DSAAM-UNet: Flood Detection Based on Lightweight Deep Learning Model and Satellite Imagery
Keywords:
Deep Learning, Remote Sensing, Flood detection, SegmentationAbstract
Flood is the most destructive type of natural disaster on Earth. Mapping the extent of a flood is essential to ascertain the damage and plan for rescue operations. Recently, Deep learning has achieved remarkable performance in remote sensing applications like flood detection. Many variations of the fundamental U-Net segmentation model have been developed and applied in the related studies. In this paper, DSAAM-UNet, an improved version of basic U-Net is proposed. This improvement is achieved by incorporating depth-wise separable convolution blocks and attention blocks in U-Net architecture. Depth-wise separable convolution considerably reduces the number of trainable parameters and training time whereas attention block adaptively focuses on relevant features from satellite imagery. The Ombria dataset is used for performance assessment of proposed model DSAAM-UNet. The proposed segmentation model outperformed the various state-of-the-art methods, such as U-Net, Depth-wise Separable U-Net, and Attention U-Net on the Ombria dataset. The DSAAM-UNet model enhances flood detection from satellite imagery data. The proposed model is beneficial to administrators for flood extent mapping.
Downloads
References
Mazhar S, Sun G, Wang Z, Liang H, Zhang H and Li Y,” Flood Mapping and Classification Jointly Using MuWI and Machine Learning Techniques”. In International Conference on Control, Automation and Information Sciences (ICCAIS), 662-667, 2021 doi: 10.1109/ICCAIS52680.2021.9624489.
Gou Z,” Urban Road Flooding Detection System based on SVM Algorithm” 2nd International Conference on Machine Learning and Computer Application (ICMLCA), Shenyang, China pp 1-82021.
Baghermanesh S, Jabari S and McGrath H, “ Urban Flood Detection Using Sentinel1-A Images “ IEEE International Geoscience and Remote Sensing Symposium IGARSS, 527-530, 2021. DOI: 10.1109/IGARSS47720.2021.9554283.
Binglin Niu,” Semantic Segmentation of Remote Sensing Image Based on Convolutional Neural Network and Mask Generation” Math. Probl. Eng., Article ID 2472726, 13 pages 2021 https://doi.org/10.1155/2021/2472726.
Jesudasan Jennifer, Subbarayan Saravanan and Devanantham Abijith, “Integration of SAR and multi-spectral imagery in flood inundation mapping – a case study on Kerala floods 2018 “ ISH J Hydraul Eng,28(1),480-490, 2020. DOI: 10.1080/09715010.2020.1791265.
Sekertekin A,” A Survey on Global Thresholding Methods for Mapping Open Water Body Using Sentinel-2 Satellite Imagery and Normalized Difference Water Index” Arch. Comput. Methods Eng., 28, 1335–1347, 2021. https://doi.org/10.1007/s11831-020-09416-2.
Ireland G, Volpi M and Petropoulos George P,” Examining the capability of supervised machine learning classifiers in extracting flooded areas from Landsat TM imagery: a case study from a Mediterranean food “ Remote Sens 7(3):3372–3399, 2015.
Pervez W , Khan, Shrf , Hussain, Ejaz , Amir, Faisal & Maud Mohammad ,” Evaluate the capability of Landsat8 operational land imager for shoreline change detection/inland water” Int. arch. photogramm.,XLII-5/W1,145–152,2017. https://doi.org/10.5194/isprs-archives-XLII-5-W1-145-2017.
Baghermanesh S, Jabari S and McGrath H,” Urban Flood Detection Using Sentinel1-A Images” IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp 527-530 DOI: 10.1109/IGARSS47720.2021.9554283.
Shahabi H, Shirzadi A, Ghaderi K, Omidvar E, Al-Ansari N, Clague JJ et al. ,”Flood Detection and Susceptibility Mapping Using Sentinel-1 Remote Sensing Data and a Machine Learning Approach: Hybrid Intelligence of Bagging Ensemble Based on K-Nearest Neighbor Classifier” Remote Sens, 12(2), 266, 2020 https://doi.org/10.3390/rs12020266.
R Jony, A Woodley, A Raj and D Perrin , “Ensemble Classification Technique for Water Detection in Satellite Images” Digital Image Computing: Techniques and Applications (DICTA), 2018, 1-8, doi: 10.1109/DICTA.2018.8615870.
Lamovec Peter, Velkanovski Tatjana, Matjaz Mikos, Kristof Osir,” Detecting flooded areas with machine learning techniques: case study of the Selška Sora river flash flood in September 2007 “ J. Appl. Remote Sens.,7(1), 073564, 2013 https://doi.org/10.1117/1.JRS.7.073564.
