New Delhi: As per the latest updates, the researchers of the Indian Institute of Technology (IIT), Mandi have recently developed a new algorithm through which Artificial Intelligence and Machine Learning (AI & ML) can improve the accuracy of prediction for natural hazards.
As per IIT Mandi, the algorithm can address the issue of data imbalance for mapping landslide susceptibility, which depicts the possibility of landslides occurring in a specific area. This result was published by the associate professor and former research scholar of IIT Mandi.
The landslide susceptibility mapping can determine the chance of a landslide occurring in a given place on the basis of the slope, elevation, geology, soil type, distance from faults, rivers and faults, and other historical landslide data.
This algorithm is developed by Dr Dericks Praise Shukla, Associate Professor, at the School of Civil and Environmental Engineering, IIT Mandi, and Dr Sharad Kumar Gupta, Former Research Scholar at IIT Mandi, currently working at Tel Aviv University (Israel).
Informing about this initiative, Dericks Praise Shukla said, “This new ML algorithm highlights the importance of data balancing in ML models and demonstrates the potential for new technologies to drive significant advancements in the field.”
He further added that this initiative by the researchers will open up new avenues in the field of LSM and other geohazard mapping and management. This development can be used in other phenomena such as floods, avalanches, extreme weather events, rock glaciers and permafrost.
It will further minimize the risks posed to human safety and property caused due to natural hazards. The algorithm uses EasyEnsemble and BalanceCascade under-sampling techniques to address the issue of imbalanced data in landslide mapping.
Talking about this development, the researchers shared that the data for this study was collected from the landslides that occurred in the Mandakini River Basin in northwest Himalaya, Uttarakhand, India, between 2004 and 2017.
The database was used to train and analyze the model. The final result shows that this initiative can be used to significantly improve the accuracy of the LSM in comparison to traditional machine learning techniques such as support vector machines and artificial neural networks.
Also Read:
Subscribe to Collegedunia to get the latest educational news and updates –
