Abstract

A methodology leveraging Neural Networks has been developed to identify completion optimization potential in the development of a mature Montney Gas Asset providing well specific and field-wide completion effectiveness analysis. This paper presents an approach that can be applied to obtain a better understanding of the relationship between practices used in hydraulic fracturing and well performance, and to highlight methods to optimise well production, based upon a dataset of 56 wells, all completed in the same stratigraphic zone of the Upper Montney, within a developed area of 200 km² in NE British Columbia.

A combined Principal Component analysis — Artificial Neural Network modelling technique (PCA-ANN) has been used in this work to identify key completion-related drivers of well performance, along with some geologically related indicators, and apply neural network modelling to predict well performance as defined by estimated ultimate recovery (EUR), from a “matrix” of completion related data. The results can be used to identify optimal hydraulic fracture design parameters for new wells to enhance production, and potentially also wells that may be candidates for recompletion.

Eight key completion-related variables are identified by the PCA method from a total of 31 considered: these include geologically related ones of breakdown pressure (BrdPr) and instantaneous shut-in pressure (ISIP), along with engineering/operational parameters including cluster spacing, perforation number, proppant amount, sand concentration, fluid volume and pumping rate. Using these variables in a sensitivity analysis to measure/predict the EUR shows that for the dataset studied, the dominant production drivers are cluster spacing and proppant amount, which are related to controllable aspects of the hydraulic fracturing process.

When applied to evaluate existing producing wells and optimise completions, the approach identifies the lower performing wells that potentially could have better performance if their completion parameters were optimised. Furthermore, the PCA-ANN technique indicates how to achieve optimal results by identifying which parameters should be changed and by how much. As such, this predictive model delivers a series of charts for selecting and evaluating different completion parameters and designs.