Year-end Sale % OFF 
Abstract
Land cover mapping in mountainous areas is a notoriously challenging task due to the rugged terrain and high spatial heterogeneity of land surfaces as well as the frequent cloud contamination of satellite imagery. Taking Southwestern China (a typical mountainous region) as an example, this paper established a new HC-MMK approach (Hierarchical Classification based on Multi-source and Multi-temporal data and geo-Knowledge), which was especially designed for land cover mapping in mountainous areas. This approach was taken in order to generate a 30 m-resolution land cover product in Southwestern China in 2010 (hereinafter referred to as CLC-SW2010). The multi-temporal native HJ (HuanJing, small satellite constellation for disaster and environmental monitoring) CCD (Charge-Coupled Device) images, Landsat TM (Thematic Mapper) images and topographical data (including elevation, aspect, slope, etc.) were taken as the main input data sources. Hierarchical classification tree construction and a five-step knowledge-based interactive quality control were the major components of this proposed approach. The CLC-SW2010 product contained six primary categories and 38 secondary categories, which covered about 2.33 million km2 (accounting for about a quarter of the land area of China). The accuracies of primary and secondary categories for CLC-SW2010 reached 95.09% and 87.14%, respectively, which were assessed independently by a third-party group. This product has so far been used to estimate the terrestrial carbon stocks and assess the quality of the ecological environments. The proposed HC-MMK approach could be used not only in mountainous areas, but also for plains, hills and other regions. Meanwhile, this study could also be used as a reference for other land cover mapping projects over large areas or even the entire globe.
Highlights
Land cover data is essential for a variety of studies such as global change [1,2], ecological environments [3,4] and resource management
This paper mainly introduced the proposed HC-MMK approach and the 30 m-resolution
The multi-temporal native HJ-CCD images, Landsat TM images and topographical data were taken as the main input data in this study
Summary
Land cover data is essential for a variety of studies such as global change [1,2], ecological environments [3,4] and resource management. It plays a critical role in improving the performance of hydrological, ecological, biogeochemical and atmospheric models [5]. A series of land cover products at global and regional scales, such as the IGBP-DIS global. Land cover products at 30 m-resolution over large regions or even the globe are highlighted, since most significant human activities on the land surface can be captured at this scale [11,14]. In mountainous areas, severe challenges arise for land cover mapping, such as the rugged terrain, the high spatial heterogeneity of land surfaces and the frequent cloud contamination of satellite imagery [16], having an enormous impact on scientific research and applications related to land cover over mountainous areas
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
