Spring drought forecasting in mainland Portugal based on large-scale climatic indices

[EN] The success of a strategy of mitigation of the effects of the droughts requires the implementation of an effective monitoring and forecasting system, able to identify drought events and follow their spatiotemporal evolution. This article demonstrates the capability of the artificial neural networks in predicting the spring standardized precipitation index, SPI, for Portugal. The validation of the models used the hindcasting, which is a technique by which a given model is tested through its application to historical data followed by the comparison of the results thus achieved with the data. The SPI index was calculated at the timescale of six months and the climate indices used as external predictors in the hindcasting were the North Atlantic Oscillation and temperatures of the sea surface. The study showed the added value of the inclusion of previous predictors in the model. Maps of the probabilities of the drought occurrences which may be very important for integrated planning and management of water resources were also developed.[PT] O sucesso de uma estratégia de mitigação dos efeitos da seca passa pela implementação de um sistema de monitorização e previsão eficaz, capaz de identificar os eventos de seca e de seguir a sua evolução espácio-temporal. Neste artigo demonstrase a eficiência de redes neuronais artificiais na previsão, para Portugal, do índice de precipitação padronizada, SPI, relativo à primavera. A validação dos modelos recorreu ao hindcasting, designando-se, por tal, a técnica através da qual um dado modelo é testado mediante a sua aplicação a períodos temporais históricos, com comparação dos resultados obtidos com as respectivas observações. O índice SPI foi calculado à escala temporal de 6 meses tendo o hindcast utilizado como indicadores climáticos a oscilação do Atlântico Norte e temperaturas da superfície do mar. O estudo evidenciou a mais valia da inclusão dos anteriores predictores externos no modelo de previsão. Elaboraram-se, ainda, mapas de probabilidade de ocorrência de seca os quais constituem importantes ferramentas no planeamento integrado e na gestão de recursos hídricosSantos, J.; Portela, M.; Pulido-Calvo, I. (2015). Previsão de secas na primavera em Portugal Continental com base em indicadores climáticos de larga escala. Ingeniería del Agua. 19(4):211-227. doi:10.4995/ia.2015.4109.211227194Agnew, C.T. (2000). Using the SPI to identify drought. Drought Network News, 12, 6-12.ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000a). Artificial neural networks in hydrology. I. Preliminary concepts. Journal of Hydrologic Engineering, 5(2), 115-123. doi:10.1061/(ASCE)1084-0699(2000)5:2(115)ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000b). Artificial neural networks in hydrology. II. Hydrologic applications. Journal of Hydrologic Engineering, 5(2), 124-137. doi:10.1061/(ASCE)1084-0699(2000)5:2(124)Bordi, I., Fraedrich, K., Petitta, M., Sutera, A. (2005). Methods for predicting drought occurrences. In Proceedings of the 6th International Conference of the European Water Resources Association, Menton, France.Bowden, G.J., Dandy, G.C., Maier, H.R. (2005). Input determination for neural network models in water resources applications. Part 1-background and methodology. Journal of Hydrology, 301(1-4), 75-92. doi:10.1016/j.jhydrol.2004.06.021Campolo, M., Andreusi, P., Soldati, A. (1999). River flood forecasting with a neural network