**Author details**

Yuriy Kuleshov

Address all correspondence to: y.kuleshov@bom.gov.au

1 Bureau of Meteorology, Melbourne, VIC, Australia

2 School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC, Australia

3 School of Science, Royal Melbourne Institute of Technology (RMIT) University, Melbourne, VIC, Australia

4 Faculty of Sciences, Engineering and Technology, Swinburne University of Technology, Melbourne, VIC, Australia

### **References**

[1] Y. Kuleshov, S. McGree, D. Jones, A. Charles, A. Cottrill, B. Prakash, T. Atalifo, S. Nihmei and F. L. S. K. Seuseu, "Extreme weather and climate events and their impacts on island countries in the Western Pacific: Cyclones, floods and droughts", Atmospheric and Climate Sciences, 4, 2014, 803–818. doi: 10.4236/acs.2014.45071.

[2] Y. Kuleshov, L. Qi, R. Fawcett and D. Jones, "On tropical cyclone activity in the southern hemisphere: Trends and the ENSO connection", Geophysical Research Letters, 35, 2008, L14S08, doi: 10.1029/2007GL032983.

ology which utilise NIÑO3 and SOI indices as LDA models' inputs [7]. Examining prospects for improving skill of operational TC seasonal forecasting, Kuleshov et al. [15] demonstrated that 5VAR index performs better than NIÑO3 and SOI. Consequently, the LDA model for annual total occurrences of TCs in the Australian region (*AR*) has been modified to use 5VAR

where 0, 2 . For a detailed mathematical description of the developed LDA model, see [15].

Support vector regression (SVR) has been identified as a skilful machine learning algorithm for application to TC seasonal prediction [9]. Using non-parametric and non-linear regression approach, annual total number of TCs expected to be formed in the coming season (*Y*) has been generated using nine variables as the model's input. Selected input variables (*X*1–*X*9) were the following indices: *X*1, Dipole mode index; *X*2, NIÑO4; *X*3, NIÑO3.4; *X*4, NIÑO3; *X*5, NIÑO1.2; *X*6, El Niño Modoki index; *X*7, 5VAR index; *X*8, multivariate ENSO index; and *X*9,

2 School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC, Aus-

3 School of Science, Royal Melbourne Institute of Technology (RMIT) University, Melbourne,

4 Faculty of Sciences, Engineering and Technology, Swinburne University of Technology,

[1] Y. Kuleshov, S. McGree, D. Jones, A. Charles, A. Cottrill, B. Prakash, T. Atalifo, S. Nihmei and F. L. S. K. Seuseu, "Extreme weather and climate events and their impacts on island

and also incorporate time trend variable (*T*) as predictors in the region:

246 Recent Developments in Tropical Cyclone Dynamics, Prediction, and Detection

SOI. For a detailed mathematical description of the SVR model, see [17].

Address all correspondence to: y.kuleshov@bom.gov.au

1 Bureau of Meteorology, Melbourne, VIC, Australia

**B. Support sector regression (SVR) model**

**Author details**

Yuriy Kuleshov

VIC, Australia

**References**

Melbourne, VIC, Australia

tralia


[12] A. Dowdy and Y. Kuleshov, "An analysis of tropical cyclone occurrence in the Southern Hemisphere derived from a new satellite-era dataset", International Journal of Remote

[13] Y. Kuleshov, R. Fawcett, L. Qi, B. Trewin, D. Jones, J. McBride and H. Ramsay, "Trends in tropical cyclones in the South Indian Ocean and the South Pacific Ocean", Journal of

[14] H. A. Ramsay, L. M. Leslie, P. J. Lamb, M. B. Rickman and M. Leplastrier, "Interannual variability of tropical cyclones in the Australian region: Role of large-scale environ-

[15] Y. Kuleshov, Y. Wang, J. Apajee, R. Fawcett and D. Jones, "Prospects for improving the operational seasonal prediction of tropical cyclone activity in the Southern Hemisphere", Atmospheric and Climate Sciences, 2(3), 2012, 298–306, doi: 10.4236/acs.

[16] A. Dowdy, "Long-term changes in Australian tropical cyclone numbers", Atmospheric

[17] J. S. Wijnands, G. Qian, K. Shelton, R. J. B. Fawcett, J. C. L. Chan and Y. Kuleshov, "Seasonal forecasting of TC activity in the Australian and the South Pacific Ocean regions", Mathematics of Climate and Weather Forecasting, 1, 2015, 21–42, doi 10.1515/

[18] S. Langford, H. H. Hendon and E.-P. Lim, "Assessment of POAMA's predictions of some climate indices for use as predictors of Australian rainfall", CAWCR Technical Report,

[19] K. J. Tory, R. A. Dare, N. E. Davidson, J. L. McBride and S. S. Chand, "The importance of low-deformation vorticity in TC formation", Atmospheric Chemistry and Physiscs,

[20] T. Yasuda, Y. Takaya, C. Kobayashi, M. Kamachi, H. Kamahori and T. Ose, "Asian monsoon predictability in JMA/MRI seasonal forecast system", CLIVAR Exchanges, 43,

[21] F. Vitart and T. N. Stockdale, "Seasonal forecasting of tropical storms using coupled

[22] Y. Takaya, T. Yasuda, T. Ose and T. Nakaegawa, "Seasonal prediction of mean location of Typhoon formation", Journal of the Meteorological Society of Japan, 88(5), 2009, 799–

[23] A. Charles, K. Shelton, T. Nakaegawa, H. Hendon and Y. Kuleshov, "Prediction of tropical cyclone activity with coarse resolution global climate models", Proceedings of the 20th International Congress on Modelling and Simulation (MODSIM2013), Ade-

GCM integrations", Monthly Weather Review, 129, 2001, 2521–2537.

laide, Australia, 1–6 December, 2013, pp. 2555–2561.

Sensing, 33(23), 2012, 7382–7397, doi: 10.1080/01431161.2012.685986.

Geophysical Research, 115, 2010, D01101, doi: 10.1029/2009JD012372.

ment", Journal of Climate, 21, 2008, 1083–1103.

248 Recent Developments in Tropical Cyclone Dynamics, Prediction, and Detection

Science Letters, 15(4), 2014, 292–298, doi: 10.1002/asl2.502.

2012.23027

mcwf-2015-0002.

031, 2011, 60 pp.

2007, 18–20.

812.

12, 2012, 17539–17581.
