Tropical Cyclone Forecaster Integrated with Case-Based Reasoning

  • James N. K. Liu
  • Simon C. K. Shiu
  • Jane You
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 28)


One of the major challenges for predicting tropical cyclone intensity is that we lack the understanding of coupling relationships of physical processes governing tropical cyclone intensification. This paper presents a Java-based case-based reasoning model to assist tropical cyclone forecasters to determine the intensity change of the tropical cyclone. Cases are constructed by using the data mining algorithms to uncover the hidden relationships between physical processes and tropical cyclone intensity. We specify the domain data, definitions of features from the data, tool for data exploration, and architecture of case-based reasoning model. Preliminary results are found to be useful to forecasters when faced with some unusual problem and under different weather situations.


Tropical Cyclone Association Rule Tropical Cyclone Intensity Apriori Algorithm Tropical Cyclone Track 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors would like to acknowledge the partial support of CRG grant G-U186 of The Hong Kong Polytechnic University.


  1. 1.
    Aamodt A, Plaza E (1994) Case-based reasoning: foundational issues, methodological variations, and system approaches. AICom – Artificial Intelligence Communications, IOS Press, 7(1):39–59Google Scholar
  2. 2.
    Dvorak VF (1975) Tropical cyclone intensity analysis and forecasting from satellite imagery. Mon Wea Rev 103:420–430CrossRefGoogle Scholar
  3. 3.
    Feng L, Dillon T, Liu J (2001) Inter-transactional association rules for prediction and their application to studying meteorological data. Data Knowl Eng, Elsevier, 37:85–115CrossRefMATHGoogle Scholar
  4. 4.
    Hansen B, Riordan D (1998) Fuzzy case-based prediction of ceiling and visibility. In: Pro. of 1st Conf. on Artificial Intelligence, American Meteorological Society, pp 118–123Google Scholar
  5. 5.
    Lee RST, Liu JNK (2000) Tropical cyclone identification and tracking system using integrated neural oscillatory elastic graph matching and hybrid RBF network track mining techniques. IEEE Trans NN 11(3):680–689MathSciNetGoogle Scholar
  6. 6.
    Li B, Liu J, Dai H (1998) Forecasting from low quality data with applications in weather forecasting. Int J Comp Inform 22(3):351–358Google Scholar
  7. 7.
    McGregor JL, Walsh KJ, Katzfey JJ (2000) Climate simulations for Tasmania. In: Pro. of 4th Int. Conf. on Southern Hemisphere Meteorological and Oceanography, American Meteorological Society, pp 514–515Google Scholar
  8. 8.
    Pal Sankar K, Shiu Simon CK (2004) Foundations of soft case-based reasoning. WileyGoogle Scholar
  9. 9.
    San Pedro J, Burstein F (2003) A framework for case-based fuzzy multi-criteria decision support for tropical cyclone forecasting. In: Pro. of 36th Hawaii Int. Conf., System SciencesGoogle Scholar
  10. 10.
    Tang J, Yang R, Kafatos M (2005) Data mining for tropical cyclone intensity prediction. In: Pro. of 6th Conf. on Coastal Atmospheric and Oceanic Prediction and Processes, Session 7.5Google Scholar
  11. 11.
    TC Formation Regions, NOAA, tc_basins.htm

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • James N. K. Liu
    • 1
  • Simon C. K. Shiu
    • 1
  • Jane You
    • 1
  1. 1.Department of ComputingHong Kong Polytechnic UniversityHung HomHong Kong

Personalised recommendations