2023
DOI: 10.3390/rs15245658
|View full text |Cite
|
Sign up to set email alerts
|

A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification

Juan Sandino,
Barbara Bollard,
Ashray Doshi
et al.

Abstract: Mapping Antarctic Specially Protected Areas (ASPAs) remains a critical yet challenging task, especially in extreme environments like Antarctica. Traditional methods are often cumbersome, expensive, and risky, with limited satellite data further hindering accuracy. This study addresses these challenges by developing a workflow that enables precise mapping and monitoring of vegetation in ASPAs. The processing pipeline of this workflow integrates small unmanned aerial vehicles (UAVs)—or drones—to collect hyperspe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
4
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
3

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 62 publications
0
4
0
Order By: Relevance
“…While both studies leverage ML, the first emphasises health assessment, and the second focuses on precise mapping, yet both contribute valuable insights into the potential applications of remote sensing technologies in monitoring the impact of climate change on the Antarctic ecosystem. Despite our adoption of the U-Net model in this study, the achieved results were comparatively lower than those obtained in the hyperspectral study that utilised XGBoost [39]. One prominent factor contributing to this performance gap is the insufficient number of training samples available for U-Net.…”
Section: Discussionmentioning
confidence: 68%
See 3 more Smart Citations
“…While both studies leverage ML, the first emphasises health assessment, and the second focuses on precise mapping, yet both contribute valuable insights into the potential applications of remote sensing technologies in monitoring the impact of climate change on the Antarctic ecosystem. Despite our adoption of the U-Net model in this study, the achieved results were comparatively lower than those obtained in the hyperspectral study that utilised XGBoost [39]. One prominent factor contributing to this performance gap is the insufficient number of training samples available for U-Net.…”
Section: Discussionmentioning
confidence: 68%
“…Our study focuses on evaluating the health of moss and lichen using multispectral imagery captured by UAVs, employing ML classifiers such as XGBoost for segmentation. In contrast, another study by Sandino et al primarily addresses the challenge of mapping the same study location using a workflow that integrates UAV, hyperspectral imagery, and same ML classifiers of XGBoost [ 39 ]. This approach resulted in an average accuracy of 95%, demonstrating the successful detection and mapping of moss and lichens.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations