Forecasting daily streamflow using online sequential extreme learning machines

Summary While nonlinear machine methods have been widely used in environmental forecasting, in situations where new data arrive continually, the need to make frequent model updates can become cumbersome and computationally costly. To alleviate this problem, an online sequential learning algorithm for single hidden layer feedforward neural networks – the online sequential extreme learning machine (OSELM) – is automatically updated inexpensively as new data arrive (and the new data can then be discarded). OSELM was applied to forecast daily streamflow at two small watersheds in British Columbia, Canada, at lead times of 1–3 days. Predictors used were weather forecast data generated by the NOAA Global Ensemble Forecasting System (GEFS), and local hydro-meteorological observations. OSELM forecasts were tested with daily, monthly or yearly model updates. More frequent updating gave smaller forecast errors, including errors for data above the 90th percentile. Larger datasets used in the initial training of OSELM helped to find better parameters (number of hidden nodes) for the model, yielding better predictions. With the online sequential multiple linear regression (OSMLR) as benchmark, we concluded that OSELM is an attractive approach as it easily outperformed OSMLR in forecast accuracy.

[1]  P. Coulibaly,et al.  Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting , 2012 .

[2]  Paul H. Whitfield,et al.  Spatiotemporal mapping of ENSO and PDO surface meteorological signals in British Columbia, Yukon, and southeast Alaska , 2010 .

[3]  Robert K. L. Gay,et al.  Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning , 2009, IEEE Transactions on Neural Networks.

[4]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[5]  T. D. Potter,et al.  Handbook of weather, climate, and water : atmospheric chemistry, hydrology, and societal impacts , 2003 .

[6]  Julio J. Valdés,et al.  Computational intelligence in earth sciences and environmental applications: Issues and challenges , 2006, Neural Networks.

[7]  Holger R. Maier,et al.  Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling , 2014, Environ. Model. Softw..

[8]  Dave Campbell,et al.  Development and Operational Testing of a Super‐Ensemble Artificial Intelligence Flood‐Forecast Model for a Pacific Northwest River , 2015 .

[9]  B. Schrauwen,et al.  Reservoir computing and extreme learning machines for non-linear time-series data analysis , 2013, Neural Networks.

[10]  Aranildo R. Lima,et al.  Nonlinear regression in environmental sciences using extreme learning machines: A comparative evaluation , 2015, Environ. Model. Softw..

[11]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[12]  Gareth J. Janacek,et al.  Predictive Uncertainty in Environmental Modelling , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[13]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[14]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[15]  A. Shamseldin.  Artificial neural network model for river flow forecasting in a developing country. , 2010 .

[16]  Jaakko Riihimäki,et al.  A Connection between Extreme Learning Machine and Neural Network Kernel , 2010, IC3K.

[17]  T. Sathish,et al.  River Flow Forecasting using Recurrent Neural Networks , 2004 .

[18]  Robert P. W. Duin,et al.  Feedforward neural networks with random weights , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[19]  Robert J. Abrahart,et al.  Neural Network Hydroinformatics: Maintaining Scientific Rigour , 2009 .

[20]  Guang-Bin Huang,et al.  An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels , 2014, Cognitive Computation.

[21]  Eric Huang,et al.  Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control , 2014 .

[22]  Alex J. Cannon,et al.  Daily streamflow forecasting by machine learning methods with weather and climate inputs , 2012 .

[23]  P. Whitfield,et al.  Regime‐dependent streamflow sensitivities to Pacific climate modes cross the Georgia–Puget transboundary ecoregion , 2007 .

[24]  Christian W. Dawson,et al.  Neural Network Solutions to Flood Estimation at Ungauged Sites , 2009 .

[25]  J. Whitaker,et al.  NOAA's Second-Generation Global Medium-Range Ensemble Reforecast Dataset , 2013 .

[26]  Dominik E. Reusser,et al.  Early flood warnings from empirical (expanded) downscaling of the full ECMWF Ensemble Prediction System , 2009 .

[27]  Yuan Lan,et al.  Ensemble of online sequential extreme learning machine , 2009, Neurocomputing.

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[30]  Yoon-Seok Timothy Hong,et al.  Dynamic nonlinear state-space model with a neural network via improved sequential learning algorithm for an online real-time hydrological modeling , 2012 .

[31]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[32]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[33]  R. R. Hocking.  The analysis and selection of variables in linear regression , 1976 .

[34]  Lloyd A. Smith,et al.  Practical feature subset selection for machine learning , 1998 .

[35]  Kevin Sene,et al.  Hydrometeorology: Forecasting and Applications , 2009 .

[36]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[37]  Marcel Vallée,et al.  The Canadian Updateable Model Output Statistics (UMOS) System: Design and Development Tests , 2002 .

[38]  Hugo Valadares Siqueira,et al.  Echo State Networks and Extreme Learning Machines: A Comparative Study on Seasonal Streamflow Series Prediction , 2012, ICONIP.

[39]  Avi Ostfeld,et al.  Data-driven modelling: some past experiences and new approaches , 2008 .

[40]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[41]  William W. Hsieh,et al.  Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels , 2009 .