Application of Machine Learning Algorithms for Optimizing Future Production in Marcellus Shale, Case Study of Southwestern Pennsylvania

Abstract

The Marcellus Shale has more than a decade of development history. However, there are many questions that still remain unanswered. What is the best inter-well spacing? What are the optimum stage length, proppant loading, and cluster spacing? What are the ideal combinations of these completion parameters? And how can we maximize the rate return on our investment? This study proposes innovative tools that allow researchers to answer these questions. We build these set of tools by utilizing the pattern recognition abilities of machine learning algorithms and public data from the Southwestern Pennsylvania region of the Marcellus Shale. By means of artificial intelligence and data mining techniques, we studied a database that includes public data from more than 2,000 wells producing from the aforementioned study area. The database contained completion, drilling, and production history information from various operators active in Allegheny, Greene, Fayette, Washington, and Westmoreland counties located in the Southwestern Pennsylvania. Extensive preprocessing and data cleansing steps were involved to prepare the database. Various machine learning techniques (Linear Regression (LR), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Gaussian Processes (GP)) were applied to understand the non-linear patterns in the data. The objective was to develop predictive models that were trained and validated based on the current database. The predictive models were validated using information originating from numerous wells in the area. Once validated, the model could be used in reservoir management decision-making workflows to answer questions such as what are the best drilling scenarios, the optimum hydraulic fracturing design, the initial production rate, and the estimated ultimate recovery (EUR). The workflow is purely based on field data and free of any cognitive human bias. As soon as more data is available, the model could be updated. The core data in this workflow is sourced from public domains, and therefore, intensive preprocessing efforts were necessary.

Development and Evaluation of Deep Learning Models for Forecasting Gas Production and Flowback Water in Shale Gas Reservoirs

“…As for the perceptron, the correlation between input variables cannot impact performance since it is ultimately learning the behavior of real data (the generated models are nonlinear models due to the use of the ReLU activation function). Additionally, in some previously reported works for other reservoirs, these input variables have been considered. − …”

Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

“…Collecting and labeling a large number of qualified training samples is also a very tough task. The well geological characteristics, well completion design, location of well, shale wettability, and reservoir quality are often adopted as dataset to optimize the well design and oil/gas production. − Shahkarami et al collected data from more than 800 wells under different drilling and hydraulic fracturing parameters and normalized the 25 input characteristics to estimate the production behavior of oil wells . Also, the completion and stimulation parameters of nearly 2700 wells are used to predict the Marcellus shale’s initial production and optimize the oil wells .…”

“…151−153 Shahkarami et al collected data from more than 800 wells under different drilling and hydraulic fracturing parameters and normalized the 25 input characteristics to estimate the production behavior of oil wells. 154 Also, the completion and stimulation parameters of nearly 2700 wells are used to predict the Marcellus shale's initial production and optimize the oil wells. 155 The SVM algorithm is proposed to evaluate the oil/gas saturation of the Ordos shale reservoir.…”

Optimizing construction parameters for fractured horizontal wells in shale oil

“…Based on this, some scholars have further established the optimal design model by considering the matching of construction parameters and geological parameters. Shahkarami et al (2018) used a publicly available data database from more than 2000 Wells in southwest Pennsylvania to establish a hydraulic fracturing parameter optimization design model that is based on linear regression, support vector machine, artificial neural network, Gaussian process, and other machine-learning methods. Through sensitivity analysis, Nguyen-Le and Shin (2019) determined the framework of controlling factors to put forward a dynamic economic index, and realized the N p value optimization model considering the comprehensive influence of reservoir parameters and fracturing parameters.…”