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

被引:5
|
作者
Sandino, Juan [1 ,2 ]
Bollard, Barbara [3 ,4 ]
Doshi, Ashray [3 ]
Randall, Krystal [3 ,4 ]
Barthelemy, Johan [3 ,5 ]
Robinson, Sharon A. [3 ,4 ]
Gonzalez, Felipe [1 ,2 ]
机构
[1] Queensland Univ Technol, Securing Antarct Environm Future, 2 George St, Brisbane, Qld 4000, Australia
[2] Queensland Univ Technol, QUT Ctr Robot, 2 George St, Brisbane, Qld 4000, Australia
[3] Univ Wollongong, Securing Antarcticas Environm Future, Northfields Ave, Wollongong, NSW 2522, Australia
[4] Univ Wollongong, Sch Earth Atmospher & Life Sci, Northfields Ave, Wollongong, NSW 2522, Australia
[5] NVIDIA, Santa Clara, CA 95051 USA
基金
澳大利亚研究理事会;
关键词
Antarctic Specially Protected Area (ASPA); data fusion; environmental monitoring; hyperspectral imaging (HSI); unmanned aerial system (UAS); unmanned aerial vehicle (UAV); CHLOROPHYLL CONCENTRATION; TERRESTRIAL VEGETATION; REFLECTANCE INDEX; UAV; ECOSYSTEMS; HEALTH; COLOR; LEAF; SOIL;
D O I
10.3390/rs15245658
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
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.
引用
收藏
页数:26
相关论文
共 50 条
  • [1] Minimal learning machine in hyperspectral imaging classification
    Hakola, Anna-Maria
    Polonen, Ilkka
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXVI, 2020, 11533
  • [2] Classification of skin cancer based on hyperspectral microscopic imaging and machine learning
    Qia, Meijie
    Liu, Yujie
    Li, Yanru
    Liu, Lixin
    Zhang, Zhoufeng
    SPIE-CLP CONFERENCE ON ADVANCED PHOTONICS 2022, 2023, 12601
  • [3] Metabolic classification of embryos and oocytes based on hyperspectral imaging and machine learning
    Ojosnegros, S.
    Parra, A.
    Denkova, D.
    Burgos-Artizzu, X.
    Oliver, I.
    Fraser, S. E.
    Chiang, H. J.
    Cutrale, F.
    Costa-Borges, N.
    Mestres, E.
    Acacio, M.
    Calderon, G.
    Rebollo, E.
    Veiga, A.
    Seriola, A.
    HUMAN REPRODUCTION, 2023, 38
  • [4] Honey botanical origin classification using hyperspectral imaging and machine learning
    Noviyanto, Ary
    Abdulla, Waleed H.
    JOURNAL OF FOOD ENGINEERING, 2020, 265
  • [5] Hyperspectral imaging for early identification of strawberry leaves diseases with machine learning and spectral fingerprint features
    Jiang, Qiyou
    Wu, Gangshan
    Tian, Chongfeng
    Li, Na
    Yang, Huan
    Bai, Yuhao
    Zhang, Baohua
    INFRARED PHYSICS & TECHNOLOGY, 2021, 118
  • [6] Ink classification in historical documents using hyperspectral imaging and machine learning methods
    Lopez-Baldomero, Ana Belen
    Buzzelli, Marco
    Moronta-Montero, Francisco
    Martinez-Domingo, Miguel angel
    Valero, Eva Maria
    SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, 2025, 335
  • [7] Multiclass Brain Tumor Classification Using Hyperspectral Imaging and Supervised Machine Learning
    Ruiz, Luisa
    Martin, Alberto
    Urbanos, Gemma
    Villanueva, Marta
    Sancho, Jaime
    Rosa, Gonzalo
    Villa, Manuel
    Chavarrias, Miguel
    Perez, Angel
    Juarez, Eduardo
    Lagares, Alfonso
    Sanz, Cesar
    2020 XXXV CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS), 2020,
  • [8] Hyperspectral imaging coupled with machine learning for classification of anthracnose infection on mango fruit
    Siripatrawan, Ubonrat
    Makino, Yoshio
    SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, 2024, 309
  • [9] Classification of peanut variety based on hyperspectral imaging and improved extreme learning machine
    Wang, Mengke
    Zhang, Hongrui
    Lv, Hongfei
    Liu, Chengye
    Xu, Jinhuan
    Li, Xiangdong
    CZECH JOURNAL OF FOOD SCIENCES, 2025,
  • [10] Facial skin colour classification using machine learning and hyperspectral imaging data
    Zhu, Wanshan
    Sang, Peng
    He, Yifan
    IET IMAGE PROCESSING, 2022, 16 (02) : 509 - 520