Modelling tree canopy cover and evaluating the driving factors based on remotely sensed data and machine learning |
| |
| Affiliation: | 1. Bursa Technical University, Forest Faculty, Landscape Architecture Department, Bursa, Turkey;2. Cukurova University, Landscape Architecture Department, Remote Sensing and GIS Lab, 01330 Adana, Turkey;3. School of Arts, Media and Engineering (AME), Arizona State University, 85281 Tempe, AZ, United States;1. Department of Earth System Science, Institute for Global Change Studies, Ministry of Education Ecological Field Station for East Asian Migratory Birds, Tsinghua University, Beijing 100084, PR China;2. Research Center of Urban Forest National Forestry and Grassland Administration, Chinese Academy of Forestry, Beijing 100091, PR China;3. The College of Forestry, Beijing Forestry University, Beijing 100083, PR China;4. Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110016, PR China;1. Graduate School of Environmental Studies, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, the Republic of Korea;2. Department of Landscape Architecture and Rural Systems Engineering, College of Agriculture and Life Sciences, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, the Republic of Korea;3. Department of Landscape Architecture and Rural Systems Engineering in College of Agriculture and Life Science, Integrated Major in Smart City Global Convergence, Research Institute of Agriculture Life Science, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, the Republic of Korea;1. Cartography & GIS Research Group, Department of Geography, Vrije Universiteit Brussel, 1050 Ixelles, Belgium;2. Cosmopolis Centre for Urban Research, Department of Geography, Vrije Universiteit Brussel, 1050 Ixelles, Belgium;3. Building, Architecture, & Town Planning (BATir) Department, Université Libre de Bruxelles, 1050 Ixelles, Belgium;1. Faculty of Forestry, University of British Columbia, 2424 Main Mall, Vancouver, BC, Canada V6T 1Z4;2. North Carolina State Extension and Union County Planning Department, 500 N. Main St., Monroe, NC 28112, United States;3. College of Natural Resources, University of Wisconsin – Stevens Point, 800 Reserve St., Stevens Point, WI 54481, United States;4. Department of Environmental Science and Studies Department, DePaul University, 1110 West Belden Ave, Chicago, IL 60614, United States;1. Instituto Multidisciplinario de Biología Vegetal (IMBIV), CONICET-Universidad Nacional de Córdoba (UNC), Av. Vélez Sarsfield 1611, X5016GCA Córdoba, Argentina;2. Department of Ecology, Faculty of Environmental Sciences, Czech University of Life Sciences Prague, Kamýcká 129. Suchdol, Prague 16500, Czech Republic;3. IES Landau, Institute for Environmental Sciences, University of Koblenz-Landau, Fortstraße 7, Landau 76829, Germany;4. Instituto de Investigaciones Biológicas y Tecnológicas (IIBYT)-CONICET, Centro de Investigaciones Entomológicas de Córdoba (CIEC), Facultad de Ciencias Exactas, Físicas y Naturales, Universidad Nacional de Córdoba, Ciudad Universitaria, Córdoba Capital, Córdoba, Argentina |
| |
| Abstract: | Quantifying urban tree cover is important to ensure sustainable urban ecosystem. This study calculates urban percent tree cover (PTC) for Bursa city, Turkey from Sentinel-2 data and evaluates the driving factors of PTC using an Artificial Neural Network-Multi Layer Perception (ANN-MLP) approach. For the PTC calculation, a Regression Tree (RT) analysis was performed using several vegetation indices (NDVI, LAI, fCOVER, MSAVI2, and MCARI) to improve accuracy. Socio-economic, topographic, and biophysical variables were incorporated into the ANN-MLP approach to evaluate the factors that drive urban PTC. A PTC prediction map was generated with an accuracy of 0.95 and a coefficient of determination of 0.87. The ANN-MLP training process yielded a correlation coefficient value of 0.71 and an R-square of 0.82 was achieved between the predicted ANN-MLP and observed tree cover maps. A priority tree cover map was generated considering statistical relationships between the factors and the ANN-MLP prediction map in addition to visual interpretations at the urban scale. Results demonstrate that, unlike other urban forms, PTC has a statistically negative relationship with the gross dwelling density (R2 =0.31). Topographic variables including slope and DEM were positively correlated with PTC with the R2 value of 0.80 and 0.72 respectively. The integration of remote sensing data with vegetation indices and driving factors yielded accurate prediction for identifying and evaluating the variability in the urban PTC. |
| |
| Keywords: | Urban Green Percent tree cover Regression Tree Artificial Neural Network |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
