Drought forecasts can be an effective tool for mitigating some of the more adverse consequences of drought. Data-driven models are suitable forecasting tools due to their rapid development times, as well as minimal information requirements compared to the information required for physically based models. This study compares the effectiveness of three data-driven models for forecasting drought conditions in the Awash River Basin of Ethiopia. The Standard Precipitation Index (SPI) is forecast and compared using artificial neural networks (ANNs), support vector regression (SVR), and wavelet neural networks (WN). SPI 3 and SPI 12 were the SPI values that were forecasted. These SPI values were forecast over lead times of 1 and 6 months. The performance of all the models was compared using RMSE, MAE, and . The forecast results indicate that the coupled wavelet neural network (WN) models were the best models for forecasting SPI values over multiple lead times in the Awash River Basin in Ethiopia. 1. Introduction Droughts, a natural occurrence in almost all climatic zones, are a result of the reduction, for an extended period of time, of precipitation from normal amounts. Extended periods of drought can lead to several adverse consequences, which include a disruption of the water supply, low agricultural yields, and reduced flows for ecosystems. Consequently, the ability to forecast and predict the characteristics of droughts, specifically their initiation, frequency, and severity, is important. Effective drought forecasts are an effective tool for water resource management as well as an effective tool for the agricultural industry. Currently, drought monitoring in Ethiopia is conducted by the National Meteorological Services Agency (NMSA). The NMSA regularly produces a 10-day bulletin that gives an analysis of rainfall based on the long-term average or normal. This bulletin is then circulated to a wide range of users, ranging from local development agents to decision makers at a national level. In addition to rainfall analysis, the normalized vegetation index (NDVI) is provided, which is a satellite-based index widely used to monitor vegetation and drought conditions. The NMSA produces a regular 10-day bulletin regarding NDVI variation that compares the current vegetation condition with normal or conditions of the previous year [1]. However, the NDVI is sensitive to changes in vegetative land cover and may not be effective in areas where vegetation is minimal. In addition, the NMSA of Ethiopia produces medium and seasonal forecasts of precipitation using the
References
[1]
E. Mersha and V. K. Boken, “Agricultural drought in Ethiopia,” in Monitoring and Predicting Agricultural Drought: A Global Study, V. K. Boken, A. P. Cracknell, and R. L. Heathcote, Eds., Oxford University Press, 2005.
[2]
A. K. Mishra and V. P. Singh, “A review of drought concepts,” Journal of Hydrology, vol. 391, no. 1-2, pp. 202–216, 2010.
[3]
T. Ross and N. Lott, “A climatology of 1980–2003 extreme weather and climate events,” National Climatic Data Center Technical Report No. 2003-01. NOAA/ NESDIS, National Climatic Data Center, Asheville, NC, USA.
[4]
A. Cancelliere, G. di Mauro, B. Bonaccorso, and G. Rossi, “Stochastic forecasting of drought indices,” in Methods and Tools For Drought Analysis and Management, G. Rossi, T. Vega, and B. Bonaccorso, Eds., Springer, 2007.
[5]
W. J. Gibbs and J. V. Maher, Rainfall Deciles as Drought Indicators, vol. 48 of Bulletin (Commonwealth Bureau of Meteorology, Australia), Bureau of Meteorology, Melbourne, Australia, 1967.
[6]
T. B. McKee, N. J. Doesken, and J. Kleist, “The relationship of drought frequency and duration to time scales,” in Proceedings of the 8th Conference on Applied Climatology, American Meteorological Society, Anaheim, Calif, USA, 1993.
[7]
H. R. Byun and D. A. Wilhite, “Objective quantification of drought severity and duration,” Journal of Climate, vol. 12, no. 9, pp. 2747–2756, 1999.
[8]
W. Palmer, “Meteorological drought,” Tech. Rep. 45, U.S. Weather Bureau, Washington, DC, USA, 1965.
[9]
H. K. Ntale and T. Y. Gan, “Drought indices and their application to East Africa,” International Journal of Climatology, vol. 23, no. 11, pp. 1335–1357, 2003.
[10]
A. K. Mishra and V. R. Desai, “Drought forecasting using feed-forward recursive neural network,” Ecological Modelling, vol. 198, no. 1-2, pp. 127–138, 2006.
[11]
S. Morid, V. Smakhtin, and K. Bagherzadeh, “Drought forecasting using artificial neural networks and time series of drought indices,” International Journal of Climatology, vol. 27, no. 15, pp. 2103–2111, 2007.
[12]
U. G. Bacanli, M. Firat, and F. Dikbas, “Adaptive Neuro-Fuzzy inference system for drought forecasting,” Stochastic Environmental Research and Risk Assessment, vol. 23, no. 8, pp. 1143–1154, 2009.
