OPEN ACCESS
Brisbane, the capital of Queensland, Australia, has flooded periodically and catastrophically, most recently in January 2011. Official seasonal rainfall forecasts failed to predict the floods. Since winter 2013, the Australian Bureau of Meteorology uses a general circulation model, the Predictive Ocean Atmosphere Model for Australia (POAMA), to make official seasonal rainfall forecasts presented as the conditional probability of rainfall being greater or less than the long-term median rainfall. We show that a more skilful forecast can be made using an artificial neural network (ANN), a form of statistical modelling based on artificial intelligence. A Jordan recurrent neural network with one hidden layer was implemented, using genetic optimization of inputs. For the sites of Gatton and Harrisville, in the Brisbane catchment, monthly rainfall forecasts from the ANN show lower root mean square errors than forecasts from POAMA. These rainfall forecasts from the ANN model were further improved by using inputs of independently forecast values for climate indices including the Southern Oscillation Index, the Interdecadal Pacific Oscillation, Pacific sea surface temperature anomalies (Niño 3.4) and also atmospheric temperature. The results presented here represent a first attempt at independently forecasting climate indices using an ANN model for the Australian east coast.
Rainfall, forecast, lagged climate indices, SOI, IPO, Niño 3.4, Brisbane, flood, artificial neural network
[1] Lough, J.M., Variations of some seasonal rainfall characteristics in Queensland, Australia: 1921–1987. International Journal of Climatology, 13, pp. 391–409, 1993. doi: http://dx.doi.org/10.1002/joc.3370130404
[2] Klingaman, N.P., Woolnough, S.J. & Syktus, J., On the drivers of inter-annual and decadal rainfall variability in Queensland, Australia. International Journal of Climatology, 3(10), pp. 2413–2430, 2012. doi: http://dx.doi.org/10.1002/joc.3593
[3] Schepen, A., Wang, Q.J. & Robertson, D., Evidence for using lagged climate indices to forecast Australian seasonal rainfall. Journal of Climate, 25, pp. 1230–1246, 2012. doi: http://dx.doi.org/10.1175/jcli-d-11-00156.1
[4] Risbey, J.S., Pook, M.J., Mcintosh, P.C., Wheeler, M.C. & Hendon, H.H., On the remote drivers of rainfall variability in Australia. Monthly Weather Review, 137, pp. 3233–3253, 2009. doi: http://dx.doi.org/10.1175/2009mwr2861.1
[5] Kirono, D.G.C., Chiew, F.H.S. & Kent, D.M., Identification of best predictors for forecasting seasonal rainfall and runoff in Australia. Hydrological Processes, 24(4), pp. 1237–1247, 2010. doi: http://dx.doi.org/10.1002/hyp.7585
[6] Chowdhury, R.K. & Beecham, S., Australian rainfall trends and their relation to the southern oscillation index. Hydrological Processes, 24, pp. 504–514, 2010. doi: http://dx.doi.org/10.1002/hyp.7504
[7] Murphy, B.F. & Ribbe, J., Variability of Southeastern Queensland rainfall and climate indices. International Journal of Climatology, 24, pp. 703–721, 2004. doi: http://dx.doi.org/10.1002/joc.1018
[8] Cai, W., Whetton, P.H. & Pittock, A.B., Fluctuations of the relationship between ENSO and northeast Australian rainfall. Climate Dynamics, 17, pp. 421–432, 2001. doi: http://dx.doi.org/10.1007/pl00013738
[9] Power, S.B. & Smith, I.N., Weakening of the Walker Circulation and apparent dominance of El Niño both reach record levels, but has ENSO really changed? Geophysical Research Letters, 34, 2007, DOI:10.1029/2007GL030854. doi: http://dx.doi.org/10.1029/2007gl030854
[10] Abbot, J. & Marohasy, J., The application of artificial intelligence for monthly rainfall forecasting in the Brisbane Catchment, Queensland, Australia. WIT Transactions on Ecology and The Environment, Vol. 172, © 2013, WIT Press: Southampton, www.witpress.com, ISSN 1743-3541 (on-line) DOI:10.2495/RBM130111.
[11] Clarke, A.J., Van Gorder, S. & Everingham, Y., Forecasting long-lead rainfall probability with application to Australia’s northeastern coast. Journal of Applied Meteorology and Climatology, 49(7), pp. 1443–1453, 2010. doi: http://dx.doi.org/10.1175/2010jamc2373.1
[12] Chiew, F.H.S., Piechota, T.C., Dracup J.A. & McMahon, T.A., El Niño/southern oscillation and Australian Rain, streamflow and drought: links and potential for forecasting. Journal of Hydrology, 204, pp. 138–149, 1998. doi: http://dx.doi.org/10.1016/s0022-1694(97)00121-2
[13] Perez-Chavarriia, M.A., Hidalgo-Silva, H.H. & Ocampo-Torres, F.J., Time series prediction using artificial neural networks. Ciencias Marinas, 28(1), pp. 67–77, 2002.
