Two hybrid data-driven models for modeling water-air temperature relationship in rivers

River water temperature (RWT) forecasting is important for the management of stream ecology. In this paper, a new method based on coupling of wavelet transformation (WT) and artificial intelligence (AI) techniques, including multilayer perceptron neural network (MLPNN) and adaptive neural-fuzzy inference system (ANFIS) for RWT prediction is proposed. The performances of the hybrid models are compared with regular MLPNN and ANFIS models and multiple linear regression (MLR) models for RWT forecasting in two river stations in the Drava River, Croatia. Model performance was evaluated using the coefficient of correlation (R), the Willmott index of agreement (d), the root mean squared error (RMSE), and the mean absolute error (MAE). Results indicate that the combination of WT and AI models (WTMLPNN and WTANFIS) yield better models than the conventional forecasting models for RWT simulation for both regular periods and heatwave events. The MLPNN and ANFIS models outperform the MLR models for RWT simulation for the studied river stations. RMSE values of WTMLPNN2 and WTANFIS2 models range from 1.127 to 1.286 °C, and 1.216 to 1.491 °C for the Botovo and Donji Miholjac stations respectively. Additionally, modeling results further confirm the importance of the day of year (DOY) on the thermal dynamics of the river. The results of this study indicate the potential of coupling of WT and MLPNN, ANFIS models in forecasting RWT.

[1]  Fatih Evrendilek.  Assessing neural networks with wavelet denoising and regression models in predicting diel dynamics of eddy covariance-measured latent and sensible heat fluxes and evapotranspiration , 2012, Neural Computing and Applications.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Vahid Nourani,et al.  Conjunction of SOM-based feature extraction method and hybrid wavelet-ANN approach for rainfall–runoff modeling , 2013 .

[4]  Agnès Ducharne,et al.  Importance of stream temperature to climate change impact on water quality , 2007 .

[5]  Daniel Caissie,et al.  Stream temperature modelling using artificial neural networks: application on Catamaran Brook, New Brunswick, Canada , 2008 .

[6]  Chuen-Tsai Sun,et al.  Neuro-fuzzy And Soft Computing: A Computational Approach To Learning And Machine Intelligence [Books in Brief] , 1997, IEEE Transactions on Neural Networks.

[7]  A. St‐Hilaire,et al.  River evaporation and corresponding heat fluxes in forested catchments , 2014 .

[8]  Stefan Banzhaf,et al.  Groundwater and Surface Water Interaction at the Regional-scale – A Review with Focus on Regional Integrated Models , 2015, Water Resources Management.

[9]  Piet F. M. Verdonschot,et al.  Variable selection for modelling effects of eutrophication on stream and river ecosystems , 2004 .

[10]  Deren Li,et al.  À Trous Wavelet Decomposition Applied to Image Edge Detection , 2001 .

[11]  Zhonggen Wang,et al.  Wavelet Neural Modeling for Hydrologic Time Series Forecasting with Uncertainty Evaluation , 2015, Water Resources Management.

[12]  Salim Heddam,et al.  Modeling daily water temperature for rivers: comparison between adaptive neuro-fuzzy inference systems and artificial neural networks models , 2018, Environmental Science and Pollution Research.

[13]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[14]  Adam P. Piotrowski,et al.  Comparing large number of metaheuristics for artificial neural networks training to predict water temperature in a natural river , 2014, Comput. Geosci..

[15]  Ozgur Kisi,et al.  Two hybrid Artificial Intelligence approaches for modeling rainfall–runoff process , 2011 .

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

[17]  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 .

[18]  A. García-Berrocal,et al.  Improving the in situ measurement of RTD response times through Discrete Wavelet Transform in NPP , 2015 .

[19]  Mohammad H. Aminfar,et al.  A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation , 2009, Eng. Appl. Artif. Intell..

[20]  Daniel Hissel,et al.  Selection of mother wavelet and decomposition level for energy management in electrical vehicles including a fuel cell , 2015 .

[21]  Marijana Hadzima-Nyarko,et al.  Implementation of Artificial Neural Networks in Modeling the Water-Air Temperature Relationship of the River Drava , 2014, Water Resources Management.

[22]  Mark J. Jensen.  An Alternative Maximum Likelihood Estimator of Long-Memeory Processes Using Compactly Supported Wavelets , 1997 .

[23]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[24]  Narayan Kumar Shrestha,et al.  Incorporation of the equilibrium temperature approach in a Soil and Water Assessment Tool hydroclimatological stream temperature model , 2017 .

[25]  Yan-Fang Sang,et al.  A Practical Guide to Discrete Wavelet Decomposition of Hydrologic Time Series , 2012, Water Resources Management.

[26]  Marijana Hadzima-Nyarko,et al.  Modelling daily water temperature from air temperature for the Missouri River , 2018, PeerJ.

[27]  Sungwon Kim,et al.  Daily water level forecasting using wavelet decomposition and artificial intelligence techniques , 2015 .

[28]  Peter W. Tse,et al.  An enhanced Kurtogram method for fault diagnosis of rolling element bearings , 2013 .

[29]  José A. Romagnoli,et al.  Process data de-noising using wavelet transform , 1999, Intell. Data Anal..

[30]  Ratko Grbic,et al.  Stream water temperature prediction based on Gaussian process regression , 2013, Expert Syst. Appl..

[31]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[32]  N. Detenbeck,et al.  Spatial statistical network models for stream and river temperature in New England, USA , 2016 .

[33]  Taher Rajaee,et al.  Wavelet and neuro-fuzzy conjunction approach for suspended sediment prediction. , 2010 .

[34]  Sungwon Kim,et al.  River Stage Forecasting Using Wavelet Packet Decomposition and Machine Learning Models , 2016, Water Resources Management.

[35]  Ozgur Kisi,et al.  River Suspended Sediment Load Prediction: Application of ANN and Wavelet Conjunction Model , 2011 .

[36]  M. Toffolon,et al.  Exploring and Quantifying River Thermal Response to Heatwaves , 2018, Water.

[37]  D. Hannah,et al.  A spatio-temporal statistical model of maximum daily river temperatures to inform the management of Scotland's Atlantic salmon rivers under climate change. , 2018, The Science of the total environment.

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

[39]  Yulong Li,et al.  De-noising of digital image correlation based on stationary wavelet transform , 2017 .