Indian Institute of Technology, Guwahati (IIT Guwahati) develops framework to predict glacial lake formation

Key facts

• Researchers from the Indian Institute of Technology, Guwahati (IIT Guwahati) have developed an advanced predictive framework to identify areas where new glacial lakes are likely to form in the Eastern Himalayas.
• The framework is designed to address the risk of Glacial Lake Outburst Floods (GLOFs) caused by rapid glacier melting and expansion due to climate change.
• The probabilistic model utilizes high-resolution satellite imagery and digital elevation data to account for topographical features such as bowl-shaped depressions and valleys.
• The research team evaluated multiple predictive methods, including Logistic Regression, Artificial Neural Networks (ANN), and Bayesian Neural Networks (BNN).
• The Bayesian Neural Network (BNN) approach was identified as the most accurate method for predicting potential glacial lake formation sites.
• The study identified 492 specific locations in the Eastern Himalayas where new glacial lakes are likely to form.
• The research findings have been published in the international journal Scientific Reports.