Exploiting Overlapping Landsat Scene Classifications and Focal Context to Identify Boreal Disturbance Mapping Uncertainty

Simple item page
dc.contributor.advisorRemmel, Tarmo
dc.contributor.authorWu, Wesley Jovia
dc.date.accessioned2022-12-14T16:21:16Z
dc.date.available2022-12-14T16:21:16Z
dc.date.copyright2022-05-25
dc.date.issued2022-12-14
dc.date.updated2022-12-14T16:21:15Z
dc.degree.disciplineGeography
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractThe BorealDB dataset is derived from a mosaic of Landsat scenes that were independently classified to identify historic fire and timber harvesting disturbances within Ontario. This thesis identifies and flags areas of classification uncertainty within BorealDB and scrutinizes them to assess classification confidence. The focal context of all orthogonal neighbour states was quantified to feed classification tree (CT) and random forest (RF) classifiers to predict focal disturbance classes. Uncertainty is deemed to exist where BorealDB and predicted CT or RF classes disagree. When RF and CT predictions were compared with the BorealDB classes, RF predicted more uncertainty (58%) than CT predictions (15%). Sampled locations compared with original satellite imagery and visual assessments suggested uncertainty depended on classifier, disturbance type, and spatial neighbours. Timber harvest disturbance classifications had the most uncertainty and CT predictions was the most consistent with neighbouring classifications and visual assessments indicating it is more effective than RF.
dc.identifier.urihttp://hdl.handle.net/10315/40620
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectGeographic information science
dc.subjectForestry
dc.subjectGeography
dc.subject.keywordsContextual classifier
dc.subject.keywordsDecision tree
dc.subject.keywordsUncertainty
dc.subject.keywordsNeighbourhood
dc.subject.keywordsRandom forest
dc.subject.keywordsFocal context
dc.subject.keywordsDisturbance
dc.subject.keywordsBoreal forest
dc.subject.keywordsForest fire
dc.subject.keywordsTimber harvest
dc.subject.keywordsOrthogonal
dc.subject.keywordsNearest neighbour
dc.titleExploiting Overlapping Landsat Scene Classifications and Focal Context to Identify Boreal Disturbance Mapping Uncertainty
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Wu_Wesley_J_2022_Masters.pdf
Size:
15.32 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Geography

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.