Conference Paper2024

Segment Anything Model 2 (SAM 2) for Accurate Flood Detection in Remote Sensing Imagery

Nusrat Sultana, Anika Islam, Yousra Tabassum, Jahanggir Hossain Setu, Asif Mahmud, Ashraful Islam, M. Ashraful Amin

2024 7th Asia Conference on Cognitive Engineering and Intelligent Interaction (CEII 2024)

IEEE, pp. 1-5

  • Sustainable Cities and Communities — Relevance: 70%
  • Climate Action — Relevance: 71%
DOI: 10.1109/ceii65291.2024.00048URL

Abstract

Floods are among the most devastating natural dis-asters. It causes extensive damage to infrastructure, agriculture, and most importantly, human life. Timely and accurate flood detection is very important for minimizing these impacts. This study explores the use of Deep Learning (DL) models to enhance flood detection through image segmentation of Synthetic Aperture Radar (SAR) imagery. Three segmentation models are compared namely, U-Net, X-Net, and Segment Anything Model 2 (SAM 2), using the NASA IMPACT ETCI 2021 flood detection dataset. The results show that SAM 2 performs better than U-Net and X-Net across key metrics. SAM 2 improves accuracy by almost 1 % over U-Net and 1.64% over X-Net. It also demonstrates a higher precision rate, reducing false positives with a 1.25 % increase compared to U-Net and a 2.32% improvement over X-Net. Moreover, SAM 2 significantly enhances recall, detecting 8.71 % more flood-affected areas than both U-Net and X-Net. In terms of segmentation quality, SAM 2 achieves a higher Dice coefficient and Jaccard index, indicating more accurate flood zone identification and boundary detection, especially in smaller or complex areas, SAM 2 proves to be the most reliable model for flood detection.

Keywords

  • flood detection
  • U-Net
  • synthetic aperture radar images
  • Segment Anything Model 2
  • Image segmentation
  • flood zone mapping
  • Remote sensing

CCDS Authors

Asif Mahmud
Asif Mahmud

Asif Mahmud

  • Co-Director, IPT Wing

Lecturer

Department of Computer Science and Engineering

Independent University, Bangladesh

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Edoardo Nemni, Joseph Aylett-Bullock, Samir Belabbès, Lars Bromley. (2020). Fully Convolutional Neural Network for Rapid Flood Segmentation in Synthetic Aperture Radar Imagery. Remote Sensing, 12(16), 2532[10.3390/rs12162532]
  2. 2.Xuan Wu, Zhijie Zhang, Shengqing Xiong, Wanchang Zhang, Jiakui Tang, Zhenghao Li, Bangsheng An, Rui Li. (2023). A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images. Remote Sensing, 15(8), 2046[10.3390/rs15082046]
  3. 3.Aurélia Bernard, Nathalie Long, M. Becker, Md Jamal Uddin Khan, Sylvie Fanchette. (2022). Bangladesh's vulnerability to cyclonic coastal flooding. Natural hazards and earth system sciences, 22(3), 729–751[10.5194/nhess-22-729-2022]
  4. 4.Binayak Ghosh, Shagun Garg, Mahdi Motagh. (2022). AUTOMATIC FLOOD DETECTION FROM SENTINEL-1 DATA USING DEEP LEARNING ARCHITECTURES. ISPRS annals of the photogrammetry, remote sensing and spatial information sciences, V-3-2022, 201–208[10.5194/isprs-annals-v-3-2022-201-2022]
  5. 5.Binayak Ghosh, Shagun Garg, Mahdi Motagh, Sandro Martinis. (2024). Automatic Flood Detection from Sentinel-1 Data Using a Nested UNet Model and a NASA Benchmark Dataset. PFG – Journal of Photogrammetry Remote Sensing and Geoinformation Science, 92(1), 1–18[10.1007/s41064-024-00275-1]
  6. 6.Binbin Huang, Peng Li, Hongyuan Lu, Jiamin Yin, Zhenhong Li, Houjie Wang. (2024). WaterDetectionNet: A New Deep Learning Method for Flood Mapping With SAR Image Convolutional Neural Network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 14471–14485[10.1109/jstars.2024.3440995]
  7. 7.Muhammad Hafizi Mohd Ali, Siti Azirah Asmai, Zulkifli Zainal Abidin, Zuraida Abal Abas, Nurul A. Emran. (2022). Flood Prediction using Deep Learning Models. International Journal of Advanced Computer Science and Applications, 13(9)[10.14569/ijacsa.2022.01309112]
  8. 8.Behrokh Bahrami, Homayoun Arbabkhah. (2024). Enhanced Flood Detection Through Precise Water Segmentation Using Advanced Deep Learning Models. Journal of Civil Engineering Researchers, 6(1), 1–8[10.61186/jcer.6.1.1]
  9. 9.Safieh Javadinejad. (2022). Causes and consequences of floods: flash floods, urban floods, river floods and coastal floods. Resources Environment and Information Engineering, 4(1), 156–166[10.25082/reie.2022.01.002]
  10. 10.Jie Wang, Bensheng Huang, Fuming Wang. (2023). Extraction and Classification of Flood-Affected Areas Based on MRF and Deep Learning. Water, 15(7), 1288[10.3390/w15071288]
← All publications