model. Water Resources Research, 35(4), 1191-1197. doi:10.1029/1998WR900086Cancelliere, A., Di Mauro, G., Bonaccorso, B., Rossi, G. (2005). Stochastic forecasting of Standardized Precipitation Index. In Proceedings of XXXI IAHR Congress Water Engineering for the future: Choice and Challenges, Seoul, Korea, 3252-3260.Cancelliere, A., Di Mauro, G., Bonaccorso, B., Rossi, G. (2007). Drought forecasting using the Standardized Precipitation Index. Water Resources Management, 21(5), 801-819. doi:10.1007/s11269-006-9062-yCordery, I., McCall, M. (2000). A model for forecasting drought from teleconnections. Water Resources Research, 36(3), 763-768. doi:10.1029/1999WR900318Dastorani, M.T., Afkhami, H. (2011). Application of artificial neural networks on drought prediction in Yazd (Central Iran). Desert, 16, 39-48.Dawson, D.W., Wilby, R. (1998). An artificial neural network approach to precipitation-runoff modeling. Hydrological Sciences Journal, 43(1), 47-66. doi:10.1080/02626669809492102Demyanov, V., Kanevsky, M., Chernov, S., Savelieva, E., Timonin, V. (1998). Neural network residual kriging application for climatic data. Journal of Geographic Information and Decision Analysis, 2(2), 215-232.Di Mauro, G., Bonaccorso, G.B., Cancelliere, A., Rossi, G. (2008). Use of NAO index to improve drought forecasting in the Mediterranean area: Application to Sicily region. Options Méditerranéennes. Série A: Séminaires Méditerranéens, No. 80.Fernando, M.K.G., Maier, H.R., Dandy, G.C. (2009). Selection of input variables for data driven models: An average shifted histogram partial mutual information estimator approach. Journal of Hydrology, 367(3-4), 165-176. doi:10.1016/j.jhydrol.2008.10.019Gámiz-Fortis, S., Esteban-Parra, M.J., Trigo, R.M., Castro-Díez, Y. (2010). Potential predictability of Iberian river flow based on its relationship with previous winter global SST. Journal of Hydrology, 385, 143-149. doi:10.1016/j.jhydrol.2010.02.010Gámiz-Fortis, S., Pozo-Vázquez, D., Trigo, R.M., Castro-Díez, Y. (2008a). Quantifying the predictability of winter river flow in Iberia. Part I: Interannual predictability. Journal of Climate, 21, 2484-2502. doi:10.1175/2007JCLI1774.1Gámiz-Fortis, S., Pozo-Vázquez, D., Trigo, R.M., Castro-Díez, Y. (2008b). Quantifying the predictability of winter river flow in Iberia. Part II: Seasonal predictability. Journal of Climate, 21, 2503-2518. doi:10.1175/2007JCLI1775.1Hoerling, M., Kumar, A. (2003). The perfect ocean for drought. Science, 299(5607), 691-694. Geophysical Research Abstracts, 12, EGU2010-8454, EGU General Assembly 2010, Viena, Austria. doi:10.1126/science.1079053Hurrell, J.W. (1995). Decadal trends in North Atlantic Oscillation: regional temperatures and precipitation. Science, 269(5224), 676-679. doi:10.1126/science.269.5224.676Hurrell, J.W., Kushnir, Y., Visbeck, M. (2001). The North Atlantic Oscillation. Science, 291(5504), 603-605. doi:10.1126/science.1058761Hurrell, J.W., Kushnir, Y., Ottersen, G., Visbeck, M. (2003). The North Atlantic Oscillation: climatic significance and environmental impact. Geophysical Monograph Series, 134, American Geophysical Union, Washington, DC, USA.Ionita, M., Lhomann, G., Rimbu, N. (2008). Prediction of spring Elbe discharge based on stable teleconnections with winter global temperature and precipitation. Journal of Climate, 21(23), 6215-6226. doi:10.1175/2008JCLI2248.1Ionita, M., Lohmann, G., Rimbu, N., Chelcea, S., Dima, M. (2012). Interannual to decadal summer drought variability over Europe and its relationship