[13]
A. P. Barros and G. J. Bowden, “Toward long-lead operational forecasts of drought: an experimental study in the Murray-Darling River Basin,” Journal of Hydrology, vol. 357, no. 3-4, pp. 349–367, 2008.
[14]
P. Cutore, G. Di Mauro, and A. Cancelliere, “Forecasting palmer index using neural networks and climatic indexes,” Journal of Hydrologic Engineering, vol. 14, no. 6, pp. 588–595, 2009.
[15]
M. Karamouz, K. Rasouli, and S. Nazif, “Development of a hybrid Index for drought prediction: case study,” Journal of Hydrologic Engineering, vol. 14, no. 6, pp. 617–627, 2009.
[16]
A. F. Marj and A. M. J. Meijerink, “Agricultural drought forecasting using satellite images, climate indices and artificial neural network,” International Journal of Remote Sensing, vol. 32, no. 24, pp. 9707–9719, 2011.
[17]
D. Labat, R. Ababou, and A. Mangin, “Wavelet analysis in karstic hydrology. 2nd part: rainfall-runoff cross-wavelet analysis,” Comptes Rendus de l'Academie de Sciences, vol. 329, no. 12, pp. 881–887, 1999.
[18]
P. Saco and P. Kumar, “Coherent modes in multiscale variability of streamflow over the United States,” Water Resources Research, vol. 36, no. 4, pp. 1049–1067, 2000.
[19]
L. C. Smith, D. L. Turcotte, and B. L. Isacks, “Stream flow characterization and feature detection using a discrete wavelet transform,” Hydrological Processes, vol. 12, no. 2, pp. 233–249, 1998.
[20]
P. Coulibaly, F. Anctil, and B. Bobée, “Daily reservoir inflow forecasting using artificial neural networks with stopped training approach,” Journal of Hydrology, vol. 230, no. 3-4, pp. 244–257, 2000.
[21]
S. N. Lane, “Assessment of rainfall-runoff models based upon wavelet analysis,” Hydrological Processes, vol. 21, no. 5, pp. 586–607, 2007.
[22]
J. F. Adamowski, “Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis,” Journal of Hydrology, vol. 353, no. 3-4, pp. 247–266, 2008.
[23]
J. Adamowski and K. Sun, “Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds,” Journal of Hydrology, vol. 390, no. 1-2, pp. 85–91, 2010.
[24]
M. ？zger, A. K. Mishra, and V. P. Singh, “Long lead time drought forecasting using a wavelet and fuzzy logic combination model: a case study in Texas,” Journal of Hydrometeorology, vol. 13, no. 1, pp. 284–297, 2012.
[25]
T. Partal and ？. Ki？i, “Wavelet and neuro-fuzzy conjunction model for precipitation forecasting,” Journal of Hydrology, vol. 342, no. 1-2, pp. 199–212, 2007.
[26]
T. W. Kim and J. B. Valdes, “Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks,” Journal of Hydrologic Engineering, vol. 8, no. 6, pp. 319–328, 2003.
[27]
V. Vapnik, The Nature of Statistical Learning Theory, Springer, New York, NY, USA, 1995.
[28]
J. B. Gao, S. R. Gunn, C. J. Harris, and M. Brown, “A probabilistic framework for SVM regression and error bar estimation,” Machine Learning, vol. 46, no. 1–3, pp. 71–89, 2002.
[29]
M. S. Khan and P. Coulibaly, “Application of support vector machine in lake water level prediction,” Journal of Hydrologic Engineering, vol. 11, no. 3, pp. 199–205, 2006.
[30]
S. Rajasekaran, S. Gayathri, and T.-L. Lee, “Support vector regression methodology for storm surge predictions,” Journal of Ocean Engineering, vol. 35, no. 16, pp. 1578–1587, 2008.
[31]
O. Kisi and M. Cimen, “Evapotranspiration modelling using support vector machines,” Hydrological Sciences Journal, vol. 54, no. 5, pp. 918–928, 2009.
[32]
O. Kisi and M. Cimen, “A wavelet-support vector machine conjunction model for monthly streamflow forecasting,” Journal of Hydrology, vol. 399, no. 1-2, pp. 132–140, 2011.
[33]
T. Asefa, M. Kemblowski, M. McKee, and A. Khalil, “Multi-time scale stream flow predictions: the support vector machines approach,” Journal of Hydrology, vol. 318, no. 1–4, pp. 7–16, 2006.
[34]
W. C. Wang, K. W. Chau, C. T. Cheng, and L. Qiu, “A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series,” Journal of Hydrology, vol. 374, no. 3-4, pp. 294–306, 2009.
[35]
R. Maity, P. P. Bhagwat, and A. Bhatnagar, “Potential of support vector regression for prediction of monthly streamflow using endogenous property,” Hydrological Processes, vol. 24, no. 7, pp. 917–923, 2010.
