Temporal Hydrological Drought Index Forecasting for New South Wales, Australia Using Machine Learning Approaches

Droughts can cause significant damage to agriculture and water resources leading to severe economic losses. One of the most important aspects of drought management is to develop useful tools to forecast drought events, which could be helpful in mitigation strategies. The recent global trends in drought events reveal that climate change would be a dominant factor in influencing such events. The present study aims to understand this effect for the New South Wales (NSW) region of Australia, which has suffered from several droughts in recent decades. The understanding of the drought is usually carried out using a drought index, therefore the Standard Precipitation Evaporation Index (SPEI) was chosen as it uses both rainfall and temperature parameters in its calculation and has proven to better reflect drought. The drought index was calculated at various time scales (1, 3, 6, and 12 months) using a Climate Research Unit (CRU) dataset. The study focused on predicting the temporal aspect of the drought index using 13 different variables, of which eight were climatic drivers and sea surface temperature indices, and the remainder were various meteorological variables. The models used for forecasting were an artificial neural network (ANN) and support vector regression (SVR). The model was trained from 1901–2010 and tested for nine years (2011–2018), using three different performance metric scores (coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The results indicate that ANN was better than SVR in predicting temporal drought trends, with the highest R2 value of 0.86 for the former compared to 0.75 for the latter. The study also reveals that sea surface temperatures and the climatic index (Pacific Decadal Oscillation) do not have a significant effect on the temporal drought aspect. The present work can be considered as a first step, wherein we only study the temporal trends, towards the use of climatological variables and drought incidences for the NSW region.

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

[2]  D. A. Sachindra,et al.  Prediction of droughts over Pakistan using machine learning algorithms , 2020 .

[3]  Puyu Feng,et al.  Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia , 2019, Agricultural Systems.

[4]  Gerrit Hoogenboom,et al.  Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks , 2011, Neural Computing and Applications.

[5]  D. Verdon‐Kidd,et al.  Nature and causes of protracted droughts in southeast Australia: Comparison between the Federation, WWII, and Big Dry droughts , 2009 .

[6]  Ravinesh C. Deo,et al.  Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia , 2015 .

[7]  C. Azorín-Molina,et al.  Performance of Drought Indices for Ecological, Agricultural, and Hydrological Applications , 2012 .

[8]  B. Timbal,et al.  Associations between rainfall variability in the southwest and southeast of Australia and their evolution through time , 2010 .

[9]  Sergio M. Vicente-Serrano,et al.  Analysis of the atmospheric circulation pattern effects over SPEI drought index in Spain , 2019 .

[10]  W. Cai,et al.  Teleconnection Pathways of ENSO and the IOD and the Mechanisms for Impacts on Australian Rainfall , 2011 .

[11]  Chai Hoon Koo,et al.  Drought forecasting: A review of modelling approaches 2007–2017 , 2019, Journal of Water and Climate Change.

[12]  R. Al-Weshah,et al.  Drought indices and indicators revisited , 2019, Arabian Journal of Geosciences.

[13]  A. Cancelliere,et al.  Drought forecasting using the Standardized Precipitation Index , 2007 .

[14]  Giuseppe Rossi,et al.  Methods and tools for drought analysis and management , 2007 .

[15]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[16]  P. Jones,et al.  Global warming and changes in drought , 2014 .

[17]  L. Le-Anh,et al.  Association of climate drivers with rainfall in New South Wales, Australia, using Bayesian Model Averaging , 2015, Theoretical and Applied Climatology.

[18]  I. Smith,et al.  Association between Australian rainfall and the Southern Annular Mode , 2007 .

[19]  S. Vicente‐Serrano,et al.  A Multiscalar Drought Index Sensitive to Global Warming: The Standardized Precipitation Evapotranspiration Index , 2009 .

[20]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

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

[22]  Chang-Soo Rim.  The implications of geography and climate on drought trend , 2013 .

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

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

[25]  Jan Adamowski,et al.  Short-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet transforms and machine learning methods , 2016, Sustainable Water Resources Management.

[26]  J. L. van Genderen,et al.  Drought: past problems and future scenarios , 2012, Int. J. Digit. Earth.

[27]  D. A. Sachindra,et al.  Machine learning for downscaling: the use of parallel multiple populations in genetic programming , 2019, Stochastic Environmental Research and Risk Assessment.

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

[29]  M. Latif,et al.  Greenhouse Warming, Decadal Variability, or El Niño? An Attempt to Understand the Anomalous 1990s , 1997 .

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

[31]  S. Vicente‐Serrano,et al.  Standardized precipitation evapotranspiration index (SPEI) revisited: parameter fitting, evapotranspiration models, tools, datasets and drought monitoring , 2014 .

[32]  J. Arblaster,et al.  A review of past and projected changes in Australia's rainfall , 2019, WIREs Climate Change.

[33]  Dominic A. Hudson,et al.  Bridging the gap between weather and seasonal forecasting: intraseasonal forecasting for Australia , 2011 .

[34]  Aranildo R. Lima,et al.  Nonlinear regression in environmental sciences by support vector machines combined with evolutionary strategy , 2013, Comput. Geosci..

[35]  Sergio M. Vicente-Serrano,et al.  Reference evapotranspiration variability and trends in Spain, 1961–2011 , 2014 .

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

[37]  D. Thompson,et al.  Australian Rainfall and Surface Temperature Variations Associated with the Southern Hemisphere Annular Mode , 2007 .

[38]  Alexei Lyapustin,et al.  Seasonal and interannual assessment of cloud cover and atmospheric constituents across the Amazon (2000–2015): Insights for remote sensing and climate analysis , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[39]  Inmaculada Pulido-Calvo,et al.  Spring drought prediction based on winter NAO and global SST in Portugal , 2014 .

[40]  Chunying Liu,et al.  Why Did Large Differences Arise in the Sea Surface Temperature Datasets across the Tropical Pacific during 2012 , 2013 .

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

[42]  Ming Zhao,et al.  Subseasonal Week 3–5 Surface Air Temperature Prediction During Boreal Wintertime in a GFDL Model , 2019, Geophysical Research Letters.

[43]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[44]  B. Pradhan,et al.  Rainfall Induced Landslide Studies in Indian Himalayan Region: A Critical Review , 2020, Applied Sciences.

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

[46]  Q. Duan,et al.  Seasonal drought predictability and forecast skill in the semi-arid endorheic Heihe River basin in northwestern China , 2018, Hydrology and Earth System Sciences.

[47]  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 .

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

[49]  M. Paulescu,et al.  A temperature‐based model for global solar irradiance and its application to estimate daily irradiation values , 2011 .

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

[51]  P. Jones,et al.  Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset , 2020, Scientific Data.

[52]  Sean W. Fleming,et al.  Streamflow Modelling: A Primer on Applications, Approaches and Challenges , 2012 .

[53]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .

[54]  Shishutosh Barua,et al.  Artificial Neural Network–Based Drought Forecasting Using a Nonlinear Aggregated Drought Index , 2012 .

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

[56]  Vijay P. Singh,et al.  Seasonal Drought Prediction: Advances, Challenges, and Future Prospects , 2018 .

[57]  Sancho Salcedo-Sanz,et al.  Accurate precipitation prediction with support vector classifiers: A study including novel predictive variables and observational data , 2014 .

[58]  Mark A. Bourassa,et al.  A Quantitative Evaluation of ENSO Indices , 2003 .

[59]  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).