ML-CASCADE

A real-time, open-source system for fast and accurate landslide mapping using Sentinel-2 imagery and minimal user input.
About ML-CASCADE

ML-CASCADE is an open-source geospatial mapping system developed to enable rapid and reliable landslide extent detection immediately after landslide events.

The platform is designed to address the operational challenges of traditional landslide mapping, which often rely on time-intensive field surveys or manual interpretation of satellite imagery.

Using pre- and post-event Sentinel-2 imagery, along with terrain information and spectral indices, ML-CASCADE allows users to generate accurate landslide extent maps with minimal manual input.

The system is capable of mapping both simple and complex landslide clusters within minutes, making it suitable for near-real-time disaster response and post-event assessment. By combining speed, accuracy, and ease of use, ML-CASCADE provides a practical and operational tool for disaster management agencies, researchers, and regional authorities involved in landslide risk management.

Open Video Guide

Explore Our Delivered Projects

Amrit Sarovar Observatory

A centralized digital observatory enabling real-time tracking of India’s largest water rejuvenation mission covering 69,000+ ponds with AI-driven detection and monitoring.

Read More

Indian Landslide Susceptibility Map (ILSM)

India’s first machine learning–based landslide susceptibility map, delivering probabilistic risk estimates at 100 m resolution across the entire country.

Read More