Precipitation Forecast Using Artificial Neural Networks in Specific Regions of Greece

In recent years, significant changes in precipitation regimes have been observed and these manifest in socio economic and ecological problems especially in regions with increased vulnerability such as the Mediterranean region. For this reason, it is necessary to estimate the future projected precipitation on short and long-term basis by analyzing long time series of observed station data. In this study, an effort was made in order to forecast the monthly maximum, minimum, mean and cumulative precipitation totals within a period of the next four consecutive months, using Artificial Neural Networks (ANNs). The precipitation datasets concern monthly totals recorded at four meteorological stations (Alexandroupolis, Thessaloniki, Athens, and Patras), in Greece. For the evaluation of the results and the ability of the developed prognostic models, appropriate statistical indexes such as the coefficient of determination (R2), the index of agreement (IA) and the root mean square error (RMSE) were used. The findings from this analysis showed that the ANN’s methodology provides satisfactory precipitation totals in four consecutive months and these results are better results, than those obtained using classical statistical methods. A fairly good consistency between the observed and the predicted precipitation totals at a statistical significance level of p < 0.01 for the most of the examined cases has been revealed. More specifically, the Index of Agreement (IA) ranges between 0.523 and 0.867 and the coefficient of determination (R2) ranges between 0.141 and 0.603. The most accurate forecasts concern the mean monthly and the cumulative precipitation for the next four consecutive months.

[1]  N. Rashevsky.  Outline of a new mathematical approach to general biology: I , 1943 .

[2]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[3]  C. Willmott.  Some Comments on the Evaluation of Model Performance , 1982 .

[4]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Robert E. Davis,et al.  Statistics for the evaluation and comparison of models , 1985 .

[6]  C. Repapis.  Temporal fluctuations of precipitation in Greece , 1986 .

[7]  J J Hopfield,et al.  Learning algorithms and probability distributions in feed-forward and feed-back networks. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[8]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[9]  Maureen Caudill,et al.  Understanding Neural Networks; Computer Explorations , 1992 .

[10]  T. Fuchs,et al.  Beobachtete Klimatrends in Europa 1891-1990 , 1994 .

[11]  Zwick Astrid,et al.  Climate Sensitivity Analysis Using Neural Networks , 1996 .

[12]  A. Comrie.  Comparing Neural Networks and Regression Models for Ozone Forecasting , 1997 .

[13]  M. Colacino,et al.  Signals of climatic change in the Central-Western Mediterranean basin , 1997 .

[14]  P. Nastos,et al.  Variability of precipitation pattern in Greece during the year , 1999 .

[15]  C. Guerreiro,et al.  Air pollution exposure monitoring and estimation. Part II. Model evaluation and population exposure. , 1999, Journal of environmental monitoring : JEM.

[16]  A. K. Sahai,et al.  All India summer monsoon rainfall prediction using an artificial neural network , 2000 .

[17]  Ashish Sharma,et al.  A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting , 2000 .

[18]  John A. Dracup,et al.  Artificial Neural Networks and Long-Range Precipitation Prediction in California , 2000 .

[19]  L. Bodri,et al.  Prediction of extreme precipitation using a neural network: application to summer flood occurence in Moravia , 2000 .

[20]  D. Melas,et al.  Neural Network Model for Predicting Peak Photochemical Pollutant Levels , 2000, Journal of the Air & Waste Management Association.

[21]  M. Kolehmainen,et al.  Neural networks and periodic components used in air quality forecasting , 2001 .

[22]  F. Chauvin,et al.  Sensitivity of the hydrological cycle to increasing amounts of greenhouse gases and aerosols , 2002 .

[23]  K. Trenberth,et al.  The changing character of precipitation , 2003 .

[24]  Hikmet Kerem Cigizoglu,et al.  Rainfall-Runoff Modelling Using Three Neural Network Methods , 2004, ICAISC.

[25]  H. Feidas,et al.  Trend analysis of precipitation time series in Greece and their relationship with circulation using surface and satellite data: 1955–2001 , 2004 .

[26]  Jörg H. Siekmann,et al.  Artificial Intelligence and Soft Computing - ICAISC 2004 , 2004, Lecture Notes in Computer Science.

[27]  Michele Brunetti,et al.  Changes in daily precipitation frequency and distribution in Italy over the last 120 years , 2004 .

[28]  F. Zwiers,et al.  On the role of statistics in climate research , 2004 .

[29]  Neil I. Fox,et al.  Very short period quantitative precipitation forecasting , 2005 .

[30]  Akira Kawamura,et al.  Medium term forecasting of rainfall using artificial neural networks , 2005 .

[31]  C. Anagnostopoulou,et al.  Cyclones in the Mediterranean region: present and future climate scenarios derived from a general circulation model (HadAM3P) , 2006 .

[32]  Slobodan P. Simonovic,et al.  An Intelligent Decision Support System for Management of Floods , 2006 .

[33]  N. J. Ferreira,et al.  Linear and Nonlinear Statistical Downscaling for Rainfall Forecasting over Southeastern Brazil , 2006 .

[34]  C. Zerefos,et al.  On extreme daily precipitation totals at Athens, Greece , 2007 .

[35]  Silas Michaelides,et al.  Preface "Observation, Prediction and Verification of Precipitation" , 2007 .

[36]  A. Altunkaynak.  Forecasting Surface Water Level Fluctuations of Lake Van by Artificial Neural Networks , 2007 .

[37]  Dimitrios Melas,et al.  Development and Assessment of Neural Network and Multiple Regression Models in Order to Predict PM10 Levels in a Medium-sized Mediterranean City , 2007 .

[38]  C. Zerefos,et al.  Decadal changes in extreme daily precipitation in Greece , 2008 .

[39]  Thinn Thu Naing,et al.  Optimum Neural Network Architecture for Precipitation Prediction of Myanmar , 2008 .

[40]  K. P. Moustris,et al.  24 hours in advance forecasting of thermal comfort-discomfort levels during the hot period of the year at representative locations of Athens city, Greece. , 2009 .

[41]  Gabriel Ibarra-Berastegi,et al.  Evaluation of statistical downscaling in short range precipitation forecasting , 2009 .

[42]  C. Zerefos,et al.  Spatial and temporal variability of consecutive dry and wet days in Greece , 2009 .

[43]  Vahid Nourani,et al.  A Multivariate ANN-Wavelet Approach for Rainfall–Runoff Modeling , 2009 .

[44]  Statistical Downscaling Forecasts for Winter Monsoon Precipitation in Malaysia Using Multimodel Output Variables , 2010 .

[45]  K. P. Sudheer,et al.  Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India , 2010 .

[46]  Athanasios G. Paliatsos,et al.  Study of the rain intensity in Athens and Thessaloniki, Greece , 2010 .

[47]  Taesoon Kim,et al.  Monthly Precipitation Forecasting with a Neuro-Fuzzy Model , 2012, Water Resources Management.