Support vector classification for geostatistical modeling of categorical variables

  • Author / Creator
    Gallardo, Enrique
  • 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.

  • Subjects / Keywords
  • Graduation date
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
  • Language
  • Institution
    University of Alberta
  • Degree level
  • Department
    • Department of Civil and Environmental Engineering
  • Supervisor / co-supervisor and their department(s)
    • Leuangthong, Oy (Civil and Environmental Engineering)
  • Examining committee members and their departments
    • Szymanski, Jozef (Civil and Environmental Engineering)
    • Ray, Nilanjan (Computing Science)