An attention-based U-Net for detecting deforestation within satellite sensor imagery

John, David; Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584. 2022 An attention-based U-Net for detecting deforestation within satellite sensor imagery. International Journal of Applied Earth Observation and Geoinformation, 107, 102685. 9, pp. 10.1016/j.jag.2022.102685

Before downloading, please read NORA policies.

Preview

Text N532301JA.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (5MB) | Preview

Abstract/Summary

In this paper, we implement and analyse an Attention U-Net deep network for semantic segmentation using Sentinel-2 satellite sensor imagery, for the purpose of detecting deforestation within two forest biomes in South America, the Amazon Rainforest and the Atlantic Forest. The performance of Attention U-Net is compared with U-Net, Residual U-Net, ResNet50-SegNet and FCN32-VGG16 across three different datasets (three-band Amazon, four-band Amazon and Atlantic Forest). Results indicate that Attention U-Net provides the best deforestation masks when tested on each dataset, achieving average pixel-wise F1-scores of 0.9550, 0.9769 and 0.9461 for each dataset, respectively. Mask reproductions from each classifier were also analysed, showing that compared to the ground reference Attention U-Net could detect non-forest polygons more accurately than U-Net and overall it provides the most accurate segmentation of forest/deforest compared with benchmark approaches despite its reduced complexity and training time, thus being the first application of an Attention U-Net to an important deforestation segmentation task. This paper concludes with a brief discussion on the ability of the attention mechanism to offset the reduced complexity of Attention U-Net, as well as ideas for further research into optimising the architecture and applying attention mechanisms into other architectures for deforestation detection. Our code is available at https://github.com/davej23/attention-mechanism-unet.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	10.1016/j.jag.2022.102685
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	0303-2434
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
Additional Keywords:	attention mechanism, attention U-Net, deep learning, deforestation mapping, Sentinel-2
NORA Subject Terms:	Ecology and Environment Electronics, Engineering and Technology
Date made live:	23 Mar 2022 10:41 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/532301

Actions (login required)

View Item

Document Downloads

More statistics for this item...