Tools
Tools
Mata, Prateek (2023) Classifying Land Cover of Ireland From Satellite Imagery using Deep Learning and Transfer Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
The use of satellite images for land cover classification has become increasingly important for governments like Ireland, where the population is increasing rapidly, to monitor changes in the environment and support urban development, disaster management, and sustainable development. However, implementing land cover and land use classification can be challenging due to the absence of a space program and the lack of labelled training data, which is expensive to generate. This research project implements two deep learning models trained on a novel land use and land cover classification dataset using transfer learning to classify a new dataset of land cover images of Ireland created using Sentinel-2A satellite images, out of which the ResNet-50 achieved a 73% accuracy. In addition, it also shows how data augmentation helps improve the accuracy of a land cover classification model where less labelled training data is available.A novel classification model was created based on the identified gaps in the results of the analyzed literature review, which is also presented.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Mulwa, Catherine UNSPECIFIED |
| Subjects: | G Geography. Anthropology. Recreation > GF Human ecology. Anthropogeography Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TR Photography Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 19 May 2023 16:47 |
| Last Modified: | 19 May 2023 16:47 |
| URI: | https://norma.ncirl.ie/id/eprint/6616 |
Actions (login required)
 |
View Item |