Spatial application of Random Forest models for fine-scale coastal vegetation classification using object based analysis of aerial orthophoto and DEM data |
| |
| Institution: | 1. Section for Biodiversity & Conservation, Department of Bioscience, Aarhus University, Grenaavej 12-14, Kalø, 8410 Rønde, Denmark;2. Section for Ecoinformatics & Biodiversity, Department of Bioscience, Aarhus University, Ny Munkegade 114, 8000 Aarhus C, Denmark;1. Joint Remote Sensing Research Program, School of Earth and Environmental Sciences, University of Queensland, St. Lucia, QLD 4072, Australia;2. Remote Sensing Centre, Queensland Department of Environment and Science GPO Box 2454, Brisbane, QLD 4001, Australia;1. Key Laboratory of Desert and Desertification, Northwest Institute of Eco–Environment and Resources, Chinese Academy of Sciences, Donggang West Road 320, Lanzhou, Gansu 730000, China;2. University of Chinese Academy of Sciences, No.19(A) Yuquan Road, Shijingshan District, Beijing 100049, China;3. College of Geography and Environmental Science, Northwest Normal University, Lanzhou, Gansu 730070, China;1. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, 4888 Shengbei Street, Changchun, Jilin 130102, PR China;2. University of Chinese Academy of Sciences, Beijing, 100049,PR China;3. Department of Natural Resources Science, University of Rhode Island, Kingston, RI 02881, USA;4. Tangshan Normal University156 Jianshe Street, Tangshan, 063000, PR China;1. School of Agriculture, Earth and Environmental Sciences, Pietermaritzburg Campus, University of KwaZulu-Natal, Scottsville P/Bag X01, Pietermaritzburg 3209, South Africa;2. Department of Agronomy, Faculty of Agriculture, University of Khartoum, Khartoum North 13314, Sudan;1. School of Earth, Atmospheric and Life Sciences, The University of Wollongong, NSW, 2522, Australia;2. NSW National Parks and Wildlife Service, Unit G, 84 Crown Street, Wollongong, NSW, 2500, Australia;3. School of Life and Environmental Sciences, Deakin University, Warrnambool, VIC, 3280, Australia;4. 12 Hyam Place, Jamberoo, NSW, 2533, Australia;5. School of Computing and Information Technology, University of Wollongong, New South Wales, NSW, 2522, Australia |
| |
| Abstract: | High spatial resolution mapping of natural resources is much needed for monitoring and management of species, habitats and landscapes. Generally, detailed surveillance has been conducted as fieldwork, numerical analysis of satellite images or manual interpretation of aerial images, but methods of object-based image analysis (OBIA) and machine learning have recently produced promising examples of automated classifications of aerial imagery. The spatial application potential of such models is however still questionable since the transferability has rarely been evaluated.We investigated the potential of mosaic aerial orthophoto red, green and blue (RGB)/near infrared (NIR) imagery and digital elevation model (DEM) data for mapping very fine-scale vegetation structure in semi-natural terrestrial coastal areas in Denmark. The Random Forest (RF) algorithm, with a wide range of object-derived image and DEM variables, was applied for classification of vegetation structure types using two hierarchical levels of complexity. Models were constructed and validated by cross-validation using three scenarios: (1) training and validation data without spatial separation, (2) training and validation data spatially separated within sites, and (3) training and validation data spatially separated between different sites.Without spatial separation of training and validation data, high classification accuracies of coastal structures of 92.1% and 91.8% were achieved on coarse and fine thematic levels, respectively. When models were applied to spatially separated observations within sites classification accuracies dropped to 85.8% accuracy at the coarse thematic level, and 81.9% at the fine thematic level. When the models were applied to observations from other sites than those trained upon the ability to discriminate vegetation structures was low, with 69.0% and 54.2% accuracy at the coarse and fine thematic levels, respectively.Evaluating classification models with different degrees of spatial correlation between training and validation data was shown to give highly different prediction accuracies, thereby highlighting model transferability and application potential. Aerial image and DEM-based RF models had low transferability to new areas due to lack of representation of aerial image, landscape and vegetation variation in training data. They do, however, show promise at local scale for supporting conservation and management with vegetation mappings of high spatial and thematic detail based on low-cost image data. |
| |
| Keywords: | Habitat structure Object-based image analysis Machine learning Aerial orthophoto imagery Model transferability |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