to global sea surface temperature. Climate Dynamics, 38(1), 363-377. doi:10.1007/s00382-011-1028-yIyer, M.S., Rhinehart, R.R. (1999). A method to determine the required number of neural-network training repetitions. IEEE Transactions on Neural Networks, 10(2), 427-432. doi:10.1109/72.750573Jain, A., Kumar, A.M. (2007). Hybrid neural network models for hydrologic time series forecasting. Applied Soft Computing, 7(2), 585-592. doi:10.1016/j.asoc.2006.03.002Jones, P.D., Jonsson, T., Wheeler, D. (1997). Extension to the North Atlantic Oscillation using early instrumental pressure observations from Gibraltar and South-West Iceland. International Journal of Climatology, 17(13), 1433-1450. doi:10.1002/(SICI)1097-0088(19971115)17:133.0.CO;2-PJones, P.D., Osborn, T.J., Briffa, K.R. (2003). Pressure-based measures of the North Atlantic oscillation (NAO): a comparison and an assessment of changes in the strength of the NAO and in its influence on surface climate parameters in The North Atlantic Oscillation: climate significance and environmental impact. Geophysics Monogram 134, 51-62, American Geophysical Union.Karunanithi, N., Grenney, W.J., Whitely, D., Bovee, K. (1994). Neural networks for river flow prediction. Journal of Computing Civil Engineering, 8(2), 201-219. doi:10.1061/(ASCE)0887-3801(1994)8:2(201)Kim T. e Juan B. Valdés, (2003). Nonlinear Model for Drought Forecasting Based on a Conjunction of Wavelet Transforms and Neural Networks. Journal of Hydrologic Engineering, 8(6), 319-328. doi:10.1061/(ASCE)1084-0699(2003)8:6(319)Kitanidis, P.K., Bras, R.L. (1980). Real time forecasting with a conceptual hydrological model. 2. Applications and results. Water Resources Research, 16(6), 1034-1044. doi:10.1029/WR016i006p01034Kurnik, B. (2009). DESERT Action JRC, Drought forecasting methods. Ljubljana on 24 September 2009 - 1st DMCSEE - JRC Workshop on Drought Monitoring.Legates, D.R., McCabe Jr., G.J. (1999). Evaluating the use of 'goodness-of-fit' measures in hydrologic and hydroclimatic model validation. Water Resources Research, 35(1), 233-241. doi:10.1029/1998WR900018Lloyd-Hughes, B. (2002). The long range predictability of European drought. PhD Thesis, Department of Space and Climate Physics, University of London, University College London, UK.López-Moreno, J.I., Vicente-Serrano, S.M. (2008). Extreme phases of the wintertime North Atlantic Oscillation and drought occurrence over Europe: a multi-temporal-scale approach. Journal of Climate, 21(6), 1220-1243. doi:10.1175/2007JCLI1739.1López-Moreno, J.I., Beguería, S., Vicente-Serrano, S.M., García-Ruiz, J.M. (2007). The influence of the NAO on water resources in central Iberia: precipitation, streamflow anomalies and reservoir management strategies. Water Resources Research, 43,W09411, doi:10.1029/2007WR005864Martín, M.L., Luna, M.Y., Morata, A., Valero, F. (2004). North Atlantic teleconnection patterns of low-frequency variability and their links with springtime precipitation in the western Mediterranean. International Journal of Climatology, 24(2), 213-230. doi:10.1002/joc.993Martín-Vide, J., Fernández, D. (2001). El índice NAO y la precipitación mensual en la España peninsular. Investigaciones Geográficas, 26, 41-58. doi:10.14198/INGEO2001.26.07May, R.J., Maier, H.R., Dandy, G.C., Fernando, T.M.K.G. (2008). Non-linear variable selection for artificial neural networks using partial mutual information. Environmental Modelling and Software, 23(10-11), 1312-1326. doi:10.1016/j.envsoft.2008.03.007McKee, T.B., Doesken, N.J., Kleist, J. (1993).The relationship of drought frequency and duration to time scales. In: Proceedings of the 8th Conference on Applied Climatology. American Meteorological Society, Boston, USA, 179-184.Mishra, A.K., Desai, V.R. (2006). Drought forecasting using feed-forward recursive neural network. Ecological Modelling, 198(1-2), 127-138. doi:10.1016/j.ecolmodel.2006.04.017Mo, K.C., Jae-Kyung, E., Schemm, E., Yoo, S.