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.

As an important part of the wetland ecosystem, alpine wetland is not only one of the most important ecological water conservation areas in the Qinghai–Tibet Plateau region, but is also an effective regulator of the local climate. In this study, using three machine learning algorithms to extract wetland, we employ the landscape ecological index to quantitatively analyze the evolution of landscape patterns and grey correlation to analyze the driving factors of Zoige wetland landscape pattern change from 1995 to 2020. The following results were obtained. (1) The random forest algorithm (RF) performs best when dealing with high-dimensional data, and the accuracy of the decision tree algorithm (DT) is better. The performance of the RF and DT is better than that of the support vector machine algorithm. (2) The alpine wetland in the study area was degraded from 1995 to 2015, whereas wetland area began to increase after 2015. (3) The results of landscape analysis show the decrease in wetland area from 1995 to 2005 was mainly due to the fragmentation of larger patches into many small patches and loss of the original small patches, while the 2005 to 2015 decrease was caused by the loss of many middle patches and the decrease in large patches from the edge to the middle. The 2015 to 2020 increase is due to an increase in the number of smaller patches and recovery of original wetland area. (4) The grey correlation degree further shows that precipitation and evaporation are the main factors leading to the change in the landscape pattern of Zoige alpine wetland. The results are of great significance to the long-term monitoring of the Zoige wetland ecosystem.