Identification of Flooded Regions through SAR Images and U-NET Deep Learning Model: A Case Study in Tabasco, Mexico
Keywords:
Flooded regions, Climate change impact, Geospatial information processingAbstract
Flooding is a prevalent issue worldwide, attributed to various factors such as climate change and land use. In Mexico, annual floods impact different regions, with Tabasco experiencing periodic inundations that result in significant losses across rural, urban, livestock, agricultural, and service sectors. Effective intervention strategies are essential for mitigating the repercussions of these floods. Consequently, diverse techniques have been developed to minimize the damage caused by this phenomenon. Satellite programs offer extensive data on the Earth's surface, complemented by geospatial information processing tools crucial for environmental monitoring, climate change analysis, risk assessment, and response to natural disasters. This research introduces an approach to classify flooded areas using synthetic aperture radar satellite images and the U-NET neural network. Focused on the Los Ríos region in Tabasco, Mexico, our preliminary findings demonstrate the effectiveness of U-NET, even with a limited training dataset. The model's accuracy improves with an increase in training data and epochs.
References
Abd-Elrahman, A., Britt, K., Liu, T. (2021). Deep learning classification of high-resolution drone images using the ArcGIS pro software. Vol. 2021, No. 5, pp. 1–7. DOI: 10.32473/edis-fr444-2021.
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamar´ıa, J., A. Fadhel, M., Al-Amidie, M., Laith, F. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, Vol. 8, No. 53. DOI: 10.1186/s40537-021-00444-8.
Bengio, Y., Courville, A. C., Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 8, pp. 1798–1828. DOI: 10.1109/TPAMI.2013.50.
Bourenane, H., Bouhadad, Y., Tas, M. (2018). Liquefaction hazard mapping in the city of Boumerdes, Northern Algeria. Bulletin of ` Engineering Geology and the Environment, Vol. 77, pp. 1473–1489. DOI: 10.1007/s10064-017-1137-x.
Centro Nacional de Prevencion de Desastres ´ (2012). Inundaciones. ¿Que es una inundaci ´ on?, 1 ´ edition, pp. 1–5.
Chen, L. C., Papandreou, G., Schroff, F., Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. DOI: 10.48550/arXiv .1706.05587.
Chini, M., Pelich, R., Pulvirenti, L., Pierdicca, N., Hostache, R., Matgen, P. (2019). Sentinel-1 InSAR coherence to detect floodwater in urban areas: Houston and hurricane Harvey as a test case. Remote Sensing, Vol. 11, No. 2. DOI: 10.3 390/rs11020107. Computación y Sistemas, Vol. 27, No. 2, 2023, pp. 449–458 doi: 10.13053/CyS-27-2-4624 456 Fernando Pech-May, Julio Víctor Sánchez-Hernández, Luis Antonio López-Gómez, et al. ISSN 2007-9737
Cuevas, J., Enr´ıquez, M., Norton, R. (2022). Inundaciones de 2020 en Tabasco: Aprender del pasado para preparar el futuro. Technical report, Centro Nacional de Prevencion de Desastres. ´ 9. Fernandez-Ordo ´ nez, Y., Soria-Ruiz, J., Leblon, ˜ B., Macedo, A., Elva, M., Ram´ırez-Guzman, M. E., ´ Escalona-Maurice, M. (2020). Imagenes de radar ´ para estudios territoriales, caso: Inundaciones en Tabasco con el uso de imagenes SAR Sentinel-1A ´ y Radarsat-2. Vol. 11, No. 1, pp. 5–24.
Gao, M., Qi, D., Mu, H., Chen, J. (2021). A transfer residual neural network based on ResNet-34 for detection of wood knot defects. Forests, Vol. 12, No. 2. DOI: 10.3390/f12020212. 11. Gupta, D., Kushwaha, V., Gupta, A., Singh, P. K. (2021). Deep learning-based detection of water bodies using satellite images. 2021 International Conference on Intelligent Technologies (CONIT), pp. 1–4. DOI: 10.1109/CONIT51480.2021.9498442.
