Enhancing Flood Area Segmentation in Remote Sensing Images Using Hybrid Attention Mechanism on DeepLabV3+ with ResNet-50 Backbone

Annisa Syifaul  Ummah; Esti  Suryani; Herdito Ibnu  Dewangkoro

doi:10.52436/1.jutif.2026.7.3.5523

Authors

Annisa Syifaul Ummah Department of Informatics, Universitas Sebelas Maret, Indonesia
Esti Suryani Department of Data Science, Universitas Sebelas Maret, Indonesia
Herdito Ibnu Dewangkoro Department of Informatics, Universitas Sebelas Maret, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.3.5523

Keywords:

DeepLabV3 , Flood Segmentation, Hybrid Attention Mechanism, Remote Sensing, ResNet-50, Semantic Segmentation

Abstract

Flooding is caused by climate change and urbanization, so rapid and accurate monitoring is essential in supporting emergency response. However, flood segmentation still faces challenges in dense vegetation. This study aims to improve and analyze the performance of the Hybrid Attention Mechanism in the form of Point-wise spatial attention (PSA) and Squeeze-and-Excitation Block (SE Block) in the DeepLabV3+ architecture with the ResNet-50 backbone. The methods used include collecting a dataset of 600 training and 63 validation, data augmentation, model development and Hybrid Attention Mechanism design, hyperparameter optimization, ablation study, and performance evaluation. The ablation results obtained show the best performance with accuracy of 0.9624, F1-score of 0.9618, IoU (Non-Flood) of 0.9323, IoU (Flood) of 0.9208, and mIoU of 0.9265, surpassing previous studies that used Modified U-Net in detecting floods in dense vegetation. This research contributes to the development of a flood segmentation model based on a hybrid attention mechanism, which is more effective in detecting flooded areas in densely vegetated regions.

Downloads

Download data is not yet available.

References

P. Akiva, M. Purri, K. Dana, B. Tellman, and T. Anderson, “H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement,” 2021.

N. A. Muhadi, A. F. Abdullah, S. K. Bejo, M. R. Mahadi, and A. Mijic, “Image Segmentation Methods for Flood Monitoring System,” Water 2020, Vol. 12, Page 1825, vol. 12, no. 6, p. 1825, Jun. 2020, doi: 10.3390/W12061825.

Mawardi Isal, “121 Orang Tewas Akibat Banjir Bandang di Texas, 170 Lainnya Hilang,” Detik News, Jakarta, 10 Juli 2025.

I. A. Hadimlioglu and S. A. King, “Geo-Information Visualization of Flooding Using Adaptive Spatial Resolution”, doi: 10.3390/ijgi8050204.

G. Antzoulatos et al., “Flood Hazard and Risk Mapping by Applying an Explainable Machine Learning Framework Using Satellite Imagery and GIS Data,” Sustainability 2022, Vol. 14, Page 3251, vol. 14, no. 6, p. 3251, Mar. 2022, doi: 10.3390/SU14063251.

L. Hashemi-Beni and A. A. Gebrehiwot, “Flood Extent Mapping: An Integrated Method Using Deep Learning and Region Growing Using UAV Optical Data,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 14, pp. 2127–2135, 2021, doi: 10.1109/JSTARS.2021.3051873.

W. Li et al., “High-Performance Segmentation for Flood Mapping of HISEA-1 SAR Remote Sensing Images,” Remote Sensing 2022, Vol. 14, Page 5504, vol. 14, no. 21, p. 5504, Nov. 2022, doi: 10.3390/RS14215504.

Y. Li, “The research on landslide detection in remote sensing images based on improved DeepLabv3+ method,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 7957-, Mar. 2025, doi: 10.1038/s41598-025-92822-y.

E. T. Wasehun et al., “UAV and satellite remote sensing for inland water quality assessments: a literature review,” Environmental Monitoring and Assessment 2024 196:3, vol. 196, no. 3, pp. 1–31, Feb. 2024, doi: 10.1007/S10661-024-12342-6.

M. Fawakherji and L. Hashemi-Beni, “Flood detection and mapping through multi-resolution sensor fusion: integrating UAV optical imagery and satellite SAR data,” Geomatics, Natural Hazards and Risk, vol. 16, no. 1, Dec. 2025, doi: 10.1080/19475705.2025.2493225;WGROUP:STRING:PUBLICATION.

R. Arya, J. Choudhary, M. Pandey, and D. P. Singh, “Advanced Semantic Segmentation of Flooded Regions in UAV Imagery Using a Modified U-Net Model,” 2025 IEEE International Students’ Conference on Electrical, Electronics and Computer Science, SCEECS 2025, 2025, doi: 10.1109/SCEECS64059.2025.10941437.

