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.

Understanding the driving mechanisms of vegetation development is critical for maintaining terrestrial ecosystem function in mountain areas, especially under the background of climate change. The Qinba Mountains (QBM), a critical north–south transition zone in China, is an environmentally fragile area that is vulnerable to climate change. It is essential to characterize how its ecological environment has changed. Currently, such a characterization remains unclear in the spatiotemporal patterns of the nonlinear effects and interactions between environmental factors and vegetation changes in the QBM. Here, we utilized the Normalized Difference Vegetation Index (NDVI), obtained from Google Earth Engine (GEE) platform, as an indicator of terrestrial ecosystem conditions. Then, we measured the spatiotemporal heterogeneity for vegetation variation in the QBM from 2003 to 2018. Specifically, the Geodetector method, a new geographically statistical method without linear assumptions, was employed to detect the interaction between vegetation and environmental driving factors. The results indicated that there is a trend of a general increase in vegetation growth amplitude (the average NDVI increased from 0.810 to 0.858). The areas with an NDVI greater than 0.8 are mainly distributed in the Qinling Mountains and the Daba Mountains, which account for more than 76.39% of the QBM area. For the entire region, the global Moran’s index of the NDVI is greater than 0.95, indicating that vegetation is highly concentrated in the spatial domain. The Geodetector identified that landform type was the primary factor in controlling vegetation changes, contributing 24.19% to the total variation, while the explanatory powers of the aridity index and the wetness index for vegetation changes were 22.49% and 21.47%, respectively. Furthermore, the interaction effects between any two factors outperformed the influence of a single environmental variable. The interaction between air temperature and the aridity index was the most significant element, contributing to 47.10% of the vegetation variation. These findings can not only improve our understanding in the interactive effects of environmental forces on vegetation change, but also be a valuable reference for ecosystem management in the QBM area, such as ecological conservation planning and the assessment of ecosystem functions.

The upper Yellow River basin over the Tibetan Plateau (TP) is an important ecological barrier in northwestern China. Effective LULC products that enable the monitoring of changes in regional ecosystem types are of great importance for their environmental protection and macro-control. Here, we combined an 18-class LULC classification scheme based on ecosystem types with Sentinel-2 imagery, the Google Earth Engine (GEE) platform, and the random forest method to present new LULC products with a spatial resolution of 10 m in 2018 and 2020 for the upper Yellow River Basin over the TP and conducted monitoring of changes in ecosystem types. The results indicated that: (1) In 2018 and 2020, the overall accuracy (OA) of LULC maps ranged between 87.45% and 93.02%. (2) Grassland was the main LULC first-degree class in the research area, followed by wetland and water bodies and barren land. For the LULC second-degree class, the main LULC was grassland, followed by broadleaf shrub and marsh. (3) In the first-degree class of changes in ecosystem types, the largest area of progressive succession (positive) was grassland–shrubland (451.13 km²), whereas the largest area of retrogressive succession (negative) was grassland–barren (395.91 km²). In the second-degree class, the largest areas of progressive succession (positive) were grassland–broadleaf shrub (344.68 km²) and desert land–grassland (302.02 km²), whereas the largest areas of retrogressive succession (negative) were broadleaf shrubland–grassland (309.08 km²) and grassland–bare rock (193.89 km²). The northern and southwestern parts of the study area showed a trend towards positive succession, whereas the south-central Huangnan, northeastern Gannan, and central Aba Prefectures showed signs of retrogressive succession in their changes in ecosystem types. The purpose of this study was to provide basis data for basin-scale ecosystem monitoring and analysis with more detailed categories and reliable accuracy.

Above-ground biomass (AGB) is a key indicator for studying grassland productivity and evaluating carbon sequestration capacity; it is also a key area of interest in hyperspectral ecological remote sensing. In this study, we use data from a typical alpine meadow in the Qinghai–Tibet Plateau during the main growing season (July–September), compare the results of various feature selection algorithms to extract an optimal subset of spectral variables, and use machine learning methods and data mining techniques to build an AGB prediction model and realize the optimal inversion of above-ground grassland biomass. The results show that the Lasso and RFE_SVM band filtering machine learning models can effectively select the global optimal feature and improve the prediction effect of the model. The analysis also compares the support vector machine (SVM), least squares regression boosting (LSB), and Gaussian process regression (GPR) AGB inversion models; our findings show that the results of the three models are similar, with the GPR machine learning model achieving the best outcomes. In addition, through the analysis of different data combinations, it is found that the accuracy of AGB inversion can be significantly improved by combining the spectral characteristics with the growing season. Finally, by constructing a machine learning interpretable model to analyze the specific role of features, it was found that the same band plays different roles in different records, and the related results can provide a scientific basis for the research of grassland resource monitoring and estimation.

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.

Nondestructive and accurate estimating of the forage nitrogen–phosphorus (N:P) ratio is conducive to the real-time diagnosis of nutrient limitation and the formulation of a management scheme during the growth and development of forage. New-generation high-resolution remote sensors equipped with strategic red-edge wavebands offer opportunities and challenges for estimating and mapping forage N:P ratio in support of the sustainable utilization of alpine grassland resources. This study aims to detect the forage N:P ratio as an ecological indicator of grassland nutrient content by employing Sentinel-2 multispectral instrument (MSI) data and a random forest (RF) algorithm. The results showed that the estimation accuracy (R²) of the forage N:P ratio model established by combining the optimized spectral bands and vegetation indices (VIs) is 0.49 and 0.59 in the vigorous growth period (July) and the senescing period (November) of forage, respectively. Moreover, Sentinel-2 MSI B9 and B12 bands contributed greatly to the estimation of the forage N:P ratio, and the VIs (RECI2) constructed by B5 and B8A bands performed well in the estimation of the forage N:P ratio. Overall, it is promising to map the spatial distribution of the forage N:P ratio in alpine grassland using Sentinel-2 MSI data at regional scales. This study will be potentially beneficial in implementing precise positioning of vegetation nutrient deficiency and scientific fertilization management of grassland.