Short-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet transforms and machine learning methods

Droughts can cause significant damage to agricultural and other systems. An important aspect of mitigating the impacts of drought is an effective method of forecasting future drought events. In this study, five methods of forecasting drought for short lead times were explored in the Awash River Basin of Ethiopia. The Standard Precipitation Index (SPI) was the drought index chosen to represent drought in the basin. Machine learning techniques including artificial neural networks (ANNs) and support vector regression (SVR) were compared with coupled models (WA-ANN and WA-SVR) which pre-process input data using wavelet analysis (WA). This study proposed and tested the SVR and WA-SVR methods for short term drought forecasting. This study also used only the approximation series (derived via wavelet analysis) as inputs to the ANN and SVR models, and found that using just the approximation series as inputs for models gave good forecast results. The forecast results of all five data driven models were compared using several performance measures (RMSE, MAE, R2 and a measure of persistence). The forecast results of this study indicate that the coupled wavelet neural network (WA-ANN) models were the best models for forecasting SPI 3 and SPI 6 values over lead times of 1 and 3 months in the Awash River Basin.

[1]  G. Di Mauro,et al.  Stochastic Forecasting of Drought Indices , 2007 .

[2]  Zhu Dehai,et al.  Drought Forecasting with Vegetation Temperature Condition Index , 2010 .

[3]  J. Michaelsen,et al.  Developing seasonal rainfall scenarios for food security early warning , 2013, Theoretical and Applied Climatology.

[4]  A. Mishra,et al.  Drought forecasting using stochastic models , 2005 .

[5]  Thian Yew Gan,et al.  Drought indices and their application to East Africa , 2003 .

[6]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[7]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[8]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[9]  Chandranath Chatterjee,et al.  Development of an accurate and reliable hourly flood forecasting model using wavelet–bootstrap–ANN (WBANN) hybrid approach , 2010 .

[10]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[11]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[12]  Alessandra Fanni,et al.  River flow forecasting using neural networks and wavelet analysis , 2005 .

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

[14]  Jan Adamowski,et al.  Development of a new method of wavelet aided trend detection and estimation , 2009 .

[15]  Stuart N. Lane,et al.  Assessment of rainfall‐runoff models based upon wavelet analysis , 2007 .

[16]  V. Singh,et al.  Simulating Hydrological Drought Properties at Different Spatial Units in the United States Based on Wavelet-Bayesian Regression Approach , 2012 .

[17]  null null,et al.  Artificial Neural Networks in Hydrology. II: Hydrologic Applications , 2000 .

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

[19]  Mahmut Firat,et al.  Adaptive Neuro-Fuzzy Inference System for drought forecasting , 2009 .

[20]  L. S. Pereira,et al.  Stochastic Prediction of Drought Class Transitions , 2008 .

[21]  Francesco Parrella.  Online Support Vector Regression , 2007 .

[22]  Mohammad Karamouz,et al.  Development of a Hybrid Index for Drought Prediction: Case Study , 2009 .

[23]  George Tsakiris,et al.  Towards a Drought Watch System based on Spatial SPI , 2004 .

[24]  B. Bonaccorso,et al.  Guidelines for Planning and Implementing Drought Mitigation Measures , 2007 .

[25]  Anteneh Meshesha Belayneh,et al.  Standard Precipitation Index Drought Forecasting Using Neural Networks, Wavelet Neural Networks, and Support Vector Regression , 2012, Appl. Comput. Intell. Soft Comput..

[26]  J. Adamowski,et al.  Juggling multiple dimensions in a complex socio-ecosystem: The issue of targeting in payments for ecosystem services , 2015 .

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

[28]  Jan Adamowski,et al.  Exploring the behavioural attributes, strategies and contextual knowledge of champions of change in the Canadian water sector , 2014 .

[29]  F. Murtagh,et al.  Wavelet-based Forecasting of Short and Long Memory Time , 2002 .

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

[31]  Mohamed S. Kamel,et al.  On the optimal number of hidden nodes in a neural network , 1998, Conference Proceedings. IEEE Canadian Conference on Electrical and Computer Engineering (Cat. No.98TH8341).

[32]  Mac McKee,et al.  Multi-time scale stream flow predictions: The support vector machines approach , 2006 .

[33]  Bernard Bobée,et al.  Daily reservoir inflow forecasting using artificial neural networks with stopped training approach , 2000 .

[34]  J. Adamowski,et al.  Assessing the Impacts of Four Land Use Types on the Water Quality of Wetlands in Japan , 2013, Water Resources Management.

[35]  Jan Adamowski,et al.  Urban water demand forecasting and uncertainty assessment using ensemble wavelet‐bootstrap‐neural network models , 2013 .

[36]  Jan Adamowski,et al.  Wavelet‐based multiscale performance analysis: An approach to assess and improve hydrological models , 2014 .

