A Comparative Assessment of Models to Predict Monthly Rainfall in Australia
Accurate rainfall prediction is a challenging task. It is especially challenging in Australia where the climate is highly variable. Australia’s climatic zones range from high rainfall tropical regions in the north to the driest desert region in the interior. The performance of prediction models may vary depending on climatic conditions. It is, therefore, important to assess and compare the performance of these models in different climatic zones. This paper examines the performance of data driven models such as the support vector machines for regression, the multiple linear regression, the k-nearest neighbors and the artificial neural networks for monthly rainfall prediction in Australia depending on climatic conditions. Rainfall data with five meteorological variables over the period of 1970–2014 from 24 geographically diverse weather stations are used for this purpose. The prediction performance of each model was evaluated by comparing observed and predicted rainfall using various measures for prediction accuracy.
KeywordsRainfall prediction Prediction models Regression analysis Prediction performance
This research by Dr. A. Bagirov was supported by the Australian Research Counsil’s Discovery Projects funding scheme (Project No. DP140103213). The authors would like to thank the Editor and two anonymous referees for their comments that helped to significantly improve the quality of the paper.
- Australian weather and seasons (2013) http://www.australia.gov.au/about-australia/australian-story/austn-weather-and-the-seasons
- Al-Qahtani F, Crone S (2013) Multivariate k-nearest neighbour regression for time series data - A novel algorithm for forecasting UK electricity demand. In: The 2013 international joint conference on neural networks (IJCNN), pp 1–8Google Scholar
- Collobert R, Bengio S (2001) SVMTorch: Support vector machines for large-scale regression problems. J Mach Learn Res 1:143–160Google Scholar
- Garnaut R (2008) The Garnaut climate change review: final report. Cambridge University Press, CambridgeGoogle Scholar
- Haykin S (2001) Neural networks: a comprehensive foundation. Upper Saddle River, N.J.: Prentice HallGoogle Scholar
- Lin GF, Chen GR, Wu MC, Chou YC (2009) Effective forecasting of hourly typhoon rainfall using support vector machines. Water Resour Res 45(8):W08440. https://doi.org/10.1029/2009WR007911
- Meyer D, Dimitriadou E, Hornik K, Weingessel A, Leisch F (2015) e1071: Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien. https://CRAN.R-project.org/package=e1071. R package version 1.6–7
- Müller KR, Smola A, Rätsch G, Schölkopf B, Kohlmorgen J, Vapnik V (1997) Predicting time series with support vector machines. In: Gerstner W, Germond A, Hasler M, Nicoud JD (eds) Artificial neural networks – ICANN’97. ICANN 1997. Lecture notes in computer science, vol 1327. Springer, Berlin, Heidelberg, pp 999–1004Google Scholar
- R Core Team (2013) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/
- Schliep K, Hechenbichler K (2016) kknn: Weighted k-Nearest Neighbors. https://CRAN.R-project.org/package=kknn
- Sharma V, van de Graaff S, Loechel B, Franks D (2013) Extractive resource development in a changing climate: learning the lessons from extreme weather events in Queensland. National Climate Change Adaptation Research Facility, Gold Coast, p 110Google Scholar
- Yakowitz S, Karlsson M (1987) Nearest neighbor methods for time series, with application to rainfall/runoff prediction. In: Advances in the statistical sciences: stochastic hydrology. Springer, Berlin, pp 149–160Google Scholar