Automated Feature Extraction for Disaster Monitoring Using U-Net Architecture: Enhancing Real-Time Response and Recovery Through Deep Learning

Year 2026, Volume: 10 Issue: 2 , 476 - 483 , 01.05.2026

Sunitha Thankappan , Nazrin Salma S , Rajesh Govindan , Uma Devi Chandrasekar , Solairaju Jothi Arunachalam

https://izlik.org/JA62CW85XM

Abstract

Disaster monitoring and response are critical for lessening the effects that natural catastrophes have on the environment and populations, playing a vital role in disaster management, environmental protection, and long-term sustainable development. This research focuses on developing an automated feature extraction framework utilizing a U-Net architecture for segmenting disaster-affected areas from remote sensing images, specifically targeting floods, landslides, and wildfires. The proposed model is trained on a dataset of annotated remote sensing images and demonstrates high accuracy and robustness. The results prove that the model can successfully extract relevant features from remote sensing imagery, enabling timely and accurate identification of disaster-affected areas. The proposed single-stage semantic segmentation network achieves an accuracy of 97.3%, a recall of 95.5%, and an F1-score of 95.3, outperforming existing methods such as BRRNet, DRNet, and ENRU-Net. The use of the U-Net architecture is particularly motivated by its ability to capture both global contextual information and fine-grained spatial details, which are crucial for identifying disaster-affected regions in high-resolution remote sensing imagery. Furthermore, by leveraging transfer learning techniques, the dependency on large volumes of labeled data is significantly reduced, enhancing the practicality and scalability of the proposed approach. Overall, this framework supports intelligent disaster management strategies and contributes to Sustainable Cities by enabling rapid damage assessment, informed decision-making, and efficient resource allocation, thereby aligning with global goals for Climate Action and sustainable disaster resilience..

Keywords

Glaucoma Detection , Graph Neural Networks , Sustainable , Vision Transformer , Grad-CAM

References

• Horoz, Melek, and Ugur Algancı. "Determining the relationship between zoning plans and urban development using remote sensing methods: A case study of Ankara." Turkish Journal of Engineering 9.3 (2025): 591-598.
• Kumar, Amit, Vivek Kumar, and Abhay Bhadauria. "Real-Time Hybrid Machine Learning-Based Next-Generation Intrusion Detection System for Edge Computing Networks." Turkish Journal of Engineering 9.3 (2025): 600-611.
• Majid, Saima, Fayadh Alenezi, Sarfaraz Masood, Musheer Ahmad, Emine Selda Gündüz, and Kemal Polat. "Attention based CNN model for fire detection and localization in real-world images." Expert Systems with Applications 189 (2022): 116114.
• Li, Yu, Patrick Matgen, and Marco Chini. "Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks." International Journal of Applied Earth Observation and Geoinformation 139 (2025): 104524.
• Thanikodi, S. and Solairaju, J.A., 2026. Green Synthesis and Process Optimization of Zinc Oxide Nanoparticles Using Pseudomonas fluorescens: Taguchi–ANN-Based Evaluation of Physico-Chemical Parameters. Turkish Journal of Engineering, 10(1), pp.204-212.
• Roohi, Mohammad, Hamid Reza Ghafouri, and Seyed Mohammad Ashrafi. "Advancing flood disaster management: leveraging deep learning and remote sensing technologies." Acta Geophysica 73, no. 1 (2025): 557-575.
• Akhyar, Akhyar, Mohd Asyraf Zulkifley, Jaesung Lee, Taekyung Song, Jaeho Han, Chanhee Cho, Seunghyun Hyun, Youngdoo Son, and Byung-Woo Hong. "Deep artificial intelligence applications for natural disaster management systems: A methodological review." Ecological Indicators 163 (2024): 112067.
• Zhu, Xinyu, Zhihua Zhang, Yi He, Wei Wang, Shuwen Yang, and Yuhao Hou. "LandslideNet: A landslide semantic segmentation network based on single-temporal optical remote sensing images." Advances in Space Research 74, no. 10 (2024): 4616-4638.
• Alrayes, Fatma S., Saud S. Alotaibi, Khalid A. Alissa, Mashael Maashi, Areej Alhogail, Najm Alotaibi, Heba Mohsen, and Abdelwahed Motwakel. "Artificial intelligence-based secure communication and classification for drone-enabled emergency monitoring systems." Drones 6, no. 9 (2022): 222.
• Gnanasekaran, K., Rajesh, M., & Hariram, V. (2025). Optimizing abrasive water jet parameters for enhanced interactivity in metal-stacked hybrid fiber laminates. Turkish Journal of Engineering, 9(1), 28-36.
• Arunachalam, S.J., Saravanan, R. and Sathish, T., 2025. Effect of Nanoparticle in jute/kenaf/glass composite for interlaminar shear strength. Interactions, 246(1), p.31.
• Alakuş, D.O. and Türkoğlu, İ., 2025. Analysis of explosion images obtained with high-speed camera with image processing and prediction of explosion loads. Turkish Journal of Engineering, 9(3), pp.479-489.
• Zhou, Xunkuai, Bingxin Han, Li Li, Jie Chen, and Ben M. Chen. "DRNet: A Miniature and Resource-Efficient MAV Detector." IEEE Transactions on Instrumentation and Measurement (2025).
• Arunachalam, S.J. and Saravanan, R., 2024. Comprehensive Insights of Chemically Treated Jute/Kenaf/Glass Fiber with TiO2 nanoparticle using RSM optimization. J. Environ. Nanotechnol, 13(2), pp.21-30.
• Wang, Shengsheng, Xiaowei Hou, and Xin Zhao. "Automatic building extraction from high-resolution aerial imagery via fully convolutional encoder-decoder network with non-local block." IEEE Access 8 (2020): 7313-7322.