Data Driven Intelligent Modeling to Estimate Adsorption of Methane Gas in Shales

Artificial intelligence is a smart tool widely used in Petroleum engineering. Adaptive Neuro-Fuzzy Inference System (ANFIS) is an artificial intelligence technique that is a hybrid between Artificial Neural Networks (ANN) and fuzzy logic. In this paper, both ANN and ANFIS were applied to propose a new methodology based on intelligent algorithms to predict adsorption of methane gas in shale. Feed-Forward Neural Network and subtractive clustering were applied to correlate adsorption with several parameters. These include temperature, pressure, moisture content, and total organic content (TOC). A real data set collected from the literature, which includes about 350 data points, was used in the development of a new empirical correlation. The set was divided into a 70:30 ratio for training and testing, respectively. The average absolute percentage error, correlation coefficient, and mean squared error were considered in the error metrics to obtain the best possible model. The results show that methane adsorption can be efficiently correlated with the inputs using both machine learning tools. Using ANN, the correlation coefficient for both testing and training data was more than 99%. A detailed sensitivity analysis for the ANN model is also provided in this paper.