A Flood Segmentation Model Enhanced by Residual Squeeze-and-Excitation (R-SE) Blocks

Year 2026, Volume: 14 Issue: 1, 17 - 25, 31.01.2026

Emre Güçlü , İlhan Aydın , Erhan Akın

https://doi.org/10.21541/apjess.1715068

Abstract

Timely flood detection and segmentation play an important role in disaster management and recovery processes by enabling effective interventions. In this study, a segmentation model with ResNet-50 infrastructure is proposed, which provides high accuracy. Our proposed model achieves high segmentation accuracy on the Flood dataset by reducing computational cost compared to standard convolutions and by using depth-separable convolutions. In order to make learning more flexible and reduce overfitting, our model uses the PReLU (Parametric ReLU) activation function, which allows learning from negative values. Squeeze-and-Excitation (SE) blocks, which strengthen feature learning by highlighting important information, are also integrated into the model. In addition, Feature Enhancement Blocks contribute to the production of more accurate and detailed segmentation maps. The effectiveness of the model is verified using the Flood dataset, where it is evaluated with various measurement metrics. The results show that the proposed model outperforms popular segmentation architectures such as FCN, SegNet and U-Net. In particular, the average IoU value obtained is 85.37%, demonstrating the high overall accuracy of the model. This work provides a valuable contribution to the field of flood detection and provides a solid foundation for future systems that aim to improve segmentation accuracy for real-time disaster response.

Keywords

Flood Segmentation , Deep Learning , Disaster Management , Segmentation

Project Number

123E669

Thanks

This study was supported by the Scientific and Technological Research Council of Türkiye (TÜBİTAK) under project number 123E669.

