MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641085383 A) filed by Sri Eshwar College Of Engineering on July 11, 2026, for An Ai-Driven Digital Twin Framework For Real-Time Landslide Susceptibility Prediction And Early Warning In Mountainous Regions.
Inventors include Dr. H. Anandakumar; Dr. R. Babitha Lincy; Ms. Minu Balakrishnan; and Mrs. K. Gowthami.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: In the mountainous region, destruction caused by landslide is one of the most serious natural hazards, in which notable loss of life, damage to infrastructure and environmental degradation occur. The traditional landslide monitoring methods are mostly based on periodic field surveys, or static susceptibility maps, which fail to provide continuous monitoring, dynamic risk assessment, and early warning in time in a rapidly changing environment. This invention presents an Internet of Things (IoT) based framework of a digital twin (DT) for real-time landslide susceptibility prediction and landslide early warning system that continuously synchronizes a digital twin of mountainous terrain by combining landslide IoT sensors, Geographic Information Systems (GIS), satellite and drone imagery, and meteorological observations. The Digital Twin dynamically models the terrain characteristics, soil conditions, drainage networks, vegetation and critical infrastructure, and it is constantly updating environmental parameters like rainfall, soil moisture, groundwater level, slope displacement, vibrations etc. Advanced Artificial Intelligence techniques, such as machine learning and deep learning models, utilize these multi-source datasets to forecast landslide susceptibility, failure probabilities, landslide risk categorization, and future landslide failure. The framework also includes hydrological and slope stability simulations, which are able to calculate several disasters and deliver early warnings in real-time via cell phones, mobile apps, dashboards, SMS and emergency notification systems. Automatic model calibration and better prediction accuracy can be achieved over time by continuous feedback from the field sensors. The proposed framework would improve disaster preparedness, minimise false alarms, be applicable to pre-planning evacuations and would give authorities reliable tools to support decisions to manage disaster risk sustainably and for resilient management of mountainous regions.
Disclaimer: Curated by HT Syndication.
