Identifying Discrete Fracture Networks by Clustering with Microseismic Data
Scott McKean, Jeffrey A. Priest, David W. Eaton
In the proceedings of: GeoEdmonton 2018: 71st Canadian Geotechnical Conference; 13th joint with IAH-CNCSession: Rock Mechanics and Engineering Geology II
ABSTRACT: Microseismic monitoring is common in the mining and petroleum industries. Pattern recognition to identify faults, fractures, and damage zones in the microseismic data can be a challenge due to the density and number of observations and their multiple attributes. This study applies unsupervised machine learning techniques to identify features in a dataset from a hydraulic fracturing program in the Duvernay Formation. It compares partitional, hierarchical, and density based clustering methods using various validation statistics and with multiple subsets of data attributes. The study shows that lower dimensional datasets tend to yield the best results, and that it is possible to cluster microseismic data using unsupervised techniques.
RÉSUMÉ: La surveillance microsismique est importante pour les industries minières et pétrolières. La reconnaissance des formes pour identifier les failles, les fractures et les zones endommagées dans les observations microsismiques est difficile en raison de la densité et le nombre d'observations et de leurs multiples attributs. Cette étude applique des techniques d'apprentissage machine sans supervision pour identifier les caractéristiques des observations d'un programme de fracturation hydraulique dans la Formation Duvernay. Il compare les méthodes de classification par partition, hiérarchique, et basée sur la densité en utilisant diverses statistiques de validation et avec plusieurs sous-ensembles d'attributs de données. L'étude montre que les ensembles de données ttributs donner les meilleurs résultats, et qu'il est possible de regrouper les observations microsismiques en utilisant des techniques non supervisées.
Access this article:
Canadian Geotechnical Society members can access to this article, along with all other Canadian Geotechnical Conference proceedings, in the Member Area. Conference proceedings are also available in many libraries.
Cite this article:
Scott McKean; Jeffrey A. Priest; David W. Eaton (2018) Identifying Discrete Fracture Networks by Clustering with Microseismic Data in GEO2018. Ottawa, Ontario: Canadian Geotechnical Society.
@article{geo2018Paper409,author = Scott McKean; Jeffrey A. Priest; David W. Eaton,title = Identifying Discrete Fracture Networks by Clustering with Microseismic Data,year = 2018}