IIT Delhi Introduces AI-Powered Tool for Efficient and Automated Landslide Extent Mapping

Researchers from IIT Delhi have developed ML-CASCADE, a cloud computing and machine learning tool that maps landslide extent using satellite data. Know details here

IIT Delhi Introduces AI-Powered Tool for Efficient and Automated Landslide Extent Mapping

Researchers from the Indian Institute of Technology (IIT) Delhi’s Civil Engineering Department have developed ML-CASCADE, a cloud computing and machine learning tool designed to map landslide extent using satellite data. This user-friendly, publicly accessible tool (Tool link: https://hydrosense.users.earthengine.app/view/ml-cascade) requires just two inputs - an approximate date and location of a landslide event and can map complex landslide clusters in under 5 minutes, while simpler landslides are processed within 2 minutes.

This speed and accuracy are crucial for post-disaster damage assessment. The model is trained on vast datasets, including satellite imagery, terrain, vegetation, and soil data. A research paper by PhD Scholar Nirdesh Kumar Sharma and Prof. Manabendra Saharia of the HydroSense Lab at the Civil Engineering Department has been published in the prestigious ‘Landslides’ journal by the International Consortium on Landslides (ICL).

Prof. Manabendra Saharia, Civil Engineering Department, IIT Delhi said, “Traditionally, landslides have been mapped by manually digitizing over satellite imagery, which is costly, inaccurate, and time-consuming. Field surveys and geological data collection cannot be done in large and remote areas. Existing simple models developed using the thresholds of vegetation indices fail in areas with minimal vegetation. Machine learning on geospatial data offers an unprecedented opportunity to overcome the drawbacks of index-based methods and integrate multiple diverse datasets to map landslides with high accuracy.

Simple Tool For Disaster Managers

To ensure ease of use for disaster managers, the user interface of ML-CASCADE was designed with input from both technical and non-technical users. The final output is available for download in multiple image formats, making it easy to share or integrate into GIS for further analysis. Powered by Google Earth Engine, the tool eliminates the need for data downloads and leverages parallel processing to generate results in minutes - tasks that would otherwise take hours on a local computer.

The tool has been validated on thousands of landslides, with case studies from major events like the 2017 Kotrupi landslide in the Himalayas and the 2018 Kodagu landslide in the Western Ghats. Since many landslides occur in remote areas, mapping them is often time-consuming and requires expertise. IIT Delhi researchers are now using the tool to create a national historical landslide inventory, which will aid in developing early warning systems. The tool’s novel architecture also holds potential for future applications in mapping floods, deforestation, sand mining, and other environmental issues.

Read More

• IIT Delhi Launches Research Communications Award to Foster Effective Communication Among PhD Candidates
• IIT Delhi Partners with DRDO to Launch ABHED Lightweight Bulletproof Jackets