Phase-space reconstruction and self-exciting threshold modeling approach to forecast lake water levels

Lake water level forecasting is very important for an accurate and reliable management of local and regional water resources. In the present study two nonlinear approaches, namely phase-space reconstruction and self-exciting threshold autoregressive model (SETAR) were compared for lake water level forecasting. The modeling approaches were applied to high-quality lake water level time series of the three largest lakes in Sweden; Vänern, Vättern, and Mälaren. Phase-space reconstruction was applied by the k-nearest neighbor (k-NN) model. The k-NN model parameters were determined using autocorrelation, mutual information functions, and correlation integral. Jointly, these methods indicated chaotic behavior for all lake water levels. The correlation dimension found for the three lakes was 3.37, 3.97, and 4.44 for Vänern, Vättern, and Mälaren, respectively. As a comparison, the best SETAR models were selected using the Akaike Information Criterion. The best SETAR models in this respect were (10,4), (5,8), and (7,9) for Vänern, Vättern, and Mälaren, respectively. Both model approaches were evaluated with various performance criteria. Results showed that both modeling approaches are efficient in predicting lake water levels but the phase-space reconstruction (k-NN) is superior to the SETAR model.

[1]  Kwok-Wing Chau,et al.  Data-driven models for monthly streamflow time series prediction , 2010, Eng. Appl. Artif. Intell..

[2]  Mohammad Ali Ghorbani,et al.  Investigating chaos in river stage and discharge time series , 2012 .

[3]  T. Ouarda,et al.  Identification of model order and number of neighbors for k-nearest neighbor resampling , 2011 .

[4]  Marco Sandri,et al.  Combining Singular-Spectrum Analysis and neural networks for time series forecasting , 2005, Neural Processing Letters.

[5]  Bellie Sivakumar,et al.  An investigation of the presence of low-dimensional chaotic behaviour in the sediment transport phenomenon , 2002 .

[6]  J. Elsner,et al.  The weather attractor over very short timescales , 1988, Nature.

[7]  Ignacio Rodriguez-Iturbe,et al.  Phase-space analysis of daily streamflow : characterization and prediction , 1998 .

[8]  Hui-Chen Su,et al.  A nonlinear time series analysis using two‐stage genetic algorithms for streamflow forecasting , 2008 .

[9]  M. Dahl,et al.  Comparison of four models simulating phosphorus dynamics in Lake Vänern, Sweden , 2004 .

[10]  Henry D. I. Abarbanel,et al.  Chaos and predictability in ocean water levels , 1999 .

[11]  P. Kitanidis,et al.  Real‐time forecasting with a conceptual hydrologic model: 2. Applications and results , 1980 .

[12]  Bellie Sivakumar,et al.  Forecasting monthly streamflow dynamics in the western United States: a nonlinear dynamical approach , 2003, Environ. Model. Softw..

[13]  Francesco Masulli,et al.  Application of an ensemble technique based on singular spectrum analysis to daily rainfall forecasting , 2003, Neural Networks.

[14]  George Sugihara,et al.  Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series , 1990, Nature.

[15]  Fernanda Strozzi,et al.  Forecasting high waters at Venice Lagoon using chaotic time series analysis and nonlinear neural networks , 2000 .

[16]  Bellie Sivakumar,et al.  Dominant processes concept in hydrology: moving forward , 2004 .

[17]  K. Chau,et al.  Predicting monthly streamflow using data‐driven models coupled with data‐preprocessing techniques , 2009 .

[18]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[19]  T. Hu,et al.  Rainfall–runoff modeling using principal component analysis and neural network , 2007 .

[20]  K. Chau,et al.  Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques , 2010 .

[21]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[22]  Upmanu Lall,et al.  Support vector machines for nonlinear state space reconstruction: Application to the Great Salt Lake time series , 2005 .

[23]  N. Copty,et al.  Modelling level change in lakes using neuro-fuzzy and artificial neural networks , 2009 .

[24]  Emanuela Marrocu,et al.  The performance of non‐linear exchange rate models: a forecasting comparison , 2002 .

[25]  Vazken Andréassian,et al.  Hydrological ensemble forecasting at ungauged basins: using neighbour catchments for model setup and updating , 2011 .

[26]  Taha B. M. J. Ouarda,et al.  Daily river water temperature forecast model with a k‐nearest neighbour approach , 2012 .

[27]  R. Tsay.  Testing and modeling multivariate threshold models , 1998 .

[28]  Shie-Yui Liong,et al.  Rainfall and runoff forecasting with SSA-SVM approach , 2001 .

[29]  A. Jayawardena,et al.  Noise reduction and prediction of hydrometeorological time series: dynamical systems approach vs. stochastic approach , 2000 .

[30]  Upmanu Lall,et al.  A Nearest Neighbor Bootstrap For Resampling Hydrologic Time Series , 1996 .

[31]  Bellie Sivakumar,et al.  Characterization and prediction of runoff dynamics: a nonlinear dynamical view , 2002 .

