Prediction of storm surge and inundation using climatological datasets for the Indian coast using soft computing techniques
- 30 Downloads
Natural hazards such as tropical cyclones is a topic of wider interest and operational forecast of their landfall, maximum sustained winds, storm surge height and associated extent of inland inundation is a challenging topic having wider socio-economic implication. Recent advancements in computational power and development of sophisticated models have resulted in better understanding the dynamics of atmosphere and ocean. Forecast quality have improved to a great extent however there are still constraints in computation time and cost for real-time operations. Soft computing techniques in the broad domain of computational intelligence are widely recognized today having diverse practical applications and beneficial value across multiple disciplines. The present study is an effort on application of soft computing techniques such as Artificial Neural Networks, Genetic Algorithm, and Genetic Programming to predict storm surge and inundation characteristics resulting from tropical cyclones. The coast of Odisha adjoining the Bay of Bengal is considered for this case study. Historically, the Odisha coast is known to be highly vulnerable to strike from maximum number of high intense tropical cyclones that form over Bay of Bengal region. Recently in a separate study the authors have developed a comprehensive pre-computed dataset on storm surges and inundation scenarios from historical cyclones that made landfall over coastal Odisha State. Present study is an effort to effectively utilize the pre-computed dataset for real-time operation using soft computing techniques and that performs rapid computation to aid emergency preparedness and planning operations. Study performed several numerical experiments using various soft computing techniques and best possible configuration for real-time operation is developed. An inter-comparison exercise was also carried out to skill assess the performance of various soft computing techniques. The authors believe that this study has immense potential for real-time operations and that can be extended to other coastal regions in India.
KeywordsStorm surge Inundation Artificial Neural Network Genetic Algorithm Genetic Programming Indian Ocean
The authors sincerely express their gratitude to the Ministry of Human Resource Development (MHRD), Government of India for the financial support vide Grant No. IIT/SRIC/NA/PIS/2013-14/231, dated 18-04-2014. This study is conducted as a part of the mega project ‘Artificial intelligence for societal needs: knowledge discovery and intelligent decision making for solving problems in Indian context related to energy, climate, water, disaster management and traffic’ under the sub-project ‘Application of Artificial Intelligence on mapping Coastal inundation and Evacuation route planning through multiple scenarios of storm surge simulations’ supported by MHRD, Government of India. In addition, this study was conducted as a part of the Centre of Excellence (CoE) in Climate Change studies established at IIT Kharagpur and funded by the Department of Science & Technology, Government of India. It forms a part of the sub-project ‘Wind-Waves and Extreme Water Level Climate Projections for the East Coast of India’ under the CoE in Climate Change at IIT Kharagpur.
Compliance with ethical standards
Conflict of interest
All authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Gonnert G, Dube SK, Murty TS, Siefert W (2001) Global storm surges: Theory, observation and application. German Coastal Engineering Research Council, Germany, p 623Google Scholar
- Hallberg R (1995) Some aspects of the circulation in ocean basins with isopycnals intersecting the sloping boundaries. University of Washington, Seattle, p 244Google Scholar
- Haupt SE (2003) Genetic Algorithms in geophysical fluid dynamics. In: AMS Conference on Artificial Intelligence, Paper P1.7, p 8Google Scholar
- Holland JH (1975) Adaptation in natural and artificial systems, 1st edn. University of Michigan Press, Michigan, p 232Google Scholar
- Ingalalli V, Silva S, Castelli M, Vanneschi L (2014) A multi-dimensional genetic programming approach for multi-class classification problems. Genet Program 8599:48–60Google Scholar
- Jelesnianski CP, Chen J, Shaffer WA (1992) SLOSH: Sea, lake, and overland surges from Hurricanes, US Department of Commerce, National Oceanic and Atmospheric Administration, National Weather Service, USAGoogle Scholar
- Luettich RA, Westerink JJ, Scheffner NW (1992) ADCIRC: an advanced three-dimensional circulation model for shelves, coasts, and estuaries. In: Report I. Theory and methodology of ADCIRC-2DDI and ADCIRC-3DLGoogle Scholar
- Rashidi F, Rashidi M (2004) Emotional temporal difference learning based multi-layer perceptron neural network application to a prediction of solar activity. In: Tsumoto S, Slowinski R, Komorowski J, Grzymala-Busse JW (eds) Lecture notes in computer science rough sets and current trends in computing RSCTC 2004, vol 3066. Springer, BerlinGoogle Scholar
- Searson DP (2014) GPTIPS 2: an open-source software platform for symbolic data mining. arXiv preprint arXiv:14124690
- Siek M (2011) Predicting storm surges: chaos, computational intelligence, data assimilation, ensembles. In: Ph.D. Thesis. Delft, The Netherlands, p 240Google Scholar
- Smith JM, Westerink JJ, Kennedy AB, Taflanidis AA, Cheung KF, Smith T (2011) SWIMS Hawaii hurricane wave, surge, and runup inundation fast forecasting tool. In: Proceedings on solutions to coastal disasters, ASCE, pp 89–98Google Scholar
- Taylor AA, Glahn B (2008) Probabilistic guidance for hurricane storm surge. In: 19th conference on probability and statistics, p 8Google Scholar
- Yip CL, Wong KY (2004) Efficient and effective tropical cyclone eye fix using Genetic Algorithm. In: Proceedings of 8th international conference on knowledge based intelligent information and engineering systemsGoogle Scholar