Flood Monitoring from SAR Data
This paper presents the intelligent techniques approach for flood monitoring using Synthetic Aperture Radar (SAR) satellite images. We applied artificial neural networks and Self-Organizing Kohonen Maps (SOMs), to SAR image segmentation and classification. Our approach was used to process data from different SAR satellite instruments (ERS-2/SAR, ENVISAT/ASAR, RADARSAT-1/2) for different flood events: Tisza River, Ukraine and Hungary in 2001; Huaihe River, China in 2007; Mekong River, Thailand and Laos in 2008; Koshi River, India and Nepal in 2008; Norman River, Australia in 2009; Lake Liambezi, Namibia in 2009; Mekong River, Laos in 2009. This approach was implemented using Sensor Web paradigm for integrated system for flood monitoring and management.
KeywordsFlood Synthetic Aperture Radar (SAR) Artificial neural networks Sensor Web paradigm
This work is supported by ESA CAT-1 project “Wide Area Grid Testbed for Flood Monitoring using Spaceborne SAR and Optical Data” (No. 4181), and by joint project of the Science and Technology Center in Ukraine (STCU) and the National Academy of Sciences of Ukraine (NASU), “Grid Technologies for Multi-Source Data Integration” (No. 4928).
- Botts M, Percivall G, Reed C, Davidson J (2007) OGC Sensor Web Enablement: Overview and High Level Architecture (OGC 07-165). http://portal.opengeospatial.org/files/?artifact_id=25562. Accessed 10 Sept 2008
- Chu X, Kobialka T, Durnota B, Buyya R (2006) Open sensor web architecture: core services. In: Proceedings of the 4th international conference on intelligent sensing and information processing (ICISIP), IEEE Press, Piscataway, NJ, pp 98–103Google Scholar
- Corbley KP (1999) Radar imagery proves valuable in managing and analyzing floods red river flood demonstrates operational capabilities. Earth Observation Magazine 8(10)Google Scholar
- Csornai G, Suba Zs, Nádor G et al (2004) Evaluation of a remote sensing based regional flood/waterlog and drought monitoring model utilising multi-source satellite data set including ENVISAT data. In: Proceedings of the 2004 ENVISAT & ERS Symposium, Salzburg, AustriaGoogle Scholar
- Cunjian Y, Yiming W, Siyuan W et al (2001) Extracting the flood extent from satellite SAR image with the support of topographic data. In: Proceedings of International Conference on Info-Tech and Info-Networks, vol 1, pp 87–92Google Scholar
- Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, Upper Saddle River, NJGoogle Scholar
- Kohonen T (1995) Self-organizing maps. Series in information sciences, vol 30. Springer, HeidelbergGoogle Scholar
- Mandl D, Frye SW, Goldberg MD et al (2006) Sensor webs: where they are today and what are the future needs? In: Proceedings of the second IEEE workshop on dependability and security in sensor networks and systems (DSSNS 2006), Columbia, MD, pp 65–70Google Scholar
- Moe K, Smith S, Prescott G et al (2008) Sensor web technologies for NASA earth science. In: Proceedings of 2008 IEEE aerospace conference, pp 1–7 Big Sky, MT Digital Object Identifier: 10.1109/AERO.2008.4526458Google Scholar
- Rees WG (2001) Physical principles of remote sensing. Cambridge University Press, CambridgeGoogle Scholar
- Scheuren J-M, de le Polain, Waroux O, Below R et al (2008) Annual disaster statistical review – the number and trends 2007. Center for Research of the Epidemiology of Disasters (CRED). Jacoffsaet Printers, Melin, BelgiumGoogle Scholar