[13] S Mazhar, G Sun, Z Wang, H Liang, H Zhang and Y Li ,” Flood Mapping and Classification Jointly Using MuWI and Machine Learning Techniques” International Conference on Control, Automation and Information Sciences (ICCAIS), 662-667, 2021 doi: 10.1109/ICCAIS52680.2021.9624489.
Ronneberger Olaf, Fischer Philipp and Thomas Brox,” U- Net: Convolutional Networks for Biomedical Image Segmentation “ CoRR, vol. abs/1505.04597.
Dong Z, Wang G, Amankwah, S Wei, X Hu, Y Feng,” A Monitoring the summer flooding in the Poyang Lake area of China in 2020 based on Sentinel-1 data and multiple convolutional neural networks” Int J Appl Earth Obs Geoinf. 102, 102400, 2021.
Lalchhanhima R, Saha G, Sur S, Kandar D,” Water body segmentation of Synthetic Aperture Radar image using Deep Convolutional Neural Networks.” Microprocess. Microsyst. Volume 87, 104360. https://doi.org/10.1016/j.micpro.2021.104360.
W Li, J Wu, H Chen, Y Wang, Y Jia and G Gui” IEEE J. Sel. Top. Appl. Earth Obs.” Remote Sens. 15, 6588-6597, 2022 doi: 10.1109/JSTARS.2022.3194375.
Bofei Zhao, Haigang Sui, Junyi Liu,” Siam-DWENet: Flood inundation detection for SAR imagery using a cross-task transfer siamese network” Int J Appl Earth Obs Geoinf,116,103132, 2022 https://doi.org/10.1016/j.jag.2022.103132.
Alshawi, Rasha, Md Tamjidul Hoque and Maik Flanagin,” A Depth-Wise Separable U-Net Architecture with Multiscale Filters to Detect Sinkholes” Remote Sens. 15(5):1384, 2023 https://doi.org/10.3390/rs15051384.
S Zabihi, E Rahimian, A Asif and A Mohammadi,” SepUnet: Depthwise Separable Convolution Integrated U-Net For MRI Reconstruction “ IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA. 2021. pp.3792-3796, 2021 doi: 10.1109/ICIP42928.2021.9506285.
Drakonakis G I, Tsagkatakis G, Fotiadou K and Tsakalides P, OmbriaNet—Supervised Flood Mapping via Convolutional Neural Networks Using Multitemporal Sentinel-1 and Sentinel-2 Data Fusion; in IEEE J Sel Top Appl Earth Obs Remote Sens. vol. 15, pp. 2341-2356, 2022 doi: 10.1109/JSTARS.2022.3155559.
Dataset available at: https://github.com/geodrak/OMBRIA. Accessed on 20/12/2023
Stateczny, Andrzej, Hirald Dwaraka Praveena, Ravikiran Hassan Krishnappa, Kanegonda Ravi Chythanya, and Beenarani Balakrishnan Babysarojam ,” Optimized Deep Learning Model for Flood Detection Using Satellite Images” Remote Sens.15(20):5037.2023 https://doi.org/10.3390/rs15205037
Wu Xuan, Zhijie Zhang, Shengqing Xiong, Wanchang Zhang, Jiakui Tang, Zhenghao Li et al. ,” A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images” Remote Sens. 15(8)8: 2046 https://doi.org/10.3390/rs15082046.
Montaha S, Azam S, Rakibul Haque Rafid, A.K.M. , Md. Zahid Hasan & Asif Karim ,” Brain Tumor Segmentation from 3D MRI Scans Using U-Net. “SN COMPUT. SCI. 2023.4, 386 https://doi.org/10.1007/s42979-023-01854-6
Yidi Wang, Yawen Shen, Behrouz Salahshour, Mecit Cetin, Khan Iftekharuddin, Navid Tahvildari et al. ,” Urban flood extent segmentation and evaluation from real-world surveillance camera images using deep convolutional neural network” Environ. Model. Softw.,Volume 173,2024,105939,ISSN 1364-8152,https://doi.org/10.1016/j.envsoft.2023.105939
Devanand Bathe, K., Patil, N.S. ,” Leveraging Potential of Deep Learning for Remote Sensing Data: A Review” In: Bhattacharyya, S., Koeppen, M., De, D., Piuri, V. (eds) Intelligent Systems and Human Machine Collaboration. Lecture Notes in Electrical Engineering, vol 985. Springer, Singapore. https://doi.org/10.1007/978-981-19-8477-8_11
Bathe, K.D., Patil, N.S. ,” Assessment of land use-land cover dynamics and its future projection through Google Earth Engine, machine learning and QGIS-MOLUSCE: A case study in Jagatsinghpur district, Odisha, India” J Earth Syst Sci 133, 111 (2024). https://doi.org/10.1007/s12040-024-02305-3
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