[36]
Z. M. Yuan and X. S. Tan, “Nonlinear screening indicators of drought resistance at seedling stage of rice based on support vector machine,” Acta Agronomica Sinica, vol. 36, no. 7, pp. 1176–1182, 2010.
[37]
C. Cacciamani, A. Morgillo, S. Marchesi, and V. Pavan, “Monitoring and forecasting drought on a regional scale: emilia-romagna region,” Water Science and Technology Library, vol. 62, part 1, pp. 29–48, 2007.
[38]
I. Bordi and A. Sutera, “Drought monitoring and forecasting at large-scale,” in Methods and Tools For Drought Analysis and Management, G. Rossi, T. Vega, and B. Bonaccorso, Eds., pp. 3–27, Springer, New York, NY, USA, 2007.
[39]
N. B. Guttman, “Accepting the standardized precipitation index: a calculation algorithm,” Journal of the American Water Resources Association, vol. 35, no. 2, pp. 311–322, 1999.
[40]
H. C. S. Thom, “A note on gamma distribution,” Monthly Weather Review, vol. 86, pp. 117–122, 1958.
[41]
D. C. Edwards and T. B. McKee, “Characteristics of 20th century drought in the United States at multiple scales,” Atmospheric Science Paper 634, 1997.
[42]
D. S. Wilks, Statistical Methods in the Atmospheric Sciences an Introduction, Academic Press, San Diego, Calif, USA, 1995.
[43]
M. Abramowitz and A. Stegun, Eds., Handbook of Mathematical Formulas, Graphs, and Mathematical Tables, Dover Publications, New York, NY, USA, 1965.
[44]
S. Morid, V. Smakhtin, and M. Moghaddasi, “Comparison of seven meteorological indices for drought monitoring in Iran,” International Journal of Climatology, vol. 26, no. 7, pp. 971–985, 2006.
[45]
J. Adamowski and H. F. Chan, “A wavelet neural network conjunction model for groundwater level forecasting,” Journal of Hydrology, vol. 407, no. 1–4, pp. 28–40, 2011.
[46]
M. ？imen, “Estimation of daily suspended sediments using support vector machines,” Hydrological Sciences Journal, vol. 53, no. 3, pp. 656–666, 2008.
[47]
A. J. Smola, Regression Estimation with Support Vector Learning Machines [M.S. thesis], Technische Universitat Munchen, Munich, Germany, 1996.
[48]
S. Gunn, “Support vector machines for classification and regression,” ISIS Technical Report, Department of Electronics and Computer Science, University of Southampton, 1998.
[49]
B. Cannas, A. Fanni, G. Sias, S. Tronci, and M. K. Zedda, “River flow forecasting using neural networks and wavelet analysis,” in Proceedings of the European Geosciences Union, 2006.
[50]
S. G. Mallat, A Wavelet Tour of Signal Processing, Academic Press, San Diego, Calif, USA, 1998.
[51]
F. Murtagh, J. L. Starck, and O. Renuad, “On neuro-wavelet modeling,” Decision Support Systems, vol. 37, no. 4, pp. 475–484, 2004.
[52]
O. Renaud, J. Starck, and F. Murtagh, Wavelet-Based Forecasting of Short and Long Memory Time Series, Department of Economics, University of Geneve, 2002.
[53]
C. E. Desalegn, M. S. Babel, A. Das Gupta, B. A. Seleshi, and D. Merrey, “Farmers' perception of water management under drought conditions in the upper Awash Basin, Ethiopia,” International Journal of Water Resources Development, vol. 22, no. 4, pp. 589–602, 2006.
[54]
D. C. Edossa, M. S. Babel, and A. D. Gupta, “Drought analysis in the Awash River Basin, Ethiopia,” Water Resources Management, vol. 24, no. 7, pp. 1441–1460, 2010.
[55]
M. K. Tiwari and C. Chatterjee, “Development of an accurate and reliable hourly flood forecasting model using wavelet-bootstrap-ANN (WBANN) hybrid approach,” Journal of Hydrology, vol. 394, no. 3-4, pp. 458–470, 2010.
[56]
N. Wanas, G. Auda, M. S. Kamel, and F. Karray, “On the optimal number of hidden nodes in a neural network,” in Proceedings of the 11th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE '98), pp. 918–921, May 1998.
[57]
J. C. Principe, N. R. Euliano, and W. Curt Lefebvre, Neural and Adaptive Systems, John Wiley & Sons, 2000.
[58]
T. Partal, “Modelling evapotranspiration using discrete wavelet transform and neural networks,” Hydrological Processes, vol. 23, no. 25, pp. 3545–3555, 2009.
[59]
F. Parrella, Online support vector regression [M.S. thesis], University of Genoa, 2007.
