CFP last date
20 May 2024
Reseach Article

Application of K-Nearest Neighbor Technique to Predict Severe Thunderstorms

by Himadri Chakrabarty, Sonia Bhattacharya
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 110 - Number 10
Year of Publication: 2015
Authors: Himadri Chakrabarty, Sonia Bhattacharya
10.5120/19349-7677

Himadri Chakrabarty, Sonia Bhattacharya . Application of K-Nearest Neighbor Technique to Predict Severe Thunderstorms. International Journal of Computer Applications. 110, 10 ( January 2015), 1-4. DOI=10.5120/19349-7677

@article{ 10.5120/19349-7677,
author = { Himadri Chakrabarty, Sonia Bhattacharya },
title = { Application of K-Nearest Neighbor Technique to Predict Severe Thunderstorms },
journal = { International Journal of Computer Applications },
issue_date = { January 2015 },
volume = { 110 },
number = { 10 },
month = { January },
year = { 2015 },
issn = { 0975-8887 },
pages = { 1-4 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume110/number10/19349-7677/ },
doi = { 10.5120/19349-7677 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:45:58.077155+05:30
%A Himadri Chakrabarty
%A Sonia Bhattacharya
%T Application of K-Nearest Neighbor Technique to Predict Severe Thunderstorms
%J International Journal of Computer Applications
%@ 0975-8887
%V 110
%N 10
%P 1-4
%D 2015
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Machine learning techniques are used in different types of pattern recognition works. Nowadays, these techniques are applied in meteorological fields for prediction purpose. In this paper, the pattern to be recognized is the severe weather event of squall-thunderstorms. Prediction of severe thunderstorms are done here by applying K-Nearest Neighbor (K-NN) technique. K-NN is a very good classifier which can classify two classes of events 'storm days' and 'no storm days'. It is a non-parametric method. Three types of weather parameters such as moisture difference, dry adiabatic lapse rate and vertical wind shear are considered here as predictors. Both surface as well as upper air data which are measured by radiosonde/ rawindsonde in the early morning are used in this case. Weather forecasting is a challenging job because of the dynamic behavior of the atmosphere. 'Storm days' are predicted correctly more than 91% and both 'storm and no storm days' are classified more than 82% accuracy, having a lead time around 12 hours.

References
  1. Maqsood, Imran, Khan M. R. , Huang G. H. , and Abdalla R "Application of soft computing models to hourly weather analysis in southern Saskatchewan, Canada", 2005, Engineering Applications of Artificial Intelligence,Vol. 18, Issue 1, pp. 115-125.
  2. Ludlam F. H "Severe Local Storms: A Review", Sept 1963, Meteorological Monographs, Vol. 5, pp. 1-30, American Meteorological Society.
  3. Chakrabarty Himadri 2, Murthy C. A. , Bhattacharya Sonia and Das Gupta Ashish, "Application of Artificial Neural Network to Predict Squall-Thunderstorms Using RAWIND Data", May-2013 International Journal of Scientific & Engineering Research (IJSER),Volume 4, Issue 5, pp. 1313-1318, ISSN: 2229-5518.
  4. Chakrabarty1 Himadri, Murthy C. A. , and Das Gupta Ashish, "Application of pattern recognition techniques to predict severe thunderstorms", 2013, International Journal of Computer Theory and Engineering (IJCTE), Vol. 5, No. 6, pp. 850-855, ISSN: 1793-8201.
  5. Moran, J. M. , Moran M. D. and Pauley P. M. , Meteorology: "The Atmosphere and the Science of Weather", 5th Edition, Chapter 6, Prentice Hall, 1997.
  6. Rotunno, Richard and Klemp Joseph B "The Influence of the Shear-Induced Pressure Gradient on Thunderstorm Motion", 1982, Monthly Weather Review, Vol. 110, pp. 136-151.
  7. Fujita Tetsuya, "Analytical Mesometeorology: A Review", 1963, Meteorological Monographs, Vol. 5, No. 27, pp. 77-125, American Meteorological Society.
  8. Sharma Sanjay, Dutta Devajyoti, Das J, and Gariola R. M. , "Nowcasting of severe storms at a station by using the Soft Computing Techniques to the Radar Imagery", 5thEuropean Conference on Severe Storms, Landshut-Germany, 2009.
  9. Cover, Thomas M. , "Estimation by the Nearest Neighbor Rule, 1968 IEEE Transactions on Information Theory", Vol. IT-14, No. 1,pp,. 50-55.
  10. Moradian, Mehdi and Baraani Ahmad, "KNNBA: K-Nearest-Neighbor Based Association Algorithm, 2009, Journal of Theoretical and Applied Information Technology", Vol. 6, No. 1, pp. 123-129.
  11. Rong Li, Wang Hua-Ning, He Han, Cui Yan-Mei and Du Zhan-Le, "Support Vector Machine combined with K-Nearest Neighbors for Solar Flare Forecasting", Chinese Journal of Astronomy and Astrophysics,,2007 Vol. 7, pp. 441-447.
  12. Brath, A. , Montanari A and Toth E, 2002, "Neural networks and non-parametric methods for improving real-time flood forecasting through conceptual hydrological models", Hydrology and Earth System Sciences, Vol. 6 (4), pp. -627-640.
  13. Jayawardena, A. W. , Fernando D. A. K. and Zhou M. C. , 1997, "Comparison of Multilayer Perceptron and Radial Basis Function networks as tools for flood forecasting", Proceedings of the Conference Water-Caused Natural Disasters, their Abatement and Control, held at Anaheim, California, Publ. no. 239.
  14. Zahoor Jan, Abrar Muhammad, Bashir Shariq and Mirza Anwar M. , 2008, "Seasonal to Inter-Annual Climate Prediction Using Data Mining KNN Techniques", Communications and Computer and Information Science, Vol. 20, ISSN: 1865-0929, PP. 40-51.
  15. Yakowitz, S. , 1987, "Near neighbor or method for time series analysis", J, Time-series Analysis, 8, 235-247.
  16. Volland, Hans, 1995, "Handbook of Atmospheric Electrodynamics", Vol. 1, ISBN: 0-8943-8647-0(V. 1)
  17. Kristen L. Corbosiero and Molinari John "The Relationship between Storm Motion, Vertical Wind Shear, and Convective Asymmetries in Tropical Cyclones", Journal of Atmospheric Sciences, 2002 Volume 60 Page No. 366.
Index Terms

Computer Science
Information Sciences

Keywords

Squall-thunderstorm Machine Learning K-Nearest Neighbor and Similarity Measure