References

• Change, I. P. O. C. (2007). Climate change 2007: the physical science basis. Agenda, 6(07), 333.
• United Nations Office for Disaster Risk Reduction (UNDRR). (2020). Global Assessment Report on Disaster Risk Reduction 2020. https://www.undrr.org/publication/global-assessment-report-disaster-risk-reduction-2020
• E. Guclu, I. Aydin, and E. Akin, "Development of vision-based autonomous UAV for railway tracking," in Proc. 2021 Int. Conf. Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Sep. 2021, pp. 120–125.
• D. R. Hartawan, T. W. Purboyo, and C. Setianingsih, "Disaster victims detection system using convolutional neural network (CNN) method," in Proc. 2019 IEEE Int. Conf. Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), Jul. 2019, pp. 105–111.
• S. N. K. B. Amit and Y. Aoki, "Disaster detection from aerial imagery with convolutional neural network," in Proc. 2017 Int. Electronics Symp. on Knowledge Creation and Intelligent Computing (IES-KCIC), Sep. 2017, pp. 239–245.
• J. Doshi, S. Basu, and G. Pang, "From satellite imagery to disaster insights," arXiv preprint arXiv:1812.07033, 2018. [Online]. Available: https://arxiv.org/abs/1812.07033
• D. B. Valdez and R. A. G. Godmalin, "A deep learning approach of recognizing natural disasters on images using convolutional neural network and transfer learning," in Proc. Int. Conf. Artificial Intelligence and Its Applications, Dec. 2021, pp. 1–7.
• R. G. C. J. Kapilaratne and S. Kaneta, "Rapid flood mapping from high resolution satellite images using convolutional neural networks," in Proc. 18th Annu. Meeting of the Asia Oceania Geosciences Society (AOGS 2021), 2022, pp. 156–158.
• N. R. Leach, P. Popien, M. C. Goodman, and B. Tellman, "Leveraging convolutional neural networks for semantic segmentation of global floods with PlanetScope imagery," in Proc. IGARSS 2022 - IEEE Int. Geosci. and Remote Sens. Symp., Jul. 2022, pp. 314–317.
• V. Barkhade, S. Mahakarkar, R. Agrawal, C. Dhule, and N. C. Morris, "Flood extent mapping with unmanned aerial vehicles data using deep convolutional neural network," in Proc. 2023 Int. Conf. Sustainable Computing and Smart Systems (ICSCSS), Jun. 2023, pp. 466–471.
• Z. Zhang, Y. Li, Q. Liu, and X. Liu, "High resolution remote sensing water image segmentation based on dual branch network," in Proc. 2022 IEEE Int. Conf. Dependable, Autonomic and Secure Computing (DASC), Pervasive Intelligence and Computing (PiCom), Cloud and Big Data Computing (CBDCom), Cyber Science and Technology Congress (CyberSciTech), Sep. 2022, pp. 1–6.
• A. Gebrehiwot and L. Hashemi-Beni, "3D inundation mapping: A comparison between deep learning image classification and geomorphic flood index approaches," Frontiers in Remote Sensing, vol. 3, p. 868104, 2022.
• P. Jain, B. Schoen-Phelan, and R. Ross, "Automatic flood detection in Sentinel-2 images using deep convolutional neural networks," in Proc. 35th Annu. ACM Symp. on Applied Computing, Mar. 2020, pp. 617–623.
• R. G. C. J. Kapilaratne and S. Kaneta, "Towards an automated flood area extraction from high resolution satellite images," Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 43, pp. 97–104, 2020.
• E. Portalés-Julià, G. Mateo-García, C. Purcell, and L. Gómez-Chova, "Global flood extent segmentation in optical satellite images," Sci. Rep., vol. 13, no. 1, p. 20316, 2023.
• N. R. Leach, P. Popien, M. C. Goodman, and B. Tellman, "Leveraging convolutional neural networks for semantic segmentation of global floods with PlanetScope imagery," in Proc. IGARSS 2022 - IEEE Int. Geosci. and Remote Sens. Symp., Jul. 2022, pp. 314–317.
• R. M. De la Cruz, N. T. Olfindo Jr, M. M. Felicen, N. J. B. Borlongan, J. K. L. Difuntorum, and J. J. S. Marciano Jr, "Near-realtime flood detection from multi-temporal Sentinel radar images using artificial intelligence," Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 43, pp. 1663–1670, 2020.
• M. Zaffaroni and C. Rossi, "Water segmentation with deep learning models for flood detection and monitoring," Int. J. Inf. Syst. for Crisis Response and Management, pp. 24–27, 2020.
• R. J. Pally and S. Samadi, "Application of image processing and convolutional neural networks for flood image classification and semantic segmentation," Environ. Model. Softw., vol. 148, p. 105285, 2022.
• B. Basnyat, N. Roy, and A. Gangopadhyay, "Flood detection using semantic segmentation and multimodal data fusion," in Proc. 2021 IEEE Int. Conf. on Pervasive Computing and Communications Workshops (PerCom Workshops), Mar. 2021, pp. 135–140.
• A. Gebrehiwot, L. Hashemi-Beni, G. Thompson, P. Kordjamshidi, and T. E. Langan, "Deep convolutional neural network for flood extent mapping using unmanned aerial vehicles data," Sensors, vol. 19, no. 7, p. 1486, 2019.
• J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7132–7141.
• M. F. Karim, K. Sharma, and N. R. Barman, "Flood Area Segmentation [Data set]," Kaggle, 2022. [Online]. Available: https://doi.org/10.34740/KAGGLE/DSV/4732950
• J. Long, E. Shelhamer, T. Darrell, and U. C. Berkeley, "Fully convolutional networks for semantic segmentation," arXiv preprint arXiv:1411.4038, 2014. [Online]. Available: https://arxiv.org/abs/1411.4038
• V. Badrinarayanan, A. Kendall, and R. Cipolla, "SegNet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, 2017.
• O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in Proc. 18th Int. Conf. Medical Image Comput. and Computer-Assisted Intervention (MICCAI), Munich, Germany, Oct. 2015, pp. 234–241, Springer.
• P. Akiva, M. Purri, K. Dana, B. Tellman, and T. Anderson, "H2O-Net: Self-supervised flood segmentation via adversarial domain adaptation and label refinement," in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2021, pp. 111–122.
• Z. Zhang, P. Angelov, E. Soares, N. Longepe, and P. P. Mathieu, "An interpretable deep semantic segmentation method for earth observation," in Proc. 2022 IEEE 11th Int. Conf. on Intelligent Systems (IS), Oct. 2022, pp. 1–8.
• K. Iselborn, M. Stricker, T. Miyamoto, M. Nuske, and A. Dengel, "On the importance of feature representation for flood mapping using classical machine learning approaches," arXiv preprint arXiv:2303.00691, 2023. [Online]. Available: https://arxiv.org/abs/2303.00691
• R. Yadav, A. Nascetti, H. Azizpour, and Y. Ban, "Unsupervised flood detection on SAR time series," arXiv preprint arXiv:2212.03675, 2022. [Online]. Available: https://arxiv.org/abs/2212.03675