Munish Sood
Mandi
In a significant step towards disaster risk reduction in the Himalayan region, researchers at the Indian Institute of Technology (IIT) Mandi have developed a fully operational Landslide Early Warning System (LEWS) capable of providing real-time forecasts and location-specific alerts across the Indian Himalayan Region (IHR).
The system has been developed under the leadership of Prof. Dericks Praise Shukla of the School of Civil and Environmental Engineering, along with research scholars Ankit Singh and Nitesh Dhiman.
With climate change contributing to a rise in landslides across the globe, the Indian Himalayan Region remains one of the country’s most vulnerable areas, witnessing frequent slope failures that result in loss of lives and extensive damage to infrastructure and property. The newly developed LEWS is designed to address this challenge by forecasting landslide probabilities using terrain susceptibility data and real-time rainfall information.
According to Prof. Shukla, the system generates daily landslide forecasts at the onset of the monsoon through a web-based platform, enabling authorities and communities to identify high-risk areas in advance and undertake timely evacuation and disaster preparedness measures.
He said satellite-based early warning systems represent one of the most effective investments in disaster risk reduction by converting scientific data into actionable information. A region-wide forecasting platform, he added, can significantly improve preparedness, strengthen emergency response and enhance coordination among disaster management agencies during the monsoon season when landslide risks are at their peak.
Unlike most existing landslide warning systems in India, which are limited to specific regions, the IIT Mandi-developed LEWS covers the entire Indian Himalayan Region, making it one of the country’s most extensive operational landslide forecasting systems.
The research team adopted a multi-stage scientific approach to develop the system. Around 26,000 historical landslides from the Geological Survey of India database were analysed to prepare a landslide susceptibility map using ensemble machine learning models that combined multiple triggering factors.
Researchers then developed the Probability of Rainfall-Induced Landslides (P-RIL) model using data from the NASA Global Landslide Catalogue and seven rainfall parameters obtained from IMERG satellite datasets. The dynamic model continuously analyses rainfall recorded over the previous 15 days to estimate changing landslide risks.
The final daily forecast is generated by integrating the static susceptibility map with the dynamic rainfall model through probability analysis. To make the forecasts easier to interpret, risk levels are categorised using percentile-based classifications.
To ensure easy public access, the IIT Mandi team has also developed a Google Earth Engine-based web portal, allowing users to view landslide forecasts for the current day as well as the previous three days. The platform also enables users to download PDF bulletins and receive location-specific alerts through WhatsApp.
The researchers believe the operational warning system will significantly strengthen disaster preparedness and risk reduction efforts across the Himalayan region by providing timely, location-specific warnings that can help minimise casualties and reduce economic losses.
