The Zoige Plateau is typical of alpine wetland ecosystems worldwide, which play a key role in regulating global climate and ecological balance. Due to the influence of global climate change and intense human activities, the stability and sustainability of the ecosystems associated with the alpine marsh wetlands are facing enormous threats. It is important to establish a precise risk assessment method to evaluate the risks to alpine wetlands ecosystems, and then to understand the influencing factors of ecological risk. However, the multi-index evaluation method of ecological risk in the Zoige region is overly focused on marsh wetlands, and the smallest units of assessment are relatively large. Although recently developed landscape ecological risk assessment (ERA) methods can address the above limitations, the final directionality of the evaluation results is not clear. In this work, we used the landscape ERA method based on land use and land cover changes (LUCC) to evaluate the ecological risks to an alpine wetland ecosystem from a spatial pixel scale (5 km × 5 km). Furthermore, the boosted regression tree (BRT) model was adopted to quantitatively analyze the impact factors of ecological risk. The results show the following: (1) From 1990 to 2016, the land use and land cover (LULC) types in the study area changed markedly. In particular, the deep marshes and aeolian sediments, and whereas construction land areas changed dramatically, the alpine grassland changed relatively slowly. (2) The ecological risk in the study area increased and was dominated by regions with higher and moderate risk levels. Meanwhile, these areas showed notable spatio-temporal changes, significant spatial correlation, and a high degree of spatial aggregation. (3) The topographic distribution, climate changes and human activities influenced the stability of the study area. Elevation (23.4%) was the most important factor for ecological risk, followed by temperature (16.2%). Precipitation and GDP were also seen to be adverse factors affecting ecological risk, at levels of 13.0% and 12.1%, respectively. The aim of this study was to provide more precise and specific support for defining conservation objectives, and ecological management in alpine wetland ecosystems.

Effective and accurate assessment of grassland above-ground biomass (AGB) especially via remote sensing (RS), is crucial for forage-livestock balance and ecological environment protection of alpine grasslands. Because of complexity and extensive spatial distribution of natural grassland resources, the RS estimation models based on moderate resolution imaging spectroradiometer (MODIS) data exhibited low accuracy and poor stability. In this study, various methods for estimating the AGB of alpine grassland vegetation using MODIS vegetation indices were evaluated by combining with meteorology, soil, topography geography and in situ measured AGB data (during grassland growing season from 2011 to 2016) in Gannan region. Results show that (1) five out of ten factors (elevation, slope, aspect, topographic position, temperature, precipitation and the concentration of clay and sand in the soil) exert significant effects on grassland AGB, with R2 0.04~0.39, and RMSE 859.68 kg/ha ~ 1075.09 kg/ha, respectively; (2) the accuracy and stability of AGB estimation model can be improved by constructing multivariate models, especially using multivariate non-parameter models; (3) the optimum estimation model is constructed on the basis of random forest algorithm (RF). Compared with univariate/multivariate parameter models, RMSE of RF model decreased 26.45 % - 44.27 %. Meanwhile, RF models can explain 89.41 % variation in AGB . This study presented a more suitable RS inversion model integrated MODIS vegetation indices and other effect factors. Besides, the accuracy of alpine grassland AGB estimation based on MODIS data were greatly improved. Thus, our study provides a scientific basis for effective and accurate estimating alpine grassland AGB.

Grassland height is one of the main factors used to evaluate grassland conditions. However, the retrieval of natural grassland height at the regional scale by remote sensing data and conventional statistical models will result in large errors, especially in the heterogeneous alpine grassland of the Tibetan Plateau (TP). In this article, we aimed to construct a model based on multiple variables (biogeographical, meteorological, and Moderate Resolution Imaging Spectroradiometer (MODIS) product) using a random forest (RF) algorithm to predict the spatial distribution of grassland height in the TP from 2003 to 2017. The results show the following conditions. 1) Seven variables (elevation, slope, aspect, enhanced vegetation index, reflectance in band seven of MODIS (B7), annual accumulated temperature (≥0 °C), and annual precipitation) that were selected by recursive feature elimination from 11 variables have high importance in the RF model. The final model exhibits good performance, with mean R ² and root mean squared error values of 0.51 and 6.15 cm, respectively, which were determined via 10-fold crossvalidation. 2) The mean grassland height (2003-2017) predicted by the RF model ranges from 5 to 10 cm in most areas of the TP, and the mean height is 10 cm. The grassland height in the east and southeast of the TP is significantly higher than that in other areas. 3) This article achieves a relatively accurate estimation of grassland height over a large spatial scale at 500-m spatial resolution, which plays an important role in accurately estimating aboveground biomass and evapotranspiration over grassland.