-H. (2009). Influence of ENSO and the Atlantic multi-decadal Oscillation on drought over the United States. Journal of Climate, 22, 5962-5982. doi:10.1175/2009JCLI2966.1Mutlu, E., Chaubey, I., Hexmoor, H., Bajwa, S.G. (2008). Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed. Hydrological Processes, 22(26), 5097-5106. doi:10.1002/hyp.7136Michie, D., Spiegelhalter, D.J., Taylor, C.C. (1994). Machine learning, neural and statistical classification. Project StatLog, Department of Statistics, University of Leeds, UK.Ochoa-Rivera, J.C., García-Bartual, R., Andreu, J. (2002). Multivariate synthetic streamflow generation using a hybrid model based on artificial neural networks. Journal of Hydrology and Earth System Sciences, 6(4), 641-654. doi:10.5194/hess-6-641-2002Ochoa-Rivera, J.C., García-Bartual, R., Andreu, J. (2007). Influence of Inflows Modeling on Management Simulation of Water Resources System. Journal of Water Resources Planning and Management, ASCE, 133(2), 106-116. doi:10.1061/(ASCE)0733-9496(2007)133:2(106)Portela, M.M., Quintela, A.C. (2006). Estimação em Portugal Continental de escoamento e de capacidades úteis de albufeiras de regularização na ausência de informação. Recursos Hídricos, 27(2), 7-18.Pulido-Calvo, I., Portela, M.M. (2007). Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds. Journal of Hydrology, 332(1-2), 1-15. doi:10.1016/j.jhydrol.2006.06.015Pulido-Calvo, I., Gutiérrez-Estrada, J.C., Savic, D. (2012). Heuristic modelling of the water resources management in the Guadalquivir River Basin, Southern Spain. Water Resources Management, 26(1), 185-209. doi:10.1007/s11269-011-9912-0Qian, B., Corte-Real, J.M., Xu, H. (2000a). Is the North Atlantic Oscillation the most important atmospheric pattern for precipitation in Europe? Journal of Geophysical Research, 105(D9), 901-910. doi:10.1029/2000JD900102Qian, B., Xu, H., Corte-Real, J.M. (2000b). Spatial-temporal structures of the quasi-periodic oscillations in precipitation over Europe. International Journal of Climatology, 20(13), 1583-1598. doi:10.1002/1097-0088(20001115)20:133.0.CO;2-YRodwell, M.J. (2003). On the predictability of the North Atlantic climate. The North Atlantic Oscillation: climate significance and environmental impact, Geophysical Monograph, 134, 173-192, Amer. Geophys. Union. doi:10.1029/134GM08Rossi, G. (2003). Requisites for a drought watch system. In: G. Rossi et al. (eds), Tools for Drought Mitigation in Mediterranean Regions, pp. 147-157. Kluwer Academic Publishing: Dordrecht. doi:10.1007/978-94-010-0129-8_9Rumelhart, D.E., Hinton, G.E., Williams, R.J. (1986). Learning representations by back-propagating errors. Nature, 323, 533-536. doi:10.1038/323533a0Santos, J.A., Corte-Real, J., Leite, S.M. (2005). Weather regimes and their connection to the winter precipitation in Portugal. International Journal of Climatology, 25(1), 33-50. doi:10.1002/joc.1101Santos, J.F., Portela, M.M., Pulido-Calvo, I. (2011). Regional frequency analysis of droughts in Portugal. Water Resources Management, 25(14), 