Land Use/Land Cover Changes and Their Driving Factors in the Northeastern Tibetan Plateau Based on Geographical Detectors and Google Earth Engine: A Case Study in Gannan Prefecture

Abstract

As an important production base for livestock and a unique ecological zone in China, the northeast Tibetan Plateau has experienced dramatic land use/land cover (LULC) changes with increasing human activities and continuous climate change. However, extensive cloud cover limits the ability of optical remote sensing satellites to monitor accurately LULC changes in this area. To overcome this problem in LULC mapping in the Ganan Prefecture, 2000–2018, we used the dense time stacking of multi-temporal Landsat images and random forest algorithm based on the Google Earth Engine (GEE) platform. The dynamic trends of LULC changes were analyzed, and geographical detectors quantitatively evaluated the key driving factors of these changes. The results showed that (1) the overall classification accuracy varied between 89.14% and 91.41%, and the kappa values were greater than 86.55%, indicating that the classification results were reliably accurate. (2) The major LULC types in the study area were grassland and forest, and their area accounted for 50% and 25%, respectively. During the study period, the grassland area decreased, while the area of forest land and construction land increased to varying degrees. The land-use intensity presents multi-level intensity, and it was higher in the northeast than that in the southwest. (3) Elevation and population density were the major driving factors of LULC changes, and economic development has also significantly affected LULC. These findings revealed the main factors driving LULC changes in Gannan Prefecture and provided a reference for assisting in the development of sustainable land management and ecological protection policy decisions.

A Long-Term Ecological Vulnerability Analysis of the Tibetan Region of Natural Conditions and Ecological Protection Programs

“…Studies in Europe and coastal areas have mainly focused on the sensitivity of the ecosystem and its response to climate change and pattern change over time [25][26][27][28][29][30], which measure ecosystem tolerance and vegetation response predictions to climate anomalies. In mainland areas, research on ecological vulnerability is more concentrated on land use patterns [31][32][33], desertification soil problems [24,[34][35][36], and human disturbances [37][38][39][40][41]. Typically, vulnerable zones with different topological characteristics are studied [38][39][40] to determine the determinants of vulnerability.…”

“…These studies have inaccurate analytical units, a small range of study periods, influences from single-type indicators, and inadequate evidence on determinant analysis [40][41][42][43][44][45]. Though numerous studies have investigated ecological health and ecosecurity and assessed the ecological risk of the Tibetan Plateau, more research is still needed on an ecological vulnerability analysis with an ecological protection project policy in the Tibetan Plateau [1,15,31,35,45,49].…”

Long-term changes of forest biomass and its driving factors in karst area, Guizhou, China

“…The larger the value is, the stronger the explanatory power of factor X on the spatial heterogeneity of Y is, and vice versa. 49,50 Results and analysis…”

Monitoring and Landscape Dynamic Analysis of Alpine Wetland Area Based on Multiple Algorithms: A Case Study of Zoige Plateau

“…Most of the articles published in the relevant study area have been combined with the Land-Use and Land-Cover Change (LUCC) classification system, and the features were divided into seven types [ 49 , 50 ]. Considering the small area of farmland and building-land types in the study area, we combined them into artificial land.…”

“…Considering the balance of samples, the number of samples is set according to the area proportion of local types [ 37 , 51 ]. The generated samples of 4500 points are “real” and are used for the classification and subsequent classification accuracy evaluation according to the 7:3 ratio [ 50 , 52 ] of training samples to test samples. We selected four kinds of accuracy evaluation indexes used in many studies to evaluate accuracy: overall accuracy, the Kappa coefficient, producer accuracy and user accuracy [ 52 , 53 ].…”