Enhancing the performance of regional land cover mapping |
| |
| Institution: | 1. State-Key Lab of Nuclear Resources and Environment, East China Institute of Technology (ECIT), Nanchang, 330013 Jiangxi, China;2. ICARDA (International Center for Agricultural Research Center in the Dry Areas), Amman, Jordan;3. Litani River Authority, Beirut, Lebanon;4. Faculty of Sciences, East China Institute of Technology (ECIT), 330013, Nanchang, Jiangxi, China;1. Key Laboratory of Mineralogy and Metallogeny, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences, Guangzhou 510640, China;2. University of Chinese Academy of Sciences, Beijing 100049, China;3. Key Laboratory of Marginal Sea Geology, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China;4. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China;1. Anhui Province Key Laboratory of Wetland Ecosystem Protection and Restoration, School of Resources and Environmental Engineering, Anhui University, Hefei 230601, China;2. Environmental Futures Research Institute, School of Environment and Science, Griffith University, Brisbane, Queensland 4111, Australia;3. College of Forestry, Jiangxi Agricultural University, Nanchang 330045, China;4. GeneCology Research Centre, Faculty of Science, Health, Education and Engineering, University of the Sunshine Coast, Maroochydore DC, QLD 4558, Australia;5. School of Medical and Applied Sciences, Central Queensland University, Bundaberg, Queensland 4670, Australia;1. State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu 610059, China;2. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China;3. Seismological Bureau of Sichuan Province, Chengdu 610041, China;4. State Key Laboratory of Geological Processes and Mineral Resources, School of Earth Sciences, China University of Geosciences, Wuhan 430074, China;5. Sichuan Changning Natural Gas Development Co., Ltd, Chengdu 610000, China;1. Key Laboratory of Silviculture, Co-Innovation Center of Jiangxi Typical Trees Cultivation and Utilization, College of Forestry, Jiangxi Agricultural University, Zhimin Rd. 1101, Nanchang 330045, PR China;2. Jiangxi Provincial Engineering Research Center For Seed-Breeding and Utilization of Camphor Trees, School of Hydraulic and Ecological Engineering, Nanchang Institute of Technology, Nanchang 330099, PR China;3. Lushan Nature Reserve of Jiangxi (Lushan Mountain National Forest Ecological Station), Henan Rd. 600, Jiujiang 332900, PR China;4. Jiyang College, Zhejiang Agriculture and Forestry University, Zhuji, Zhejiang 311800, PR China;5. Department of Forestry and Environmental Conservation, Clemson University, Clemson, SC 29634, USA;1. Key Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China;2. University of Chinese Academy of Sciences, Beijing 100049, China |
| |
| Abstract: | Different pixel-based, object-based and subpixel-based methods such as time-series analysis, decision-tree, and different supervised approaches have been proposed to conduct land use/cover classification. However, despite their proven advantages in small dataset tests, their performance is variable and less satisfactory while dealing with large datasets, particularly, for regional-scale mapping with high resolution data due to the complexity and diversity in landscapes and land cover patterns, and the unacceptably long processing time. The objective of this paper is to demonstrate the comparatively highest performance of an operational approach based on integration of multisource information ensuring high mapping accuracy in large areas with acceptable processing time. The information used includes phenologically contrasted multiseasonal and multispectral bands, vegetation index, land surface temperature, and topographic features. The performance of different conventional and machine learning classifiers namely Malahanobis Distance (MD), Maximum Likelihood (ML), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs) and Random Forests (RFs) was compared using the same datasets in the same IDL (Interactive Data Language) environment. An Eastern Mediterranean area with complex landscape and steep climate gradients was selected to test and develop the operational approach. The results showed that SVMs and RFs classifiers produced most accurate mapping at local-scale (up to 96.85% in Overall Accuracy), but were very time-consuming in whole-scene classification (more than five days per scene) whereas ML fulfilled the task rapidly (about 10 min per scene) with satisfying accuracy (94.2–96.4%). Thus, the approach composed of integration of seasonally contrasted multisource data and sampling at subclass level followed by a ML classification is a suitable candidate to become an operational and effective regional land cover mapping method. |
| |
| Keywords: | Multisource data integration Phenological contrast Topographic features Separability Accuracy |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
