A Regionalized Study on the Spatial-Temporal Changes of Grassland Cover in the Three-River Headwaters Region from 2000 to 2016

Naijing Liu, Yaping Yang, Ling Yao and Xiafang Yue
Additional contact information
Naijing Liu: School of Geography and Tourism, Shaanxi Normal University, Xi’an 710119, China
Yaping Yang: State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Beijing 100101, China
Ling Yao: State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Beijing 100101, China
Xiafang Yue: State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Beijing 100101, China

Sustainability, 2018, vol. 10, issue 10, 1-24

Abstract: The Three-River Headwaters Region (TRHR) is located in the interior of the Qinghai-Tibetan Plateau, which is a typical research area in East Asia and is of fragile environment. This paper studied the characteristics of grassland cover changes in the TRHR between 2000 and 2016 using methods of area division (AD) based on natural conditions and tabulate area (TA) dependent on Moderate-resolution Imaging Spectroradiometer (MODIS) 44B product. Further investigations were conducted on some of the typical areas to determine the characteristics of the changes and discuss the driving factors behind these changes. Classification and Regression Trees (CART), Random Forest (RF), Bayesian (BAYE), and Support Vector Machine (SVM) Machine Learning (ML) methods were employed to evaluate the correlation between grassland cover changes and corresponding variables. The overall trend for grassland cover in the TRHR towards recovery that rose 0.91% during the 17-year study period. The results showed that: (1) The change in grassland cover was more divisive in similar elevation and temperature conditions when the precipitation was stronger. The higher the temperature was, the more significant the rise of grassland cover was in comparable elevation and precipitation conditions. (2) There was a distinct decline and high change standard deviation of grassland cover in some divided areas, and strong correlations were found between grassland cover change and aspect, slope, or elevation in these areas. (3) The study methods of AD and TA achieved enhancing performance in interpretation of grassland cover changes in the broad and high elevation variation areas. (4) RF and CART methods showed higher stability and accuracy in application of grassland cover change study in TRHR among the four ML methods utilized in this study.

Keywords: MOD44B; grassland cover; regionalization; Machine Learning (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2018
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2071-1050/10/10/3539/pdf (application/pdf)
https://www.mdpi.com/2071-1050/10/10/3539/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:10:y:2018:i:10:p:3539-:d:173304

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().