ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Share
Publications Copernicus
Download
Citation
Share
Articles | Volume X-5/W2-2025
https://doi.org/10.5194/isprs-annals-X-5-W2-2025-613-2025
https://doi.org/10.5194/isprs-annals-X-5-W2-2025-613-2025
19 Dec 2025
 | 19 Dec 2025

Spatio-Temporal Analysis of Climate Variability on Vegetation and Land Use Using LISS-IV Satellite Imagery (2013–2025) with AI/ML-Based Change Detection in the Western Himalayan Region

Agyeya Shukla, Aaryan Shukla, Danny Savla, Navin Kumar P. J., and Yogita Shukla

Keywords: Vegetation Cover Change, High Altitude Himalayas, Climate Variability, LISS-IV Satellite Imagery

Abstract. Mountainous regions such as the Western Himalayas shows strong indications of climate change impact through drastic shifts in high-altitude vegetation patterns. Vegetation plays crucial roles in moderating sunlight absorption and heat exchange with land and helps maintain natural ecosystemic equilibrium. Studying vegetation changes over time across diverse locations remains pretty crucial to understand the climate system dynamics of the region. This study examines the vegetation change dynamics in high altitude Garhwal region above 3000 meters in Uttarakhand, India, and leverages satellite imagery quite extensively, examining shifts in vegetation and land cover changes between 2013 and 2025. High-resolution LISS-IV satellite images provide multispectral bands in green, red and NIR regions making it quite suitable for vegetation change analysis. NDVI data measuring vegetation health and proliferation over years with considerable accuracy can be derived from LISS-IV sensor. Results show a stark rise in vegetation mostly in areas 3000-4500 meters above sea level, with marked growth observed in these regions. Many areas exhibited remarkably low NDVI values below 0.15 in 2013, but by 2025 values had substantially improved to between 0.35 and 0.45. NDVI increases are very prominent above 4500 meters, showing extensive greening in these altitudinal areas, possibly because of rising temperatures and human activities. The study utilized modern techniques like artificial intelligence and machine learning alongside remote sensing and GIS to better understand these changes in vegetation that are occurring rapidly. AI/ML-based classification methods captured subtle changes in vegetation patterns, effectively over a period of time with considerable precision and high accuracy. The growing necessity for sustainable environmental management strategies protecting fragile mountain environments amidst rapidly changing climatic conditions becomes increasingly evident after this study. 

Share