PhD Scholar Nirdesh Sharma’s landslide susceptibility publication covered in EOS Landslide Blog, The Hindu, Shaashtra, and Times of India
- Post by: hydrosenseadmin
- January 5, 2024
- No Comment
The Hindu | The Times of India | EOS Landslide Blog
Releasing the Indian Landslide Susceptibility Map (ILSM) at 100 meter spatial resolution.
– Visualization Tool: https://hydrosense.users.earthengine.app/view/ilsm
– Dataset: https://zenodo.org/doi/10.5281/zenodo.10085271
– Publication: https://www.sciencedirect.com/science/article/pii/S0341816223007440?via%3Dihub
– Lead: Nirdesh Kumar Sharma, PhD scholar
We are releasing India’s first national-scale landslide susceptibility map at 100 meter scale. India suffers heavy losses every year, accounting for 8% of global landslide fatalities. We based the map on a model incorporating 16 landslide conditioning factors such as height, slope, soil composition, road distance, river proximity, vegetation cover, precipitation. The model is developed using a historical landslide inventory of more than 1,50,000 events. We found that Sikkim and Uttarakhand have over 50% of area in the ‘very high susceptibility’ zone, in addition to identifying new landslide-prone zones in the eastern ghats that were not reported previously. We used an Ensemble Machine Learning approach, where results of multiple machine learning models are combined to enhance the overall accuracy. We used oversampling (SVMSMOTE) and undersampling (one-sided selection) to create a representative database.