85% of U’khand dists, 45% of Himachal flood-prone: IIT Roorkee study
TNN / May 06, 2026, 23:05 (IST)
Researchers applied a deep learning model, CNN U-Net, to analyse flood susceptibility at a fine spatial resolution of 90 metres. The model incorporated 14 key factors, including elevation, slope, vegetation cover and water flow characteristics, to identify high-risk zones.