 2920 data points from 1460-feet depth interval. Following that, 5 clustering algorithms are applied on the 13 ‘easy-to-acquire’ logs to identify clusters and compare them with the prediction performance of the shallow learning models used for log synthesis. Dimensionality reduction algorithm is used to visualize the characteristics of the clustering algorithm. Hierarchical clustering, DBSCAN, and self-organizing map (SOM) algorithms are sensitive to outliers and did not effectively differentiate the input data into consistent clusters. Gaussian mixture model can well differentiate the various formations, but the clusters do not have a strong correlation with the prediction performance of the log-synthesis models. Clusters identified using K-means method have a strong correlation with the prediction performance of the shallow learning models. By combining the predictive shallow learning models for log synthesis with the K-means clustering algorithm, we propose a reliable workflow that can synthesize the DTC and DTS logs, as well as generate a reliability indicator for the predicted logs to help an user better understand the performance of the shallow learning models during deployment.

Automatic Optimization of Multi-Well Multi-Stage Fracturing Treatments Combining Geomechanical Simulation, Reservoir Simulation and Intelligent Algorithm

“…The standard DK girds are applied out of the SRV. Thus, the transient behavior of reservoir fluids from the matrix to fractures can be accurately modeled, and the influences of natural fractures can be considered [26]. Sierra et al reported that the creation of planar fracture in shale reservoirs is more effective, while a complex fracture network is preferable only for formation with a permeability less than 10 −7 µm 2 [27].…”

Optimization of Energy Consumption in Oil Fields Using Data Analysis

“…The lower system efficiency leads to huge energy consumption in the field, which also affects oil production [10][11][12][13][14]. Due to the low prices of oil, companies are starting to reduce expenses and improve oil production and efficiency [15][16][17][18][19][20][21][22]. There are over 920,000 operating wells in the world [23][24][25][26], and 87% of them are producing oil with artificial lift methods [27,28].…”

Modeling and scale-bridging using machine learning: nanoconfinement effects in porous media

“…www.nature.com/scientificreports/ (ML) techniques have found their way into petroleum engineering and studies of porous media. For instance, Fulford et al 20 used ML to tackle the challenges for predicting well performance in shale reservoirs, and similarly, Li et al 21 used an ensemble of ML techniques to construct the expensive-to-acquire logs which provided a reliable way to estimate the in-situ geomechanical properties of shale reservoirs. Kamrava et al 22 used ML to generate synthetic 3D micropore structures in shale.…”