The unique characteristics of desert vegetation, such as different leaf morphology, discrete canopy structures, sparse and uneven distribution, etc., pose significant challenges for remote sensing-based estimation of fractional vegetation cover (FVC). The Unmanned Aerial Vehicle (UAV) system can accurately distinguish vegetation patches, extract weak vegetation signals, and navigate through complex terrain, making it suitable for applications in small-scale FVC extraction. In this study, we selected the floodplain fan with Caragana korshinskii Kom as the constructive species in Hatengtaohai National Nature Reserve, Bayannur, Inner Mongolia, China, as our study area. We investigated the remote sensing extraction method of desert sparse vegetation cover by placing samples across three gradients: the top, middle, and edge of the fan. We then acquired UAV multispectral images; evaluated the applicability of various vegetation indices (VIs) using methods such as supervised classification, linear regression models, and machine learning; and explored the feasibility and stability of multiple machine learning models in this region. Our results indicate the following: (1) We discovered that the multispectral vegetation index is superior to the visible vegetation index and more suitable for FVC extraction in vegetation-sparse desert regions. (2) By comparing five machine learning regression models, it was found that the XGBoost and KNN models exhibited relatively lower estimation performance in the study area. The spatial distribution of plots appeared to influence the stability of the SVM model when estimating fractional vegetation cover (FVC). In contrast, the RF and LASSO models demonstrated robust stability across both training and testing datasets. Notably, the RF model achieved the best inversion performance (R² = 0.876, RMSE = 0.020, MAE = 0.016), indicating that RF is one of the most suitable models for retrieving FVC in naturally sparse desert vegetation. This study provides a valuable contribution to the limited existing research on remote sensing-based estimation of FVC and characterization of spatial heterogeneity in small-scale desert sparse vegetation ecosystems dominated by a single species.

Arid inland saline lakes are key components of basin ecosystems. As the largest saline lake in Xinjiang and a critical ecological barrier in northwest China, Ebinur Lake’s area dynamics are vital to regional sustainable development. This study integrates Landsat imagery (1992–2024) with meteorological and socio-economic data to investigate optimal water extraction methods, spatio-temporal lake area variations, and driving mechanisms. Multiple methods were employed, including water index comparison, Mann–Kendall test, Pearson correlation, and ridge regression. Results show that: (1) the Normalized Difference Water Index (NDWI) maintains high, stable classification accuracy across years and months, making it suitable for long-term monitoring; (2) from 1992 to 2024, lake area demonstrates a significant fluctuating downward trend without abrupt change points, indicating continuous degradation. During the growing season (April–October), it first decreases and then increases, with larger early-season areas, minima in August and September, coinciding with peak agricultural irrigation demand; (3) regarding driving mechanisms, socio-economic factors dominate (approximately 70%), while meteorological factors play a weakly regulatory role (about 30%). Population growth and increased water consumption are the primary drivers, with obvious seasonal differences. Meteorological changes, socio-economic development, and ecological measures jointly influence lake area. Although extreme events (e.g., anomalous precipitation) induce short-term fluctuations, they do not alter the long-term degradation trend dominated by human activities. This study provides methodological support for long-term monitoring of arid saline lakes and scientific evidence for ecological conservation and water resource management in the Ebinur Lake Basin.