Comparison of machine learning methods for runoff forecasting in mountainous watersheds with limited data / Porównanie metod uczenia maszynowego do prognozowania spływu w zlewniach górskich na podstawie ograniczonych danych

Abstract Runoff forecasting in mountainous regions with processed based models is often difficult and inaccurate due to the complexity of the rainfall-runoff relationships and difficulties involved in obtaining the required data. Machine learning models offer an alternative for runoff forecasting in these regions. This paper explores and compares two machine learning methods, support vector regression (SVR) and wavelet networks (WN) for daily runoff forecasting in the mountainous Sianji watershed located in the Himalayan region of India. The models were based on runoff, antecedent precipitation index, rainfall, and day of the year data collected over the three year period from July 1, 2001 and June 30, 2004. It was found that both the methods provided accurate results, with the best WN model slightly outperforming the best SVR model in accuracy. Both the WN and SVR methods should be tested in other mountainous watershed with limited data to further assess their suitability in forecasting. Streszczenie Prognozowanie spływu z obszarów górskich z użyciem programowanych modeli jest często trudne i niedokładne z powodu złożonych zależności między opadem a spływem i problemów związanych z pozyskaniem niezbędnych danych. Modele uczenia maszynowego stwarzają alternatywę dla prognozowania spływu z takich regionów. W pracy analizowano i porównano dwie metody uczenia maszynowego - metodę regresji wektorów nośnych (SVR) i sieci falkowych (WN) do dobowego prognozowania spływu w górskiej zlewni Sianji, usytuowanej w indyjskiej części Himalajów. Modele opracowano na podstawie danych o spływie, wskaźniku poprzednich opadów, opadzie i kolejnym dniu roku za trzyletni okres od 1 lipca 2001 r. do 30 czerwca 2004 r. Stwierdzono, że obie metody zapewniają dokładne wyniki, przy czym najlepszy model WN nieco przewyższa najlepszy model SVR pod względem dokładności. Obie metody powinny być testowane w innych zlewniach górskich o ograniczonej liczbie danych, aby lepiej ocenić ich przydatność do prognozowania.

[1]  Chandranath Chatterjee,et al.  A new wavelet-bootstrap-ANN hybrid model for daily discharge forecasting , 2011 .

[2]  C. L. Wu,et al.  Methods to improve neural network performance in daily flows prediction , 2009 .

[3]  Turgay PartalT. Partal.  River flow forecasting using different artificial neural network algorithms and wavelet transform , 2009 .

[4]  M. Castellano-Méndez,et al.  Modelling of the monthly and daily behaviour of the runoff of the Xallas river using Box-Jenkins and neural networks methods , 2004 .

[5]  Niranjan Pramanik,et al.  Simulation of river stage using artificial neural network and MIKE 11 hydrodynamic model , 2010, Comput. Geosci..

[6]  Linda See,et al.  Data preprocessing for river flow forecasting using neural networks: Wavelet transforms and data partitioning , 2006 .

[7]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[8]  Rameswar Panda,et al.  Application of neural network and adaptive neuro-fuzzy inference systems for river flow prediction , 2009 .

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

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

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

[12]  Ronny Berndtsson,et al.  Monthly runoff simulation: Comparing and combining conceptual and neural network models , 2006 .

[13]  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 .

[14]  Y. R. Satyaji Rao,et al.  Time Series Modeling of River Flow Using Wavelet Neural Networks , 2011 .

[15]  Maziar Palhang,et al.  Generalization performance of support vector machines and neural networks in runoff modeling , 2009, Expert Syst. Appl..

[16]  Shiv O. Prasher,et al.  Modeling runoff from middle Himalayan watersheds employing artificial intelligence techniques , 2006 .

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

[18]  Jan Adamowski,et al.  Comparison of Multivariate Regression and Artificial Neural Networks for Peak Urban Water-Demand Forecasting: Evaluation of Different ANN Learning Algorithms , 2010 .

[19]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[20]  Slobodan P. Simonovic,et al.  Short term streamflow forecasting using artificial neural networks , 1998 .

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

[22]  O. Kisi.  Neural Networks and Wavelet Conjunction Model for Intermittent Streamflow Forecasting , 2009 .

[23]  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 .