Project Title: Integrated Machine Learning and Remote Sensing for Real-Time Predictive Modeling of rainfall-Induced Landslides in Kamand Valley.
1. Project Details
Sanction Date: 09.08.2024
Project Category MG
Year 2024-2025
Project Duration 3 Year
BTA : WRM
Project Site/ State/ Districts/ Villages Covered:

District Mandi, Himachal Pradesh

Organization/ Implementation Agency: Indian Institute of Technology Mandi, Himachal Pradesh
Project Partners: S.No. Name
1 Intiot Services Pvt. Ltd. (IIOTS) IIT Mandi, VPO Kamand, District Mandi, HP, India - 175005
2 District Disaster Mandi, District Mandi, HP, India-175001
Lead Proponent:

Dr. Varun Dutt
School of Computing and Electrical Engineering Indian Institute of Technology-Mandi (IIT-Mandi) Mandi, Himachal Pradesh

Project Brief Description: Because of the Kamand Valley's vulnerability to landslides caused by precipitation, which pose serious dangers to people's lives, property, and the environment in the Mandi District of Himachal Pradesh, the planned project is extremely important. By creating an integrated system for the real-time prediction and monitoring of landslides, this program seeks to improve the mitigation of landslide risk and help global and national efforts to reduce the risk of disasters. Sophisticated Machine Learning (ML) models will be used to do this, together with satellite-based remote sensing and low-cost Landslide Monitoring Systems (LMSs). Enhancement of Landslide Monitoring and Warning Systems (LMWS): Several low-cost, locally made monitoring and warning systems are to be put into place as part of this project. These systems will incorporate soil movement data and real-time weather alerts, which are essential for precise and prompt landslide prediction. Furthermore, the prediction models will be improved by using satellite-derived landslide velocity profiles, which offer a thorough understanding of possible landslide behaviors. Advanced ML-Based Landslide Prediction: By utilizing cutting-edge ML methods, we want to increase the accuracy and promptness of landslide predictions caused by precipitation. The research will make use of a dataset that contains climatic variables, soil properties, and movement metrics gathered from the region. Our models' ability to estimate power will be improved with the addition of satellite data on landslide movements, resulting in the timely release of early warnings. Integration of Satellite-Based Remote Sensing: By including velocity profiles from satellite photography into our prediction models, we can get a more precise understanding of how landslides behave over time. This integration makes it possible to analyze landslides more broadly and makes it easier to identify precursory motions that occur before significant landslide occurrences. Community Involvement and Resilience Building: Through awareness-raising and educational initiatives, the project places a strong emphasis on community involvement. By teaching locals about landslide hazards and preparedness techniques and teaching them how to properly interpret alerts and warnings from the LMWS, these programs seek to increase community resilience and decrease vulnerability. Contribution to Scientific Knowledge and Technological Innovation: By utilizing cutting-edge technology and ML methods, this research is expected to make a substantial contribution to our understanding of the mechanics of landslides and prediction modeling. It advances the goals of technical advancement and national independence. In conclusion, this project not only tackles a pressing issue pertaining to the environment and public safety, but it also establishes a standard for fusing cutting-edge scientific techniques with useful technical applications. The project has the potential to provide a strong early warning system against rainfall-induced landslides, an informed local community that can respond to disasters effectively, and a model for comparable projects in other landslide-prone areas of the world.
Beneficiaries/ Stakeholders:

• Local Residents:Primary beneficiaries who will experience increased safety and reduced risk of property damage due to improved landslide predictions and early warning systems.
• Local Government and Disaster Management Agencies: Stakeholders responsible for public safety and disaster response. They will utilize the project's data and systems for better disaster preparedness and response strategies.
• Farmers and Agricultural Workers: Direct beneficiaries who rely on the land for their livelihoods. They will benefit from reduced disruption due to landslides, which can damage crops and soil fertility.
• Educational Institutions: Beneficiaries in terms of research opportunities and educational enhancements. Schools and universities can incorporate project data into academic programs and research projects.
• Tourism Industry Operators: Stakeholders who benefit from the enhanced safety and infrastructure stability that attract more tourists to the area.
• Infrastructure Developers and Urban Planners: Beneficiaries who use the project's geotechnical data for safer and more sustainable infrastructure development in the region.
• Non-Governmental Organizations (NGOs): Stakeholders focused on community development and disaster risk reduction. They can leverage project outcomes to enhance their initiatives.
• Researchers and Scientists: Beneficiaries who gain access to valuable data for studying landslide dynamics and related fields, contributing to broader scientific understanding.
• Policy Makers: Stakeholders who can use the insights and data provided by the project to formulate better policies on land use, environmental protection, and disaster management.

Activity Chart (For 3 years)
2. Financial Details
Total Grants (in Rs.) Rs. 1,00,00,000 (Rupees: One crore only)
1st Installment (in Rs.) : Rs. 47,73,840 (Rupees: Forty seven lakh seventy three thousand eight hundred forty only)
3. Project Objectives, Deliverables and Monitoring Indicators
Project Objectives Quantifiable Deliverables Monitoring Indicators
• Identifying rainfall-induced Landslide-prone Areas through Advanced Geospatial Analysis
• Development and Deployment of Affordable Landslide Monitoring and Early Warning Systems
• Construction of Comprehensive ML Models
• Real-Time Deployment of Refined ML Models
• Execution of Awareness and Educational Workshops.
• Development and implementation of sophisticated ML models that to enhance the accuracy and timeliness of landslide predictions.
• Web interface to landslide monitoring and real time prediction.
• An Android App giving weather and landslide predictions also supported by API, Google Maps.
• Development and distribution of a scalable prototype or finalized version of the LMSs and software for adaptation and use in other vulnerable regions of the Himalayas.
• Compilation and detailed analysis of extensive datasets gathered from the deployed LMSs.
• Execution of a minimum of 10 community workshops aimed at enhancing local knowledge and preparedness for landslide risks.
• Publication of at least 3 peer-reviewed articles in high-impact journals, contributing significantly to the global body of knowledge in geohazard assessment.
• Training of at least 50 individuals, including project staff, disaster response personnel, and local community leaders, to enhance regional competencies in landslide risk management and response strategies.
•No. of Analytical/ Assessment Reports: Geospatial Analysis Report on rainfall-induced Landslide Prone Areas along with Corrective/ Preventive/ Mitigation Measures (Nos.);
• No. of Landslide Early Warning System (EWS) developed and deployed (Nos.);
• No. of Models developed (Nos.);
• No. of Database/ Datasets (Nos.);
• No. of functional IT Applications: RT Web Interface, Android App., etc. (Nos.);
• No. of Technological Models/ Prototypes (Nos.);
• Scope of Patent(s) and/ or Technological/ Industrial Transfer.
• No. of Knowledge Products: Research articles, Book Chapters, Popular articles, etc. (Nos.);
• Stakeholders Capacity Built: Trainings and Workshops along with beneficiaries (Nos.);
S.No. Name (Sanctioned) Salary (Sanctioned)
1. 1 RA-3 @ 67000/- +HRA 9% pm
2. 02 SRF @ 42000/- +HRA 9% pm
S.No. Name of Equipment (Sanctioned) Cost (in INR)
1. High Performance Equipment (Workstations, Laptops, Tablets, Computers). 8,98,760/-
Website Hits:
Unique Visitor:
Last Update: 02.06.2025
Contact Us |   Designed, Developed & hosted by NMHS-PMU