The Indian Institute of Technology Mandi (IIT Mandi) researchers has invented a new algorithm using Artificial Intelligence and Machine Learning (AI & ML) that could enhance the precision of prediction for natural hazards.

Former research scholar IIT Mandi, Dr. Sharad Kumar Gupta, currently working at Tel Aviv University (Israel), and Associate Professor, School of Civil and Environmental Engineering, IIT Mandi, Dr. Dericks Praise Shukla, developed the algorithm.

The algorithm can tackle the challenge of data imbalance for landslide vulnerability mapping representing the possibility of landslide occurrences in a given location. The results of their invention have been published in the journal: Landslides.

Landslides are recurring natural hazard in mountainous regions across the world that causes substantial losses of life and property. In order to estimate these risks, it is essential to determine areas that are susceptible to landslides. (LSM)- Landslide Susceptibility Mapping reveals the likelihood of a landslide happening in a specific location on the basis of causative factors such as slope, soil type, distance from faults, geology, rivers and faults, elevation, and historical landslide data.

Artificial Intelligence is becoming essential for predicting natural disasters such as landslides. They can detect events in real-time, deliver situational awareness, envision extreme events, create risk maps, and support decision-making.

Machine Learning is a subfield of AI that allows computers to learn and enhance from experience without being explicitly programmed. It depends on algorithms that can make predictions or decisions, analyse data, and identify patterns, much like human intelligence.

Dr. Shukla and his team have developed a new algorithm that crushes the problem of data imbalance for training the algorithm. It uses two under-sampling techniques, EasyEnsemble and BalanceCascade, in order to handle the issue of imbalanced data in landslide mapping.