Subsurface geological characterization requires solving a classification problem to obtain a model of facies that is later populated with continuous properties. The classification problem, which consists of assigning a single category to any unsampled location based on observed data, is analyzed and solved in this thesis using geostatistical and machine learning tools.
This research proposes an easy-to-implement heuristic technique that uses geostatistical criteria, such as correct classification of the observed data and good reproduction of the global proportions of categories, to obtain from the SVC algorithm a boundary classifier. This boundary is used to generate the facies model.
The case studies show that the implementation of the proposed technique is highly automatic. The responses are comparable in terms of prediction accuracy to those obtained by the conventional geostatistical approach. / Mining Engineering
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:AEU.10048/541 |
| Date | 11 1900 |
| Creators | Gallardo, Enrique |
| Contributors | Leuangthong, Oy (Civil and Environmental Engineering), Szymanski, Jozef (Civil and Environmental Engineering), Ray, Nilanjan (Computing Science) |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | 3507460 bytes, application/pdf |
Page generated in 0.0024 seconds