A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification
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 challeng...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://eprints.qut.edu.au/245097/ |
id |
ftqueensland:oai:eprints.qut.edu.au:245097 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Queensland University of Technology: QUT ePrints |
op_collection_id |
ftqueensland |
language |
unknown |
topic |
Antarctic Specially Protected Area (ASPA) data fusion environmental monitoring hyperspectral imaging (HSI) unmanned aerial system (UAS) unmanned aerial vehicle (UAV) |
spellingShingle |
Antarctic Specially Protected Area (ASPA) data fusion environmental monitoring hyperspectral imaging (HSI) unmanned aerial system (UAS) unmanned aerial vehicle (UAV) Sandino, Juan Bollard, Barbara Doshi, Ashray Randall, Krystal Barthelemy, Johan Robinson, Sharon A. Gonzalez, Felipe A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
topic_facet |
Antarctic Specially Protected Area (ASPA) data fusion environmental monitoring hyperspectral imaging (HSI) unmanned aerial system (UAS) unmanned aerial vehicle (UAV) |
description |
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 hyperspectral and multispectral imagery (HSI and MSI), global navigation satellite system (GNSS) enhanced with real-time kinematics (RTK) to collect ground control points (GCPs), and supervised machine learning classifiers. This workflow was validated in the field by acquiring ground and aerial data at ASPA 135, Windmill Islands, East Antarctica. The data preparation phase involves a data fusion technique to integrate HSI and MSI data, achieving the collection of georeferenced HSI scans with a resolution of up to 0.3 cm/pixel. From these high-resolution HSI scans, a series of novel spectral indices were proposed to enhance the classification accuracy of the model. Model training was achieved using extreme gradient boosting (XGBoost), with four different combinations tested to identify the best fit for the data. The research results indicate the successful detection and mapping of moss and lichens, with an average accuracy of 95%. Optimised XGBoost models, particularly Model 3 and Model 4, demonstrate the applicability of the custom spectral indices to achieve high accuracy with reduced computing power requirements. The integration of these technologies results in significantly more accurate mapping compared to conventional methods. This workflow serves as a foundational step towards more extensive remote sensing applications in Antarctic and ASPA vegetation mapping, as well as in monitoring the impact of climate change on the Antarctic ecosystem. |
format |
Article in Journal/Newspaper |
author |
Sandino, Juan Bollard, Barbara Doshi, Ashray Randall, Krystal Barthelemy, Johan Robinson, Sharon A. Gonzalez, Felipe |
author_facet |
Sandino, Juan Bollard, Barbara Doshi, Ashray Randall, Krystal Barthelemy, Johan Robinson, Sharon A. Gonzalez, Felipe |
author_sort |
Sandino, Juan |
title |
A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
title_short |
A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
title_full |
A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
title_fullStr |
A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
title_full_unstemmed |
A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification |
title_sort |
green fingerprint of antarctica: drones, hyperspectral imaging, and machine learning for moss and lichen classification |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://eprints.qut.edu.au/245097/ |
genre |
Antarc* Antarctic Antarctica East Antarctica Windmill Islands |
genre_facet |
Antarc* Antarctic Antarctica East Antarctica Windmill Islands |
op_source |
Remote Sensing |
op_relation |
https://eprints.qut.edu.au/245097/1/remotesensing_15_05658.pdf doi:10.3390/rs15245658 Sandino, Juan, Bollard, Barbara, Doshi, Ashray, Randall, Krystal, Barthelemy, Johan, Robinson, Sharon A., & Gonzalez, Felipe (2023) A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification. Remote Sensing, 15(24), Article number: 5658. http://purl.org/au-research/grants/arc/SR200100005 http://purl.org/au-research/grants/arc/T3_P028 http://purl.org/au-research/grants/arc/T2-P023 http://purl.org/au-research/grants/arc/T2-P016 http://purl.org/au-research/grants/arc/T2-P036 https://eprints.qut.edu.au/245097/ Centre for Robotics; Faculty of Engineering; School of Electrical Engineering & Robotics |
op_rights |
free_to_read http://creativecommons.org/licenses/by/4.0/ 2023 The Authors This work is covered by copyright. Unless the document is being made available under a Creative Commons Licence, you must assume that re-use is limited to personal use and that permission from the copyright owner must be obtained for all other uses. If the document is available under a Creative Commons License (or other specified license) then refer to the Licence for details of permitted re-use. It is a condition of access that users recognise and abide by the legal requirements associated with these rights. If you believe that this work infringes copyright please provide details by email to qut.copyright@qut.edu.au |
op_doi |
https://doi.org/10.3390/rs15245658 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
24 |
container_start_page |
5658 |
_version_ |
1797574031369568256 |
spelling |
ftqueensland:oai:eprints.qut.edu.au:245097 2024-04-28T08:02:45+00:00 A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification Sandino, Juan Bollard, Barbara Doshi, Ashray Randall, Krystal Barthelemy, Johan Robinson, Sharon A. Gonzalez, Felipe 2023-12-02 application/pdf https://eprints.qut.edu.au/245097/ unknown Multidisciplinary Digital Publishing Institute https://eprints.qut.edu.au/245097/1/remotesensing_15_05658.pdf doi:10.3390/rs15245658 Sandino, Juan, Bollard, Barbara, Doshi, Ashray, Randall, Krystal, Barthelemy, Johan, Robinson, Sharon A., & Gonzalez, Felipe (2023) A Green Fingerprint of Antarctica: Drones, Hyperspectral Imaging, and Machine Learning for Moss and Lichen Classification. Remote Sensing, 15(24), Article number: 5658. http://purl.org/au-research/grants/arc/SR200100005 http://purl.org/au-research/grants/arc/T3_P028 http://purl.org/au-research/grants/arc/T2-P023 http://purl.org/au-research/grants/arc/T2-P016 http://purl.org/au-research/grants/arc/T2-P036 https://eprints.qut.edu.au/245097/ Centre for Robotics; Faculty of Engineering; School of Electrical Engineering & Robotics free_to_read http://creativecommons.org/licenses/by/4.0/ 2023 The Authors This work is covered by copyright. Unless the document is being made available under a Creative Commons Licence, you must assume that re-use is limited to personal use and that permission from the copyright owner must be obtained for all other uses. If the document is available under a Creative Commons License (or other specified license) then refer to the Licence for details of permitted re-use. It is a condition of access that users recognise and abide by the legal requirements associated with these rights. If you believe that this work infringes copyright please provide details by email to qut.copyright@qut.edu.au Remote Sensing Antarctic Specially Protected Area (ASPA) data fusion environmental monitoring hyperspectral imaging (HSI) unmanned aerial system (UAS) unmanned aerial vehicle (UAV) Contribution to Journal 2023 ftqueensland https://doi.org/10.3390/rs15245658 2024-04-03T15:55:43Z 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 hyperspectral and multispectral imagery (HSI and MSI), global navigation satellite system (GNSS) enhanced with real-time kinematics (RTK) to collect ground control points (GCPs), and supervised machine learning classifiers. This workflow was validated in the field by acquiring ground and aerial data at ASPA 135, Windmill Islands, East Antarctica. The data preparation phase involves a data fusion technique to integrate HSI and MSI data, achieving the collection of georeferenced HSI scans with a resolution of up to 0.3 cm/pixel. From these high-resolution HSI scans, a series of novel spectral indices were proposed to enhance the classification accuracy of the model. Model training was achieved using extreme gradient boosting (XGBoost), with four different combinations tested to identify the best fit for the data. The research results indicate the successful detection and mapping of moss and lichens, with an average accuracy of 95%. Optimised XGBoost models, particularly Model 3 and Model 4, demonstrate the applicability of the custom spectral indices to achieve high accuracy with reduced computing power requirements. The integration of these technologies results in significantly more accurate mapping compared to conventional methods. This workflow serves as a foundational step towards more extensive remote sensing applications in Antarctic and ASPA vegetation mapping, as well as in monitoring the impact of climate change on the Antarctic ecosystem. Article in Journal/Newspaper Antarc* Antarctic Antarctica East Antarctica Windmill Islands Queensland University of Technology: QUT ePrints Remote Sensing 15 24 5658 |