Mr. G. Ravi Kumar,S. Pavan Kalyan, S. L. Sri Harshitha, P. Sai Charan, CH. Jnana Sowmya 03 03 Accurate and timely identification of floodaffected regions is critical for disaster response emergency resource allocation and damage assessment This paper proposes a deep learningbased flood region segmentation system using an enhanced SegNet encoderdecoder architecture adapted for multisource remote sensing image analysis The proposed model is augmented with skip connections attention gates and multiscale input processing to improve flood boundary delineation accuracy The system achieves a mean IoU of 873 for flood region segmentation on the Copernicus Emergency Management Service dataset outperforming baseline SegNet UNet and FCN models The framework produces pixelwise flood maps within seconds supporting rapid disaster response workflows with strong generalization across diverse geographic environments and flood event types Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026