Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery through Data Augmentation
| dc.contributor.author | Hnatushenko, Viktoriia V. | en |
| dc.contributor.author | Hnatushenko, Volodymyr V. | en |
| dc.contributor.author | Soldatenko, Dmytro V. | en |
| dc.contributor.author | Heipke, Christian | en |
| dc.date.accessioned | 2023-12-19T11:38:56Z | |
| dc.date.available | 2023-12-19T11:38:56Z | |
| dc.date.issued | 2023 | |
| dc.description | Vic. Hnatushenko: ORCID 0000-0001-5304-4144; Vol. Hnatushenko: ORCID 0000-0003-3140-3788; D. Soldatenko: ORCID 0000-0001-6041-7383 | en |
| dc.description.abstract | ENG: This study aims to enhance the quality of detecting burned areas in satellite imagery using deep learning by optimizing the training dataset volume through the application of various augmentation methods. The study analyzes the impact of image flipping, rotation, and noise addition on the overall accuracy for different classes of burned areas in a forest: fire, burned, smoke and background. Results demonstrate that while single augmentation techniques such as flipping and rotation alone did not result in significant improvements, a combined approach and the addition of noise resulted in an enhancement of the classification accuracy. Moreover, the study shows that augmenting the dataset through the use of multiple augmentation methods concurrently, resulting in a fivefold increase in input data, also enhanced the recognition accuracy. The study also highlights the need for further research in developing more efficient CNN models and in experimenting with additional augmentation methods to improve the accuracy of burned area detection, which would benefit environmental protection and emergency response services. | en |
| dc.description.sponsorship | Dnipro University of Technology, Dnipro, Ukraine; Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Germany | en |
| dc.identifier.citation | Hnatushenko Vic., Hnatushenko V., Soldatenko D., Heipke C. Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery through Data Augmentation. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2023. Vol. XLVIII-1/W2-2023. P. 1749–1755. DOI: https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1749-2023. | en |
| dc.identifier.doi | https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1749-2023 | en |
| dc.identifier.issn | 1682-1750 (Print) | |
| dc.identifier.issn | 2194-9034 (Online) | |
| dc.identifier.uri | https://isprs-archives.copernicus.org/articles/XLVIII-1-W2-2023/1749/2023/isprs-archives-XLVIII-1-W2-2023-1749-2023.html | en |
| dc.identifier.uri | https://crust.ust.edu.ua/handle/123456789/17903 | en |
| dc.language.iso | en | |
| dc.publisher | Copernicus GmbH (Copernicus Publications) on behalf of the International Society of Photogrammetry and Remote Sensing | en |
| dc.subject | forest fire | en |
| dc.subject | satellite images | en |
| dc.subject | augmentation | en |
| dc.subject | CNN | en |
| dc.subject | КІТС | uk_UA |
| dc.subject.classification | TECHNOLOGY::Information technology::Image analysis | en |
| dc.title | Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery through Data Augmentation | en |
| dc.type | Article | en |