[37]  Ashim Das Gupta,et al.  Drought Analysis in the Awash River Basin, Ethiopia , 2010 .

[38]  Ozgur Kisi,et al.  Evapotranspiration modelling using support vector machines / Modélisation de l'évapotranspiration à l'aide de ‘support vector machines’ , 2009 .

[39]  Jan Adamowski,et al.  Trend detection in surface air temperature in Ontario and Quebec, Canada during 1967–2006 using the discrete wavelet transform , 2013 .

[40]  J. Adamowski,et al.  Forecasting Urban Water Demand Via Wavelet-Denoising and Neural Network Models. Case Study: City of Syracuse, Italy , 2012, Water Resources Management.

[41]  O. Kisi,et al.  Wavelet and neuro-fuzzy conjunction model for precipitation forecasting , 2007 .

[42]  T. McKee,et al.  THE RELATIONSHIP OF DROUGHT FREQUENCY AND DURATION TO TIME SCALES , 1993 .

[43]  N. Guttman.  ACCEPTING THE STANDARDIZED PRECIPITATION INDEX: A CALCULATION ALGORITHM 1 , 1999 .

[44]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[45]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[46]  J. Adamowski,et al.  A wavelet neural network conjunction model for groundwater level forecasting , 2011 .

[47]  J Halbe,et al.  Towards adaptive and integrated management paradigms to meet the challenges of water governance. , 2013, Water science and technology : a journal of the International Association on Water Pollution Research.

[48]  Juan B. Valdés,et al.  NONLINEAR MODEL FOR DROUGHT FORECASTING BASED ON A CONJUNCTION OF WAVELET TRANSFORMS AND NEURAL NETWORKS , 2003 .

[49]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[50]  Fionn Murtagh,et al.  On neuro-wavelet modeling , 2004, Decis. Support Syst..

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

[52]  Chuntian Cheng,et al.  A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series , 2009 .

[53]  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 .

[54]  Shiv O. Prasher,et al.  Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data , 2012 .

[55]  Ozgur Kisi,et al.  Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review , 2014 .

[56]  Rajib Maity,et al.  Potential of support vector regression for prediction of monthly streamflow using endogenous property , 2010 .

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

[58]  J. Adamowski,et al.  Influence of Trend on Short Duration Design Storms , 2010 .

[59]  M. A. Kohler,et al.  Hydrology for engineers , 1958 .

[60]  A. Mishra,et al.  Drought forecasting using feed-forward recursive neural network , 2006 .

[61]  Praveen Kumar,et al.  Coherent modes in multiscale variability of streamflow over the United States , 2000 .

[62]  Gavin J. Bowden,et al.  Toward long-lead operational forecasts of drought: An experimental study in the Murray-Darling River Basin , 2008 .

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

[64]  Jan Adamowski,et al.  Land use and land cover classification over a large area in Iran based on single date analysis of satellite imagery , 2011 .

[65]  R. V. Sachs,et al.  Wavelets in time-series analysis , 1999, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

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

[67]  G. Di Mauro,et al.  Forecasting Palmer Index Using Neural Networks and Climatic Indexes , 2009 .

[68]  L. S. Pereira,et al.  Drought class transition analysis through Markov and Loglinear models, an approach to early warning , 2005 .

[69]  Jan Adamowski,et al.  Using discrete wavelet transforms to analyze trends in streamflow and precipitation in Quebec and Ontario (1954–2008) , 2012 .

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

[71]  Ahmad Fatehi Marj,et al.  Agricultural drought forecasting using satellite images, climate indices and artificial neural network , 2011 .

[72]  J. Adamowski,et al.  Recasting payments for ecosystem services (PES) in water resource management: A novel institutional approach , 2014 .

[73]  Jan Adamowski,et al.  Erratum to: Forecasting Urban Water Demand Via Wavelet-Denoising and Neural Network Models. Case Study: City of Syracuse, Italy , 2012, Water Resources Management.

[74]  Jan Adamowski,et al.  Spatial and temporal trends of mean and extreme rainfall and temperature for the 33 urban centers of the arid and semi-arid state of Rajasthan, India , 2014 .

[75]  Jan Adamowski,et al.  Empowering marginalized communities in water resources management: addressing inequitable practices in Participatory Model Building. , 2015, Journal of environmental management.

[76]  Jan Adamowski,et al.  Using causal loop diagrams for the initialization of stakeholder engagement in soil salinity management in agricultural watersheds in developing countries: a case study in the Rechna Doab watershed, Pakistan. , 2015, Journal of environmental management.

[77]  V. Pavan,et al.  Monitoring and Forecasting Drought on a Regional Scale: Emilia-Romagna Region , 2007 .

[78]  Jan Adamowski,et al.  Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. , 2010 .