Meteorological drought analysis using data-driven models for the Lakes District, Turkey

Abstract

Droughts may be classified as meteorological, hydrological or agricultural. When meteorological drought appears in a region, agricultural and hydrological droughts follow. In this study, the standardized precipitation index (SPI) was applied for meteorological drought analysis at nine stations located around the Lakes District, Turkey. Analyses were performed on 3-, 6-, 9-and 12-month-long data sets. The SPI drought classifications were modelled by Adaptive Neural-Based Fuzzy Inference System (ANFIS) and Fuzzy Logic, which has the advantage that, in contrast to most of the time series modelling techniques, it does not require the model structure to be known a priori. Comparison of the observed values and the modelling results shows a better agreement with SPI-12 and ANFIS models than with fuzzy logic models.Key words drought; standardized precipitation index (SPI); adaptive neural-based fuzzy inference system (ANFIS); fuzzy logic; the Lakes District, TurkeyAnalyse des sécheresses météorologiques à l'aide de modèles conditionnés par les données dans la Région des Lacs, Turquie Résumé Les sécheresses peuvent être classées comme météorologiques, hydrologiques ou agricoles. Lorsqu'une sécheresse météorologique survient dans une région, elle est suivie par des sécheresses agricole et hydrologique. Dans cette étude, l'indice de précipitation standardisé SPI a été appliqué pour l'analyse des sécheresses météorologiques de neuf stations localisées dans la Région des Lacs, Turquie. L'analyse a été faite sur des séries de données longues de 3, 6, 9 et 12 mois. Les classifications de sécheresse basées sur l'indice SPI ont été modélisées par système adaptatif d'inférence floue à base neuronale (ANFIS) et par logique floue, qui a l'avantage, contrairement à la plupart des techniques de modélisation de séries temporelles, de ne pas requérir de connaître a priori la structure du modèle. La comparaison des valeurs observées et modélisées montre une meilleure correspondance avec les modèles SPI-12 et ANFIS qu'avec les modèles à base de logique floue.Mots clefs sécheresse; indice de précipitation standardisé (SPI); système adaptatif d'inférence floue à base neuronale (ANFIS); logique floue; Région des Lacs, Turquie

Comparison of multi-monthly rainfall-based drought severity indices, with application to semi-arid Konya closed basin, Turkey

“…Due to its rainfall-only data requirement, simplicity of calculations, decent reliability, and ability to address a variety of drought related issues, SPI has been used extensively in Turkey (Durdu, 2010;Keskin et al, 2009;Sonmez et al, 2005;Touchan et al, 2005;Turkes and Tatli, 2009), Mediterranean region (Lana and Burgueno, 2000;Lana et al, 2001;Paulo and Pereira, 2006;Salvati et al, 2009;Vicente-Serrano et al, 2004), United States (Budikova, 2008;Guttman, 1999;Hayes, 2000;Hayes et al, 1999;Heim, 2002;Keyantash and Dracup, 2002), and other parts of the world (Edossa et al, 2010;Mishra and Singh, 2009;Ntale and Gan, 2003;Pandey et al, 2008;Patel et al, 2007;Roudier and Mahe, 2010;Stricevic et al, 2011;Zhai et al, 2010).…”

Meteorological drought analysis using artificial neural networks

“…Keskin et al (2009) used ANFIS and fuzzy logic techniques for modeling drought. In this study, it is examined that ANN can be used to model drought.…”

“…In Turkey, total useable water amount reaches 110 billion m 3 which is the sum of annual mean stream flow and ground water potential. Considering that the population of Turkey is 70 million, about 1570 m 3 of water is available per capita annually, which indicates that in future Turkey may encounter serious problems especially in drought periods (Keskin et al, 2009). Türkeş (1999) examined regional and historical changes of precipitation and drought index series as climatic factors for 1930 to 1993.…”

Drought prediction using co-active neuro-fuzzy inference system, validation, and uncertainty analysis (case study: Birjand, Iran)

“…They proposed an approach to develop drought early warning index (DEWI) for southern Taiwan to detect the drought in advance for setting up proper plans to mitigate the water shortage impact. Similar work using adaptive neurofuzzy inference system (ANFIS) was carried out by Keskin et al (2009) for drought classification in Turkey. Bacanli et al (2009) employed ANFIS to forecast drought in Turkey.…”