[14] Baawain, M.S., Nour, M.H., El-Din, A.G. & El-Din, M.G., El Nino southern-oscillation prediction using southern oscillation index and Nino3 as onset indicators: application of artificial neural networks. Journal of Environmental Engineering and Science, 4(2), pp. 113–121, 2005. doi: http://dx.doi.org/10.1139/s04-047
[15] van den Honert, R.C. & McAneney, J., The 2011 Brisbane Floods: causes, impacts and implications. Water, 3, pp. 1149–1173, 2011. doi: http://dx.doi.org/10.3390/w3041149
[16] Cratchley, D., Insurers prepared for mounting flood costs. Herald Sun Jan 13, 2013. Available online at: http://www.heraldsun.com.au/news/breaking-news/insurers-blame-councils-forflood-damage/story-e6frf7kf-1226564743427
[17] Johnson, S., Queensland floods class action could set record. Yahoo 7 News January 20, 2013. Available online at: http://au.news.yahoo.com/latest/a//latest/15887827/qld-floods-class-actioncould-set-record/
[18] Dahamsheha, A. & Aksoyb, H., Artificial neural network models for forecasting intermittent monthly precipitation in arid regions. Meteorological Application, 16, pp. 325–337, 2009. doi: http://dx.doi.org/10.1002/met.127
[19] Shukla, R.P., Tripathi, K.C., Pandey, A.C. & Das, I.M.L., Prediction of Indian summer monsoon rainfall using Niño indices: a neural network approach. Atmospheric Research, 102, pp. 99–109, 2011. doi: http://dx.doi.org/10.1016/j.atmosres.2011.06.013
[20] Wu, X., Cao, H., Flitman, A., Wei, F. & Feng, G., Forecasting monsoon precipitation using artificial neural networks. Advances in Atmospheric Sciences, 18, pp. 950–958, 2001.
[21] Philip, N.S. & Joseph, K.B., 2A neural network tool for analysing trends in rainfall. Computers & Geosciences, 29, pp. 215–223, 2003. doi: http://dx.doi.org/10.1016/s0098-3004(02)00117-6
[22] Chakraverty, S. & Gupta, P., Comparison of neural network configurations in the long-range forecast of southwest monsoon rainfall over India. Neural Computing & Applications, 17, pp. 187–192, 2008. doi: http://dx.doi.org/10.1007/s00521-007-0093-y
[23] Mekanik, F. & Imteaz, M.A., Forecasting Victorian spring rainfall using ENSO and IOD: a comparison of linear multiple regression and nonlinear ANN International Conference on Uncertainty Reasoning and Knowledge Engineering. Proc. of the 2nd Int. Conf. on Uncertainty Reasoning and Knowledge Engineering (URKE 2012), Jakarta, Indonesia, pp. 86–89, 2012. doi: http://dx.doi.org/10.1109/urke.2012.6319591
[24] Abbot, J. & Marohasy, J., Application of artificial neural networks to rainfall forecasting in Queensland, Australia. Advances in Atmospheric Sciences, 29(4), pp. 717–730, 2012. doi: http://dx.doi.org/10.1007/s00376-012-1259-9
[25] Vaze, J., Teng, J. & Chiew, F.H.S., Assessment of GCM simulations of annual and seasonal rainfall and daily rainfall distribution across south-east Australia. Hydrological Processes, 25, pp. 1486–1497, 2011. doi: http://dx.doi.org/10.1002/hyp.7916
[26] Raisanen, J., Ruokolainen, L. & Ylhaisi, J., Weighting of model results for improving best estimates of climate change. Climate Dynamics, 35, pp. 407–422, 2010. doi: http://dx.doi.org/10.1007/s00382-009-0659-8
[27] Pennell, C. & Reichler, T., On the effective number of climate models. Journal of Climate, 24, pp. 2358–2367, 2011. doi: http://dx.doi.org/10.1175/2010jcli3814.1
[28] Kodra, E., Ghosh, S. & Ganguly, A.R., Evaluation of global climate models for Indian monsoon climatology. Environmental Research Letters, 7(1), 014012, 2012. doi: http://dx.doi.org/10.1088/1748-9326/7/1/014012