Ienco, D., Gaetano, R., Interdonato, R., Ose, K., Ho-Tong-Minh, D. (2019). Combining Sentinel-1 and Sentinel-2 time series via RNN for object-based land cover classification. IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, pp. 4881–4884. DOI: 10.1109/IGAR SS.2019.8898458.
Kant-Singh, K., Singh, A. (2017). Identification of flooded area from satellite images using hybrid Kohonen fuzzy C-Means sigma classifier. The Egyptian Journal of Remote Sensing and Space Science, Vol. 20, No. 1, pp. 147–155. DOI: 10.1016/ j.ejrs.2016.04.003.
Konapala, G., Sujay, K., Khalique-Ahmad, S. (2021). Exploring Sentinel-1 and Sentinel-2 diversity for flood inundation mapping using deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 180, pp. 163–173. DOI: 10.1016/j.is prsjprs.2021.08.016.
Labrador-Garc´ıa, M., Evora Brondo, J., Arbelo, ´ M. (2012). Satelites de teledetecci ´ on para la gesti ´ on´ del territorio. Proyecto SATELMAC.
Lee, S. U., Yoon-Chung, S., Hong-Park, R. (1990). A comparative performance study of several global thresholding techniques for segmentation. Computer Vision, Graphics, and Image Processing, Vol. 52, No. 2, pp. 171–190. DOI: 10.1016/0734-1 89X(90)90053-X.
Li, Y., Martinis, S., Wieland, M. (2019). Urban flood mapping with an active self-learning convolutional neural network based on TerraSAR-X intensity and interferometric coherence. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 152, pp. 178–191. DOI: 10.1016/j.isprsjprs.2019.04.014.
Marc, R., Marco, K. (2018). Multi-temporal land cover classification with sequential recurrent encoders. ISPRS International Journal of Geo-Information, Vol. 7, No. 4, pp. 1–18. DOI: 10.3390/ijgi7040129.
Ohki, M., Yamamoto, K., Tadono, T., Yoshimura, K. (2020). Automated processing for flood area detection using alos-2 and hydrodynamic simulation data. Remote Sensing, Vol. 12, No. 17. DOI: 10.339 0/rs12172709.
Paz, J., Jimenez, F., S ´ anchez, B. (2018). ´ Urge un manejo sustentable del agua en Tabasco. Technical report, Universidad Nacional Autonoma de M ´ exico y ´ Asociacion Mexicana de Ciencias para el Desarrollo ´ Regional A. C., Ciudad de Mexico. ´
Pech-May, F., Sanchez-Hern ´ andez, J. V., Jacinto, ´ H. G. S., Magana-Govea, J. (2021). ˜ Analisis de ´ zonas de cultivo y cuerpos de agua mediante el cálculo de ´ ´ındices radiometricos con im ´ agenes ´ Sentinel-2. Vol. 1, No. 24, pp. 48–59. DOI: 10.215 01/21454086.3601.
Ponmani, E., Saravanan, P. (2021). Image denoising and despeckling methods for SAR images to improve image enhancement performance: A survey. Multimedia Tools and Applications, Vol. 80, pp. 26547–26569. DOI: 10.1007/s11042-021-108 71-7.
Rudner, T. G., Rußwurm, M., Fil, J., Pelich, R., Bischke, B., Kopackov ˇ a, V., Bili ´ nski, P. ´ (2019). Multi3Net: Segmenting flooded buildings via fusion of multiresolution, multisensor, and multitemporal satellite imagery. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, pp. 702–709. DOI: 10.1609/aaai.v33i01.3301702.
Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems (NIPS 2015), Vol. 28.
Sirirattanapol, C., Tamkuan, N., Nagai, M., Ito, M. (2020). Apply deep learning techniques on classification of single-band SAR satellite images. Geoinformatics for Sustainable Development in Asian Cities, Springer International Publishing, pp. 1–11. DOI: 10.1007/978-3-030-33900-5 1.