A. A. Sundaresan and A. A. Solomon, “Post-disaster flooded region segmentation using DeepLabv3+ and unmanned aerial system imagery,” Natural Hazards Research, vol. 5, no. 2, pp. 363–371, Jun. 2025, doi: 10.1016/J.NHRES.2024.12.003.

H. Zhao et al., “PSANet: Point-wise Spatial Attention Network for Scene Parsing,” 2018. Accessed: Aug. 22, 2025. [Online]. Available: https://github.com/hszhao/PSANet

H. Hu, Q. Li, Y. Zhao, and Y. Zhang, “Parallel Deep Learning Algorithms with Hybrid Attention Mechanism for Image Segmentation of Lung Tumors,” IEEE Trans Industr Inform, vol. 17, no. 4, pp. 2880–2889, Apr. 2021, doi: 10.1109/TII.2020.3022912.

B. Zhang et al., “Multi-scale segmentation squeeze-and-excitation UNet with conditional random field for segmenting lung tumor from CT images,” Comput Methods Programs Biomed, vol. 222, p. 106946, Jul. 2022, doi: 10.1016/J.CMPB.2022.106946.

Z. Wang, J. Wang, K. Yang, L. Wang, F. Su, and X. Chen, “Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+,” Comput Geosci, vol. 158, p. 104969, Jan. 2022, doi: 10.1016/J.CAGEO.2021.104969.

A. Amelio et al., “Representation and compression of Residual Neural Networks through a multilayer network based approach,” Expert Syst Appl, vol. 215, Apr. 2023, doi: 10.1016/j.eswa.2022.119391.

S. E. Abdallah et al., “Deep Learning Model Based on ResNet-50 for Beef Quality Classification,” Information Sciences Letters, vol. 12, no. 1, p. 289, 2023, doi: 10.18576/isl/120124.

J. Hu, L. Shen, and G. Sun, “Squeeze-and-Excitation Networks,” 2018. Accessed: Jun. 30, 2025. [Online]. Available: http://image-net.org/challenges/LSVRC/2017/results

C. Y. Hsu, R. Hu, Y. Xiang, X. Long, and Z. Li, “Improving the Deeplabv3+ Model with Attention Mechanisms Applied to Eye Detection and Segmentation,” Mathematics 2022, Vol. 10, Page 2597, vol. 10, no. 15, p. 2597, Jul. 2022, doi: 10.3390/MATH10152597.

S. O. Atik, M. E. Atik, and C. Ipbuker, “Comparative research on different backbone architectures of DeepLabV3+ for building segmentation,” https://doi.org/10.1117/1.JRS.16.024510, vol. 16, no. 2, p. 024510, May 2022, doi: 10.1117/1.JRS.16.024510.

M. Fadhil and R. A. Saputra, “Klasifikasi dan evaluasi performa model random forest untuk prediksi,” Jurnal Teknik, vol. 12, no. 2, Oct. 2023, doi: 10.31000/JT.V12I2.9099.

D. Wang et al., “SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model”, Accessed: Dec. 22, 2025. [Online]. Available: https://segment-anything.com/demo

X. Hao, L. Yin, X. Li, L. Zhang, and R. Yang, “A Multi-Objective Semantic Segmentation Algorithm Based on Improved U-Net Networks,” Remote Sensing 2023, Vol. 15, Page 1838, vol. 15, no. 7, p. 1838, Mar. 2023, doi: 10.3390/RS15071838.

S. Cai, Y. Tian, H. Lui, H. Zeng, Y. Wu, and G. Chen, “Dense-UNet: a novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network Cai et al. Dense-UNet for MPM image segmentation,” Quant Imaging Med Surg, vol. 10, no. 6, 2020, doi: 10.21037/qims-19-1090.

G. Wang, J. Yu, W. Xu, A. Muhammad, and D. Li, “Automated fish counting system based on instance segmentation in aquaculture,” Expert Syst Appl, vol. 259, p. 125318, Jan. 2025, doi: 10.1016/J.ESWA.2024.125318.

T. Yang, S. Zhou, A. Xu, J. Ye, and J. Yin, “An Approach for Plant Leaf Image Segmentation Based on YOLOV8 and the Improved DEEPLABV3+,” Plants 2023, Vol. 12, Page 3438, vol. 12, no. 19, p. 3438, Sep. 2023, doi: 10.3390/PLANTS12193438.