Scientists at IIT Mandi have developed a fully operational Landslide Early Warning System (LEWS) for the Indian Himalayan Region (IHR), aiming to improve disaster preparedness as climate change continues to increase the frequency of landslides across the region.

The research was led by Prof. Dericks Praise Shukla from the School of Civil and Environmental Engineering at IIT Mandi, along with research scholars Mr. Ankit Singh and Mr. Nitesh Dhiman.

The Indian Himalayan Region is among the most landslide-prone areas in the country, with frequent slope failures causing significant loss of lives and property, especially during the monsoon. The newly developed LEWS has been designed to forecast landslide risks using real-time rainfall data and topographical susceptibility, allowing authorities to take preventive measures before disasters occur.

Explaining the significance of the system, Prof. Dericks Praise Shukla said:

"At the very onset of the monsoon, our Landslide Early Warning System (LEWS) provides daily landslide forecasts through a web-based application. The system is designed to help identify high-risk areas in advance, enabling authorities and communities to undertake timely evacuation and disaster preparedness measures."

He further added that satellite-based early warning systems are among the most effective investments in disaster risk reduction, as they convert scientific data into timely and actionable decisions. According to him, a region-wide forecasting platform like LEWS can strengthen disaster preparedness, improve response time, and enhance coordination among disaster management agencies, particularly during the monsoon season.

Unlike many existing landslide warning systems in India that are limited to smaller geographical areas, IIT Mandi's LEWS covers the entire Indian Himalayan Region, making it one of the country's most extensive landslide forecasting systems.

The research team developed the system through a multi-stage process. They first mapped landslide susceptibility using nearly 26,000 landslide records from the Geological Survey of India (GSI) database. The team then combined multiple landslide-triggering factors with ensemble machine learning models to improve prediction accuracy.

To estimate rainfall-induced landslide risks, the researchers developed the P-RIL (Probability of Rainfall-Induced Landslides) model using data from the NASA Global Landslide Catalogue and seven rainfall parameters obtained from IMERG satellite datasets. Since the model analyses rainfall data from the previous 15 days, it can dynamically adapt to changing weather conditions.

The final daily landslide forecast is generated by combining the static susceptibility map with the dynamic P-RIL model through probability analysis. The results are presented in percentile-based risk categories, making the forecasts easier for users to understand.

To make the system easily accessible, the IIT Mandi team has also developed a Google Earth Engine (GEE)-based web portal. The platform allows users to view landslide forecasts for the current day and the previous three days, download forecast bulletins in PDF format, and receive WhatsApp alerts for selected locations.

According to the researchers, the operational Landslide Early Warning System will play an important role in disaster preparedness and risk reduction across the Indian Himalayan Region by providing timely, location-specific warnings that can help reduce both human and economic losses.