Remote sensing is crucial for monitoring decadal-scale snow cover dynamics in response to climate change across mountainous ecosystems. This study analyzes spatiotemporal snow cover trends and their driving factors using satellite observations, topographic data, and climate variables. MODIS snow product (MOD10A1) data from 2000 to 2022 were used to assess snow cover changes across 69 High Mountain Ecosystems (HME) in the Middle East. We analyzed data from January to April and October to December to capture seasonal snow cover dynamics. A linear regression method detected significant trends in the Normalized Difference Snow Index (NDSI), while a pixel-based Random Forest (RF) regression model assessed environmental drivers influencing NDSI variability. Results show that northern and northwestern humid regions generally experienced increasing NDSI, whereas central and southern arid regions exhibited a decline, highlighting spatial and temporal heterogeneity in snow cover trends. Temperature and precipitation change significantly influenced NDSI patterns, suggesting climate variability plays a critical role in snow cover disturbances. RF analysis identified mean annual temperature, precipitation changes, and mean annual precipitation as the top three drivers of NDSI variability. Future research should focus on the impact of extreme weather events on snow cover. Additionally, refining the methodology with higher-resolution data across diverse climate zones could enhance predictive accuracy.