Abstract ID: 3.12014 | Accepted as Talk | Talk | TBA | TBA

Dharamshala is a major tourist destination and the fastest-growing urban center, situated in the picturesque Kangra Valley, Himachal Pradesh. In recent years, the region is experiencing rapid population growth demanding more infrastructural development, deforestation due to expansion of agricultural lands which significantly altering land use land cover (LULC). These changes disrupt slope stability and increase the likelihood of landslides occurrences. LULC changes are more dynamic factors among other causative factors and play a significant role in triggering landslides in geologically sensitive mountainous areas. Therefore, the study aims to examine and analyze the impact of LULC changes on landslide susceptibility in Dharamshala Region using remote sensing, Geographical Information System (GIS) and machine-learning techniques. The study will also assess the impact of landslide conditioning factors such as slope, aspect, lithology, vegetation cover, distance from settlements, distance from roads, and rainfall on landslide occurrences. Multi-temporal satellite imagery will be utilized to quantify changes in LULC classes. Cellular Automata-Artificial Neural Network (CA-ANN) model will be used to predict future LULC changes and landslide-prone areas. The findings of this study will highlight the need to incorporate LULC change assessment in landslide risk assessment and the potential use of machine learning models to enhance early warning systems in mountainous regions. The study will also provide insights to policymakers, planners, and stakeholders to focus on the need to monitor LULC changes to minimize its adverse impact on landslides in mountainous regions.