3537-3558. doi:10.1007/s11269-011-9869-zSantos, J.F., Portela, M.M., Pulido-Calvo, I. (2013). Dimensionality reduction in drought modelling. Hydrological Processes, 27(10), 1399-1410. doi:10.1002/hyp.9300Santos, J.F., Portela, M.M., Pulido-Calvo, I., (2014). Spring drought prediction based on winter NAO and global SST in Portugal, Hydrological Processes, 28(3), 1009-1024. doi:10.1002/hyp.9641Santos, J.F., Pulido-Calvo, I., Portela, M.M. (2010). Spatial and temporal variability of droughts in Portugal. Water Resources Research, 46(3). DOI: 10.1029/2009WR008071. doi:10.1029/2009WR008071Senthil-Kumar, A.R., Sudheer, K.P., Jain, S.K., Agarwal, P.K. (2005). Rainfall-runoff modelling using artificial neural networks: comparison of network types. Hydrological Processes, 19(6), 1277-1291. doi:10.1002/hyp.5581Silva, A.T., Portela, M.M., Naghettini, M. (2012), Nonstationarities in the occurrence rates of flood events in Portuguese watersheds. Journal of Hydrology and Earth System Sciences, 16, 241-254. doi:10.5194/hess-16-241-2012Smith, T.M., Reynolds, R.W., Peterson, T.C. Lawrimore, J. (2008). Improvements to NOAA's Historical Merged Land-Ocean Surface Temperature Analysis (1880-2006). Journal of Climate, 21, 2283-2296. doi:10.1175/2007JCLI2100.1Snedecor, G.W., Cochran, W.G. (1989). Statistical methods, Ames, Iowa State University Press (8th edition), Iowa, USA.Trigo, R.M., Osborn, T.J., Corte-Real, J.M. (2002). The North Atlantic Oscillation influence on Europe. Climate impacts and associated physical mechanisms. Climate Research, 20, 9-17. doi:10.3354/cr020009Trigo, R.M., Pozo-Vázquez, D., Osborn, T.J., Castro-Díez, Y., Gámiz-Fortis, S., Esteban-Parra, M.J. (2004). North Atlantic Oscillation influence on precipitation, river flow and water resources in the Iberian Peninsula. International Journal of Climatology, 24(8), 925-944. doi:10.1002/joc.1048Trigo, R., Xoplaki, E., Zorita, E., Luterbacher, J., Krichak, S.O., Alpert, P., Jacobeit, J., Sáenz, J., Fernández, J., González-Rouco, F., García-Herrera, R., Rodo, X., Brunetti, M., Nanni, T., Maugeri, M., Trkes, M., Gimeno, L., Ribera, P., Brunet, M., Trigo, I.F., Crepon, M., Mariotti, A. (2006). Relations between Variability in the Mediterranean region and mid-latitude variability. In: Mediterranean Climate Variability, edited by: Lionello P., Malanotte-Rizzoli P., e R. Boscolo. Amsterdam, Elsevier, 179-226. doi:10.1016/s1571-9197(06)80006-6Vicente-Serrano, S.M., López-Moreno, J.I., Lorenzo-Lacruz, J., El Kenawy, A., Azorin-Molina, C., Morán-Tejeda, E., Pasho, E., Zabalza, J., Beguería, S., Angulo-Martínez, M. (2011). The NAO impact on droughts in the Mediterranean region. In: VicenteSerrano S.M. e Trigo R. (Eds.), Hydrological, socioeconomic and ecological impacts of the North Atlantic Oscillation in the Mediterranean region. Advances in Global Research (AGLO) series, Springer-Verlag. doi:10.1007/978-94-007-1372-7_3Vinther, B.M., Andersen, K.K., Hansen, A.W., Schmith, T., Jones, P.D. (2003). Improving the Gibraltar/Reykjavik NAO Index. Geophysical Research Letters, 30(23), 2222. doi:10.1029/2003GL018220Xoplaki E., González-Rouco J.F., Luterbacher J. e H. Wanner, (2004). Wet season Mediterranean precipitation variability: influence of large-scale dynamics and predictability. Climate Dynamiques 23, 63-78.Xue, Y., Smith, T.M., Reynolds, R.W. (2003). Interdecadal changes of 30-yr SST normals during 1871-2000. Journal of Climate, 16, 1601-1612. doi:10.1175/1520-0442-16.10.1601Yevjevich, V. (1972). Stochastic Processes in Hydrology. Water Resources Publications, Fort Collins, Co