Typhoon Damage Forecasting with Self-Organizing Maps, Multiple Regression and Decision Trees

Kazuhiro Kohara, Ryo Hasegawa

2009

Abstract

Damage caused by typhoons to both people and structures has decreased in Japan due to improvements of countermeasures against natural disasters, however, such damage still occurs. A typhoon warning that represents the risk posed by a typhoon with high accuracy should be issued appropriately. Thus, we propose a new typhoon warning system which forecasts the likely extent of damage associated with a typhoon towards humans and buildings. The relation between typhoon data and damage data is investigated and typhoon damage is forecast using typhoon data. Self-organizing maps (SOM), multiple regression analysis and decision trees were used for typhoon damage forecasting. We consider two types of forecasting: two-class (yes or no) and three-class (small, medium or large scale) damage forecasting. Experimental results on accuracy of two-class and three-class forecasting with SOM were 93.3% and 96.8%, respectively. The accuracy with SOM was much better than that with multiple regression and decision trees. We recommend a new typhoon damage forecasting method based on these results.

References

  1. Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Rumelhart, D., McClelland, J., the PDP Research Group (eds.): Parallel Distributed Processing, Vol. 1. MIT Press, Cambridge, MA (1986).
  2. Kohonen, T.: Self-Organizing Maps. Springer (1995).
  3. Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kaufmann (1993).
  4. Jensen, F.: Bayesian Networks and Decision Graphs. Springer (2001).
  5. Pham, D., Liu, X.: Neural Networks for Identification, Prediction and Control. Springer (1995).
  6. Kohara, K.: Neural networks for economic forecasting problems. In: Leondes, C. T.: Expert Systems - The Technology of Knowledge Management and Decision Making for 21st Century -. Academic Press (2002).
  7. Kohara, K.: Combining selective-presentation and selective-learning-rate approaches for neural network forecasting of stock markets, Proceedings of International Workshop on Artificial Neural Networks and Intelligent Information Processing. Madeira (2008) Pp 3-9.
  8. Harada, H., Momma, E., Ishii, H., Ono, T.: Forecast of typhoon course using multi-layered neural network (III), Proceedings of National Convention of the Institute of Electrical Engineers of Japan, Toyama (2007) Vol. 3, 111.
  9. Takata, H., Kawaji, S., Ha, T.: Study on a Prediction Method of Typhoon Damage of Electric Power Systems in each District on the Main Island in Kagoshima Prefecture, Technical Report 48, Faculty of Engineering, Kagoshima University (2006).
  10. Udagawa, S., Nishio, S., Kimura, M.: Rain prediction by the Bayesian network, Proceedings of National Convention of the Information Processing Society of Japan (2005) Vol.3, 237-238.
  11. Murayama, K.: Introduction to Typhoon Study. Yama-Kei Publishers (2006).
  12. Nyoumura, Y.: Weather Damage Prediction and Countermeasure. Ohmsha (2002).
  13. National Research Institute for Earth Science and Disaster Prevention (2008). http://www.bosai.go.jp/index.html
  14. National Institute of Informatics (2008). http://agora.ex.nii.ac.jp/digital-typhoon
  15. Japan Weather Association (2008). http://www.jwa.or.jp/synfos/
Download


Paper Citation


in Harvard Style

Kohara K. and Hasegawa R. (2009). Typhoon Damage Forecasting with Self-Organizing Maps, Multiple Regression and Decision Trees . In Proceedings of the 5th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: Workshop ANNIIP, (ICINCO 2009) ISBN 978-989-674-002-3, pages 106-111. DOI: 10.5220/0002254601060111


in Bibtex Style

@conference{workshop anniip09,
author={Kazuhiro Kohara and Ryo Hasegawa},
title={Typhoon Damage Forecasting with Self-Organizing Maps, Multiple Regression and Decision Trees},
booktitle={Proceedings of the 5th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: Workshop ANNIIP, (ICINCO 2009)},
year={2009},
pages={106-111},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002254601060111},
isbn={978-989-674-002-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: Workshop ANNIIP, (ICINCO 2009)
TI - Typhoon Damage Forecasting with Self-Organizing Maps, Multiple Regression and Decision Trees
SN - 978-989-674-002-3
AU - Kohara K.
AU - Hasegawa R.
PY - 2009
SP - 106
EP - 111
DO - 10.5220/0002254601060111