An unsupervised classification-based time series change detection approach for mapping forest disturbance

Simple item page
dc.contributor.authorParshakov, Ilia
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorPeddle, Derek Roland
dc.date.accessioned2021-02-26T20:39:59Z
dc.date.available2021-02-26T20:39:59Z
dc.date.issued2021
dc.degree.levelPh.Den_US
dc.description.abstractUnsupervised Classification to Change (UC-Change) is a new remote sensing approach for mapping areas affected by logging and wildfires. It addresses the main limitations of existing image time-series change detection techniques, such as limited multi-sensor capabilities, use of purely spectral-based forest recovery metrics, and poor detection of salvage harvesting. UC Change detects disturbances and tracks forest recovery by analyzing changes in the spatial distribution of spectral classes over time. The algorithm detected approximately 85% and 70% of reference cutblock and fire scar pixels at a ±2-year temporal agreement, respectively, consistently outperforming existing algorithms across different biogeoclimatic zones of British Columbia, Canada. The results indicate an upper estimate of 7.5 million ha of forest cleared between 1984 and 2014, which is above estimates based on existing maps and databases (6.3 – 6.7 million ha). Also presented is a new framework for using open-access data for validation of change detection results.en_US
dc.description.sponsorshipNatural Sciences and Engineering Research Council of Canada (NSERC) Collaborative Research and Training Experience (CREATE) grant entitled Advanced Methods, Education and Training in Hyperspectral Science and Technology (AMETHYST). Financial code: KS-NSERC2 Staenz 40307-4185-8001en_US
dc.identifier.urihttps://hdl.handle.net/10133/5840
dc.language.isoen_USen_US
dc.proquest.subject0799en_US
dc.proquest.subject0768en_US
dc.proquest.subject0478en_US
dc.proquestyesYesen_US
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Geography and Environmenten_US
dc.publisher.departmentDepartment of Geography and Environmenten_US
dc.publisher.facultyArts and Scienceen_US
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)en_US
dc.subjectremote sensingen_US
dc.subjectchange detectionen_US
dc.subjectenvironmental monitoringen_US
dc.subjectforest disturbanceen_US
dc.subjectmachine learningen_US
dc.subjectforestryen_US
dc.subjecttime seriesen_US
dc.subjectLandsaten_US
dc.subjectSentinel-2en_US
dc.subjectUC-Changeen_US
dc.subjectcutblocksen_US
dc.subjectclearcutsen_US
dc.subjectforest harvesten_US
dc.subjectForest monitoring -- British Columbiaen_US
dc.subjectForests and forestry -- British Columbia -- Remote sensingen_US
dc.subjectForests and forestry -- British Columbia -- Forecasting -- Mathematical modelsen_US
dc.subjectForests and forestry -- British Columbia -- Measurement -- Data processingen_US
dc.subjectForest mapping -- British Columbiaen_US
dc.subjectTime series analysis -- Data processingen_US
dc.subjectClearcutting -- British Columbia -- Measurementen_US
dc.subjectCutover lands -- British Columbia -- Measurementen_US
dc.subjectLogging -- British Columbia -- Measurementen_US
dc.subjectWildfires -- British Columbia -- Measurementen_US
dc.subjectImage analysis -- Data processingen_US
dc.subjectRemote sensing images -- Data processingen_US
dc.subjectDissertations, Academicen_US
dc.titleAn unsupervised classification-based time series change detection approach for mapping forest disturbanceen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
PARSHAKOV_ILIA_PHD_2021.pdf
Size:
3.37 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
3.25 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses