Data

Robinson Ridge Lichen Segmentation Maps Using UAV imagery and Machine Learning

Australian Antarctic Division

Amarasingam, N., Sandino, J., Doshi, A., Randall, K., King, D., Blackman, E., Barthelemy, J., Bollard, B., Robinson, S. and Gonzalez, F. ; AMARASINGAM, NARMILAN ; SANDINO, JUAN ; DOSHI, ASHRAY ; RANDALL, KRYSTAL ; KING, DIANA ; BLACKMAN, ELKA ; BARTHELEMY, JOHAN ; BOLLARD, BARBARA ; ROBINSON, SHARON ; GONZALEZ, FELIPE

Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]

ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.26179/xahj-dq75&rft.title=Robinson Ridge Lichen Segmentation Maps Using UAV imagery and Machine Learning&rft.identifier=10.26179/xahj-dq75&rft.publisher=Australian Antarctic Data Centre&rft.description=This is a child record, see the parent record AAS_4628_UAS for more information.This work was completed as part of the program Securing Antarctica's Environmental Future (SAEF).Dataset Components (Open Access)1. Output Segmentation MapsThis record includes vegetation segmentation outputs generated by standalone deep learning models (DeepLabv3+, FCN, U-Net) and an ensemble stacking approach using XGBoost. These models were used to classify vegetation communities in the study area. The results provide detailed segmentation maps that highlight the distribution of different vegetation types. The output segmentation maps are critical for understanding and analysing the vegetation communities in Robinson Ridge, Antarctica. These maps, generated through advanced machine learning techniques, support further research, validation, and applications in environmental monitoring. The inclusion of Vegetation Indices (VIs) helps in deriving additional insights into vegetation health and distribution.Data Collection and AnalysisData was collected in January 2023 using a BMR3.9RTK UAV developed by SaiDynamics Australia, equipped with a MicaSense Altum multispectral sensor and a Sony Alpha 5100 RGB camera. Flights at 70 m altitude yielded a ground sampling distance of 2.93 cm/pixel. A total of 2,814 images were collected, covering around 5.15 hectares.Usage NotesRefer to the readme.txt files in each record for further details on data formats.Files:- .dat, .hdr, .tif – Segmentation maps and vegetation indices- readme.txt – Description and metadata for data usage and formatsProgress Code: completedStatement: During data collection, poor image quality in certain sections of the orthomosaic—caused by lighting conditions and snow—reduced the visual clarity necessary for reliable interpretation. In the analysis stage, accurately identifying vegetation species was challenging due to suboptimal image resolution. Furthermore, the lack of sufficient ground truth data made it difficult to validate segmentation results and assess accuracy.&rft.creator=Amarasingam, N., Sandino, J., Doshi, A., Randall, K., King, D., Blackman, E., Barthelemy, J., Bollard, B., Robinson, S. and Gonzalez, F. &rft.creator=AMARASINGAM, NARMILAN &rft.creator=SANDINO, JUAN &rft.creator=DOSHI, ASHRAY &rft.creator=RANDALL, KRYSTAL &rft.creator=KING, DIANA &rft.creator=BLACKMAN, ELKA &rft.creator=BARTHELEMY, JOHAN &rft.creator=BOLLARD, BARBARA &rft.creator=ROBINSON, SHARON &rft.creator=GONZALEZ, FELIPE &rft.date=2025&rft.coverage=westlimit=110.35767; southlimit=-66.4453; eastlimit=110.74219; northlimit=-66.23146&rft.coverage=westlimit=110.35767; southlimit=-66.4453; eastlimit=110.74219; northlimit=-66.23146&rft_rights=These data are not yet publicly available for download from the provided URL.&rft_rights=Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/legalcode&rft_rights=This data set conforms to the CCBY Attribution License (http://creativecommons.org/licenses/by/4.0/). Please follow instructions listed in the citation reference provided at http://data.aad.gov.au/aadc/metadata/citation.cfm?entry_id=AAS_4628_UAS_Robinson_Ridge_Lichen_Maps when using these data.&rft_rights=This metadata record is publicly available.&rft_subject=imageryBaseMapsEarthCover&rft_subject=biota&rft_subject=environment&rft_subject=EARTH SCIENCE > BIOLOGICAL CLASSIFICATION > PLANTS > MOSSES/HORNWORTS/LIVERWORTS&rft_subject=EARTH SCIENCE > BIOSPHERE > VEGETATION > VEGETATION INDEX&rft_subject=EARTH SCIENCE > SPECTRAL/ENGINEERING > VISIBLE WAVELENGTHS > VISIBLE IMAGERY&rft_subject=EARTH SCIENCE > BIOLOGICAL CLASSIFICATION > FUNGI > LICHENS&rft_subject=EARTH SCIENCE > DATA ANALYSIS AND VISUALIZATION > IMAGE PROCESSING&rft_subject=EARTH SCIENCE > BIOSPHERE > ECOSYSTEMS > TERRESTRIAL ECOSYSTEMS&rft_subject=USNEA SPP.&rft_subject=BLACK LICHEN&rft_subject=SNOW/ROCK/BARE GROUND&rft_subject=SEGMENTATION&rft_subject=MACHINE LEARNING&rft_subject=DEEP LEARNING&rft_subject=ROTARY WING UAVS&rft_subject=RGB IMAGING&rft_subject=MULTISPECTRAL ORTHOMOSAIC&rft_subject=MULTISPECTRAL IMAGING&rft_subject=SAEF&rft_subject=SECURING ANTARCTICA’S ENVIRONMENTAL FUTURE&rft_subject=ANTARCTIC TERRESTRIAL ECOSYSTEMS&rft_subject=HIGH-RESOLUTION MULTISPECTRAL DATA&rft_subject=ORTHOMOSAIC IMAGE ANALYSIS&rft_subject=EXTREME ENVIRONMENT REMOTE SENSING&rft_subject=DRONE-BASED ENVIRONMENTAL MONITORING&rft_subject=MOSS AND LICHEN DETECTION&rft_subject=CAMERAS&rft_subject=HRV > High Resolution Visible Imaging System&rft_subject=MULTI-SPECTRAL > Multispectral Camera&rft_subject=UAV > Unmanned Aerial Vehicle&rft_subject=AMD&rft_subject=AMD/AU&rft_subject=CEOS&rft_subject=CONTINENT > ANTARCTICA > ROBINSON RIDGE&rft_subject=GEOGRAPHIC REGION > POLAR&rft.type=dataset&rft.language=English Access the data

Access data via landing page
http://data.aad.gov.au...

Cite Saved to MyRDA Save to MyRDA

Licence & Rights:

Open Licence view details

Attribution 4.0 International (CC BY 4.0)
https://creativecommons.org/licenses/by/4.0/legalcode

These data are not yet publicly available for download from the provided URL.

This data set conforms to the CCBY Attribution License (http://creativecommons.org/licenses/by/4.0/). Please follow instructions listed in the citation reference provided at http://data.aad.gov.au/aadc/metadata/citation.cfm?entry_id=AAS_4628_UAS_Robinson_Ridge_Lichen_Maps when using these data.

This metadata record is publicly available.

Access:

Other

Full description

This is a child record, see the parent record AAS_4628_UAS for more information.

This work was completed as part of the program Securing Antarctica's Environmental Future (SAEF).

Dataset Components (Open Access)

1.    Output Segmentation Maps
This record includes vegetation segmentation outputs generated by standalone deep learning models (DeepLabv3+, FCN, U-Net) and an ensemble stacking approach using XGBoost. These models were used to classify vegetation communities in the study area. The results provide detailed segmentation maps that highlight the distribution of different vegetation types. The output segmentation maps are critical for understanding and analysing the vegetation communities in Robinson Ridge, Antarctica. These maps, generated through advanced machine learning techniques, support further research, validation, and applications in environmental monitoring. The inclusion of Vegetation Indices (VIs) helps in deriving additional insights into vegetation health and distribution.

Data Collection and Analysis
Data was collected in January 2023 using a BMR3.9RTK UAV developed by SaiDynamics Australia, equipped with a MicaSense Altum multispectral sensor and a Sony Alpha 5100 RGB camera. Flights at 70 m altitude yielded a ground sampling distance of 2.93 cm/pixel. A total of 2,814 images were collected, covering around 5.15 hectares.

Usage Notes
Refer to the readme.txt files in each record for further details on data formats.
Files:
-    .dat, .hdr, .tif – Segmentation maps and vegetation indices
-    readme.txt – Description and metadata for data usage and formats

Lineage

Progress Code: completed

Statement: During data collection, poor image quality in certain sections of the orthomosaic—caused by lighting conditions and snow—reduced the visual clarity necessary for reliable interpretation. In the analysis stage, accurately identifying vegetation species was challenging due to suboptimal image resolution. Furthermore, the lack of sufficient ground truth data made it difficult to validate segmentation results and assess accuracy.

Data time period: 2023-01-01 to 2023-01-15