Lethbridge, Alta : University of Lethbridge, Dept. of Geography
Tree species mapping around reclaimed oil and gas wells sites using hyperspectral and Light Detection and Ranging (LiDAR) remote sensing
Abstract
dc:description.abstractOil and gas activities in Alberta require disturbing forested lands, among other ecosystems, in order to extract resources. Due to the number of oil and gas sites requiring reclamation, monitoring can be problematic. Remote sensing provides cost-effective, timely, and repeatable data of these areas in support of monitoring efforts. Support Vector Machine (SVM) and Multiple Endmember Spectral Mixture Analysis (MESMA) were tested in order to identify tree species around reclaimed and abandoned well sites near Cold Lake, Alberta using CHRIS satellite imagery with and without airborne LiDAR data. A hierarchical classification approach was employed, which achieved an accuracy of 83.4 % when using SVM together with CHRIS imagery and LiDAR. This positive result indicates the ability of remote sensing to support reclamation management and monitoring objectives within Alberta’s forested areas.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Grantor dc:publisher
- Lethbridge, Alta : University of Lethbridge, Dept. of Geography
- Year dc:date.issued
- 2016
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Banting, James
- University of Lethbridge. Faculty of Arts and Science
- Advisors dc:contributor.supervisor
-
- Staenz, Karl
- Rochdi, Nadia
Subjects
dc:subject × 6Rights
- Language dc:language.iso
- en_CA
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/10133/4482