[32]  Roberto Revelli,et al.  A comparison of nonlinear flood forecasting methods , 2003 .

[33]  S. H. Hsieh,et al.  THRESHOLD MODELS FOR NONLINEAR TIME SERIES ANALYSIS. , 1987 .

[34]  Farmer,et al.  Predicting chaotic time series. , 1987, Physical review letters.

[35]  G. Weyhenmeyer,et al.  Increasingly ice-free winters and their effects on water quality in Sweden’s largest lakes , 2008, Hydrobiologia.

[36]  S. Jain,et al.  Fitting of Hydrologic Models: A Close Look at the Nash–Sutcliffe Index , 2008 .

[37]  H. Abarbanel,et al.  Prediction in chaotic nonlinear systems: Methods for time series with broadband Fourier spectra. , 1990, Physical review. A, Atomic, molecular, and optical physics.

[38]  K. Lam,et al.  River flow time series prediction with a range-dependent neural network , 2001 .

[39]  Mohammad Ali Ghorbani,et al.  Dynamics of hourly sea level at Hillarys Boat Harbour, Western Australia: a chaos theory perspective , 2011 .

[40]  T. Rientjes,et al.  Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation , 2005 .

[41]  Francesco Lisi,et al.  CHAOTIC FORECASTING OF DISCHARGE TIME SERIES: A CASE STUDY 1 , 2001 .

[42]  Anu Reinart,et al.  Mapping surface temperature in large lakes with MODIS data , 2008 .

[43]  W. C. Lennox,et al.  Chaos based Analytical techniques for daily extreme hydrological observations , 2007 .

[44]  Radko Mesiar,et al.  Comparison of forecasting performance of nonlinear models of hydrological time series , 2006 .

[45]  C. Dunning.  Hydrological Modeling of the Upper South Saskatchewan River Basin: Multi-basin Calibration and Gauge De-clustering Analysis , 2009 .

[46]  N. G. Serbov,et al.  Signatures of low-dimensional chaos in hourly water level measurements at coastal site of Mariupol, Ukraine , 2008 .

[47]  Wen Wang.  Stochasticity, nonlinearity and forecasting of streamflow processes , 2006 .

[48]  Hakan Tongal,et al.  Comparison of Recurrent Neural Network, Adaptive Neuro-Fuzzy Inference System and Stochastic Models in Eğirdir Lake Level Forecasting , 2010 .

[49]  L. Tsimring,et al.  The analysis of observed chaotic data in physical systems , 1993 .

[50]  Bellie Sivakumar,et al.  River flow forecasting: use of phase-space reconstruction and artificial neural networks approaches , 2002 .

[51]  Shie-Yui Liong,et al.  Practical Inverse Approach for Forecasting Nonlinear Hydrological Time Series , 2002 .

[52]  Ashu Jain,et al.  Temporal scaling in river flow: can it be chaotic? / L’invariance d’échelle de l’écoulement fluvial peut-elle être chaotique? , 2004 .

[53]  James P. Crutchfield,et al.  Geometry from a Time Series , 1980 .

[54]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[55]  A. Altunkaynak.  Forecasting Surface Water Level Fluctuations of Lake Van by Artificial Neural Networks , 2007 .

[56]  D. Pierson,et al.  The effects of variability in the inherent optical properties on estimations of chlorophyll a by remote sensing in Swedish freshwaters. , 2001, The Science of the total environment.

[57]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[58]  Marcella Niglio,et al.  The moments of SETARMA models , 2006 .

[59]  Luca Ridolfi,et al.  Nonlinear analysis of river flow time sequences , 1997 .

[60]  E. Willén.  Four Decades of Research on the Swedish Large Lakes Mälaren, Hjälmaren, Vättern and Vänern: The Significance of Monitoring and Remedial Measures for a Sustainable Society , 2001, Ambio.

[61]  Upmanu Lall,et al.  Streamflow simulation: A nonparametric approach , 1997 .

[62]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[63]  I. Kozhevnikova,et al.  Nonlinear dynamics of level variations in the Caspian Sea , 2008 .

[64]  Upmanu Lall,et al.  Nonlinear Dynamics of the Great Salt Lake: Nonparametric Short-Term Forecasting , 1996 .

[65]  Marcella Niglio,et al.  Multi-step SETARMA predictors in the analysis of hydrological time series , 2006 .

[66]  Christophe Tricaud,et al.  Great Salt Lake Surface Level Forecasting Using FIGARCH Model , 2007 .

[67]  H. Kvarnäs.  Morphometry and Hydrology of the Four Large Lakes of Sweden , 2001, Ambio.

[68]  J. A. Ferreira,et al.  Singular spectrum analysis and forecasting of hydrological time series , 2006 .

[69]  M. J. Booij,et al.  Seasonality of low flows and dominant processes in the Rhine River , 2013, Stochastic Environmental Research and Risk Assessment.

[70]  M. Josefsson,et al.  The Environmental Consequences of Alien Species in the Swedish Lakes Mälaren, Hjälmaren, Vänern and Vättern , 2001, Ambio.