Multi-time-scale analysis of hydrological drought forecasting using support vector regression (SVR) and artificial neural networks (ANN)

In this study, the preprocessing of the gamma test was used to select the appropriate input combination into two models including the support vector regression (SVR) model and artificial neural networks (ANNs) to predict the stream flow drought index (SDI) of different timescales (i.e., 3, 6, 9, 12, and 24 months) in Latian watershed, Iran, which is one of the most important sources of water for the large metropolitan Tehran. The variables used included SDIt, SDIt − 1, SDIt − 2, SDIt − 3, and SDIt − 4 monthly delays. Two variables including SDIt and SDIt − 1 with lower gamma values were identified as the most optimal combination of variables in all drought timescales. The results showed that the gamma test was able to correctly identify the right combination for the forecasting of 6, 9, and 12 months SDI using the ANN model. Also, the gamma test was considered in selecting the appropriate inputs for identifying the values of 9, 12, and 24 months SDI in SVR. The support vector machine approach showed a better efficiency in the forecast of long-term droughts compared to the artificial neural network. In total, among forecasts made for 30 scenarios, the support vector machine model only in scenario 3 of SDI3, scenario 1 of SDI6, and scenarios 2 and 3 of SDI24 represented poorer efficiency compared to the artificial neural network (MLP layer), but in other scenarios, the results of SVR had better efficiency.

[1]  R. Noori,et al.  Uncertainty analysis of streamflow drought forecast using artificial neural networks and Monte‐Carlo simulation , 2014 .

[2]  Nenad Koncar,et al.  A note on the Gamma test , 1997, Neural Computing & Applications.

[4]  Ozgur Kisi,et al.  A wavelet-support vector machine conjunction model for monthly streamflow forecasting , 2011 .

[5]  Dawei Han,et al.  Evaporation Estimation Using Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Techniques , 2009 .

[6]  Richard M. Vogel,et al.  PROBABILITY DISTRIBUTION OF ANNUAL MAXIMUM, MEAN, AND MINIMUM STREAMFLOWS IN THE UNITED STATES , 1996 .

[7]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[8]  I-Fan Chang,et al.  Support vector regression for real-time flood stage forecasting , 2006 .

[9]  Miklas Scholz,et al.  Sensitivity of surface runoff to drought and climate change : application for shared river basins , 2014 .

[10]  Hossein Tabari,et al.  MLP-based drought forecasting in different climatic regions , 2012, Theoretical and Applied Climatology.

[11]  Jimson Mathew,et al.  Hydrological Data Driven Modelling: A Case Study Approach , 2015 .

[12]  S. Morid,et al.  Drought forecasting using artificial neural networks and time series of drought indices , 2007 .

[13]  Aman Mohammad Kalteh,et al.  Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform , 2013, Comput. Geosci..

[14]  Sergio M. Vicente-Serrano,et al.  Accurate Computation of a Streamflow Drought Index , 2012 .

[15]  F. Vanclay,et al.  The social experience of drought in rural Iran , 2013 .

[16]  M. Çimen,et al.  Estimation of daily suspended sediments using support vector machines , 2008 .

[17]  M. Janga Reddy,et al.  Ensemble prediction of regional droughts using climate inputs and the SVM–copula approach , 2014 .

[18]  V. Vapnik.  Pattern recognition using generalized portrait method , 1963 .

[19]  Keith Beven,et al.  A manifesto for the equifinality thesis , 2006 .

[20]  Gwo-Fong Lin,et al.  Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self‐organizing map , 2014 .

[21]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[22]  A Hezarjaribi,et al.  EVALUATION EFFECT OF INPUT PARAMETERS PREPROCESSING IN ARTIFICIAL NEURAL NETWORKS (ANNS) BY USING STEPWISE REGRESSION AND GAMMA TEST TECHNIQUES FOR FAST ESTIMATION OF DAILY EVAPOTRANSPIRATION , 2010 .

[23]  Fi-John Chang,et al.  Modeling water quality in an urban river using hydrological factors--data driven approaches. , 2015, Journal of environmental management.

[24]  Vijay P. Singh,et al.  Long Lead Time Drought Forecasting Using a Wavelet and Fuzzy Logic Combination Model: A Case Study in Texas , 2012 .

[25]  Donald A. Wilhite,et al.  The Enigma of Drought , 1993 .

[26]  Ali Danandeh Mehr,et al.  A gene-wavelet model for long lead time drought forecasting , 2014 .

[27]  J. Adamowski.  Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis , 2008 .

[28]  Jan Adamowski,et al.  Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS , 2014, Expert Syst. Appl..

[29]  Jan Adamowski,et al.  Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models , 2014 .

[30]  Mohammad Karamouz,et al.  Input data selection for solar radiation estimation , 2009 .

[31]  A. Sutera,et al.  Drought Monitoring and Forecasting at Large Scale , 2007 .

[32]  U. Panu,et al.  Predicting return periods of hydrological droughts using the Pearson 3 distribution: a case from rivers in the Canadian prairies , 2015 .

[33]  I. Nalbantis.  Evaluation of a Hydrological Drought Index , 2009 .

[34]  MohammadSajjad Khan,et al.  Application of Support Vector Machine in Lake Water Level Prediction , 2006 .

[35]  Zoran Kapelan,et al.  Comparing Low and High-Level Hybrid Algorithms on the Two-Objective Optimal Design of Water Distribution Systems , 2014, Water Resources Management.

[36]  A. Ahmadi,et al.  Daily suspended sediment load prediction using artificial neural networks and support vector machines , 2013 .

[37]  V. Singh,et al.  Drought Forecasting Using a Hybrid Stochastic and Neural Network Model , 2007 .

[38]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[39]  Emmanuel Nkoro Asagha,et al.  Modeling and Simulation of Global Solar Radiation in Warri, Nigeria Using Gamma Test and Artificial Neural Network Algorithms , 2014 .

[40]  X. Wen,et al.  Wavelet Analysis-Support Vector Machine Coupled Models for Monthly Rainfall Forecasting in Arid Regions , 2015, Water Resources Management.

[41]  George Tsakiris,et al.  Assessment of Hydrological Drought Revisited , 2009 .

[42]  V. Singh,et al.  A review of drought concepts , 2010 .

[43]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[44]  Dawei Han,et al.  Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction , 2011 .