The Discovery of the Marcellus Shale Play, An Operator’s Experience

The development of shale assets has reached a point where operators face the challenge of infill drilling. The scope of this project is to investigate the impact of neighboring well pads on the performance of a newly developed well/pad. This paper highlights the differences in production performance of "old" pads versus "new" well and analyzes how the depletion history of the existing pads affects the performance of new well. The study area covers two pads: Pad A and Pad B which have 10 and 12 wells respectively; these wells have been producing since 2016 from the dry gas region of Marcellus Shale in southwestern Pennsylvania. Pad A and Pad B are more than 9000 ft apart, and the region between these two pads has potential for future development. For this project, a 3-D reservoir simulation model that includes both pads was built and calibrated to match past performance of Pad A and Pad B. The calibrated simulation model then was utilized for developing new wells. The reservoir simulation model was used to perform a sensitivity analysis on reservoir characteristics and the impact of Pad A and Pad B's depletion history on the performance of new well(s). The workflow involves optimizing the well spacing of proposed well(s) with/without considering the depletion history. Usually, with the very low permeability of shale reservoirs, the depletion history of neighboring wells is expected to affect the performance of newly developed wells. The new wells are considered as a different well pad, and their stimulated reservoir volume does not overlap with the Pad A and Pad B. However, the region average reservoir pressure is reduced due to the Pad A and Pad B production history. In most of shale reservoir numeral simulation studies, the reservoir is considered virgin. The average reservoir pressure potentially impacts the well spacing optimization workflow as well as the designing of an effective well completion job. In this study we compare two scenarios. One scenario considers the depletion history of neighboring well pads and the other one does not. The net present value optimization was done with and without considering the impact of depletion history. This project studies the effects of neighboring well pads on production performance of newly developed pad. Compared to the interaction of parent/child well in a single well pad, multi-pad studies are rare primarily because of the high computational cost associated with a multi-pad numerical simulation analysis.

show abstract

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

Shahkarami

Ayers²,

Wang

et al. 2018

SPE/AAPG Eastern Regional Meeting

View full text Add to dashboard Cite

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.

show abstract

The Discovery of the Marcellus Shale Play, An Operator’s Experience

Cited by 3 publications

References 0 publications

Modeling and predicting natural gas fracking pad landscapes require a multidisciplinary approach: A commentary

Modeling and predicting natural gas fracking pad landscapes require a multidisciplinary approach: A commentary

Impacts of Field Depletion on Future Infill Drilling Plans in the Marcellus Shale

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

Contact Info

Product

Resources

About