Artificial Intelligence Approach for Predicting the Shale Brittleness Index - A Middle East Basin Case Study

Abstract

Abstract Brittleness Index (BI) of rocks can help target the most suitable formation for the hydraulic fracturing stimulation in the tight shale reservoirs. The two most widely used approaches in the petroleum industry are based on mineralogical composition and elastic parameters for the BI estimation. However, these approaches may not be applied for all wells for BI determination due to the scarcity of mineralogical-composition and shear wave slowness data. This paper presents a machine learning (ML) approach to predict the BI using readily available well logs. Well log data were collected from three different wells that encompass a total of 2000 ft thick interval of potential shale gas formation in one of the middle eastern basins. Mineralogical composition of shale formation revealed that the shale intervals are comprising of alternate high brittle and low brittle zones and mainly composed of quartz, clay, feldspar, and mica. Feed-forward artificial neural network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were employed to develop the predictive model for the BI. The proposed model was tested and validated to check the consistency of the model. The reliability of the proposed AI model was reflected by the correlation coefficient (CC) ‘0.97’ between predicted and actual brittleness indices. The root mean squared ‘RMSE’ and average absolute percentage error ‘AAPE’ of the predicted brittleness were observed as 3.78 percent and 1.98 respectively for the ANN model. AAPE and RMSE for ANFIS predictive model were 3.51 and 1.81 respectively. The coefficient of determinations (R2) for ANN and ANFIS models were 0.945 and 0.951 respectively.ANN was found to be better than ANFIS by giving high accuracy. The proposed model was then compared with widely used models in the industry such as Jarvie et al., (2007) and Rybacki et al., (2016) on a blind dataset. The predictive model was also validated by comparing with two widely used mineralogy-based approaches. The developed approach can be applied to identify the brittle layers/zones within the shale gas reservoirs to optimize the hydraulic fracturing stimulation treatment. Results showed that the proposed model outperformed previous models by giving less error.