Using Sentinel-2 imagery and an M-RCNN to detect canopy and deforestation
dc.contributor.advisor
Nichol, Caroline
en
dc.contributor.author
Carter, William
en
dc.date.accessioned
2021-05-13T15:26:12Z
dc.date.available
2021-05-13T15:26:12Z
dc.date.issued
2020-08-31
dc.description.abstract
Continued deforestation is a global problem with major consequences for climate change. Several UN-REDD-recognized canopy disturbance methods are available, all of which currently rely on numerous pre-processing steps before an output is created, making them time-consuming methods of surveillance in situations where timely intervention to halt deforestation is essential. This study trains an M-RCNN using Sentinal-2 imagery with transfer learning to produce high-resolution deforestation. Monitoring which can be frequently and rapidly updated. By testing different hyperparameters, an M-RCNN tool was developed to produce optimal imagery change detection within the confines of the available computational capacity. This study has shown that, with a more powerful GPU and by building on training techniques, machine learning is a reliable and straightforward object and change recognition tool which could be used for rapid detection of deforestation. Future developments for this study would be to train the model using SAR so that cloud mitigation techniques are not required.
en
dc.identifier.uri
https://hdl.handle.net/1842/37613
dc.identifier.uri
http://dx.doi.org/10.7488/era/894
dc.language.iso
en
dc.publisher
The University of Edinburgh
en
dc.subject
M-RCNN
en
dc.subject
deforestation
en
dc.subject
machine learning
en
dc.subject
Sentinel-2
en
dc.subject
computer vision
en
dc.title
Using Sentinel-2 imagery and an M-RCNN to detect canopy and deforestation
en
dc.type
Thesis or Dissertation
en
dc.type.qualificationlevel
Masters
en
dc.type.qualificationname
MSc Master of Science
en
Files
This item appears in the following Collection(s)