Modeling daily water temperature for rivers: comparison between adaptive neuro-fuzzy inference systems and artificial neural networks models

River water temperature is a key control of many physical and bio-chemical processes in river systems, which theoretically depends on multiple factors. Here, four different machine learning models, including multilayer perceptron neural network models (MLPNN), adaptive neuro-fuzzy inference systems (ANFIS) with fuzzy c-mean clustering algorithm (ANFIS_FC), ANFIS with grid partition method (ANFIS_GP), and ANFIS with subtractive clustering method (ANFIS_SC), were implemented to simulate daily river water temperature, using air temperature (Ta), river flow discharge (Q), and the components of the Gregorian calendar (CGC) as predictors. The proposed models were tested in various river systems characterized by different hydrological conditions. Results showed that including the three inputs as predictors (Ta, Q, and the CGC) yielded the best accuracy among all the developed models. In particular, model performance improved considerably compared to the case where only Ta is used as predictor, which is the typical approach of most of previous machine learning applications. Additionally, it was found that Q played a relevant role mainly in snow-fed and regulated rivers with higher-altitude hydropower reservoirs, while it improved to a lower extent model performance in lowland rivers. In the validation phase, the MLPNN model was generally the one providing the highest performances, although in some river stations ANFIS_FC and ANFIS_GP were slightly more accurate. Overall, the results indicated that the machine learning models developed in this study can be effectively used for river water temperature simulation.

[1]  Annunziato Siviglia,et al.  Prediction of river water temperature: a comparison between a new family of hybrid models and statistical approaches , 2016 .

[2]  J.-L. Boillat,et al.  Hydropeaking indicators for characterization of the Upper-Rhone River in Switzerland , 2011, Aquatic Sciences.

[3]  M. A. Yurdusev,et al.  Adaptive neuro fuzzy inference system approach for municipal water consumption modeling: An application to Izmir, Turkey , 2009 .

[4]  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.

[5]  R. Wilby,et al.  Inferring air–water temperature relationships from river and catchment properties , 2013 .

[6]  Erwan Gloaguen,et al.  Water temperature modelling: comparison between the generalized additive model, logistic, residuals regression and linear regression models , 2017 .

[7]  Qinggai Wang.  Prediction of Water Temperature as Affected by a Pre‐Constructed Reservoir Project Based on MIKE11 , 2013 .

[8]  Salim Heddam,et al.  New modelling strategy based on radial basis function neural network (RBFNN) for predicting dissolved oxygen concentration using the components of the Gregorian calendar as inputs: case study of Clackamas River, Oregon, USA , 2016, Modeling Earth Systems and Environment.

[9]  Marco Toffolon,et al.  A hybrid model for river water temperature as a function of air temperature and discharge , 2015 .

[10]  Salim Heddam,et al.  Multilayer perceptron neural network-based approach for modeling phycocyanin pigment concentrations: case study from lower Charles River buoy, USA , 2016, Environmental Science and Pollution Research.

[11]  B. Majone,et al.  Prediction of surface temperature in lakes with different morphology using air temperature , 2014 .

[12]  Mysore G. Satish,et al.  Predicting water temperatures using a deterministic model : Application on Miramichi River catchments (New Brunswick, Canada) , 2007 .

[13]  M. Parlange,et al.  Stream temperature prediction in ungauged basins: review of recent approaches and description of a new physics-derived statistical model , 2015 .

[14]  Bernard Bobée,et al.  A Review of Statistical Water Temperature Models , 2007 .

[15]  Adam P. Piotrowski,et al.  Comparing various artificial neural network types for water temperature prediction in rivers , 2015 .

[16]  D. Caissie.  The thermal regime of rivers : a review , 2006 .

[17]  Heinz G. Stefan,et al.  A nonlinear regression model for weekly stream temperatures , 1998 .

[18]  Pavel Kabat,et al.  Global river temperatures and sensitivity to atmospheric warming and changes in river flow , 2011 .

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

[20]  J. Garvey,et al.  Water Temperature and River Stage Influence Mortality and Abundance of Naturally Occurring Mississippi River Scaphirhynchus Sturgeon , 2010 .

[21]  M. Huijbregts,et al.  Sensitivity of native and non-native mollusc species to changing river water temperature and salinity , 2012, Biological Invasions.

[22]  Jason B. Dunham,et al.  Can air temperature be used to project influences of climate change on stream temperature? , 2014 .

[23]  J. Dunham,et al.  Relationships between water temperatures and upstream migration, cold water refuge use, and spawning of adult bull trout from the Lostine River, Oregon, USA , 2010 .

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

[25]  A. Rosenberger,et al.  A global review of freshwater crayfish temperature tolerance, preference, and optimal growth , 2016, Reviews in Fish Biology and Fisheries.

[26]  B. Vondracek,et al.  Air‐Water Temperature Relationships in the Trout Streams of Southeastern Minnesota's Carbonate‐Sandstone Landscape , 2012 .

[27]  J. Kur,et al.  Genetic and biochemical characterization of yeasts isolated from Antarctic soil samples , 2017, Polar Biology.

[28]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[29]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[30]  Marijana Hadzima-Nyarko,et al.  Modelling river temperature from air temperature: case of the River Drava (Croatia) , 2015 .

[31]  Ozgur Kisi,et al.  Estimation of Daily Pan Evaporation Using Two Different Adaptive Neuro-Fuzzy Computing Techniques , 2012, Water Resources Management.

[32]  Daniele Tonina,et al.  Estimation of daily stream water temperatures with a Bayesian regression approach , 2017 .

[33]  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.

[34]  M. Temizyurek,et al.  Modelling the effects of meteorological parameters on water temperature using artificial neural networks. , 2018, Water science and technology : a journal of the International Association on Water Pollution Research.

[35]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[36]  Qingzhong Liu,et al.  Predicting injection profiles using ANFIS , 2007, Inf. Sci..

[37]  K. Alfredsen,et al.  Hydrological and thermal effects of hydropeaking on early life stages of salmonids: A modelling approach for implementing mitigation strategies. , 2016, The Science of the total environment.

[38]  Dennis P. Lettenmaier,et al.  Coupled daily streamflow and water temperature modelling in large river basins , 2012 .

[39]  R. Knust,et al.  Temperature-dependent metabolism in Antarctic fish: Do habitat temperature conditions affect thermal tolerance ranges? , 2016, Polar Biology.

[40]  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..

[41]  Matthias Schmid,et al.  Developing and testing temperature models for regulated systems: A case study on the Upper Delaware River , 2014 .

[42]  Heinz G. Stefan,et al.  Extreme value analysis of a fish/temperature field database , 1995 .

[43]  Feng Liu,et al.  Quantifying the impact of the Three Gorges Dam on the thermal dynamics of the Yangtze River , 2018 .

[44]  D. Schindler,et al.  Watershed geomorphology and snowmelt control stream thermal sensitivity to air temperature , 2015 .

[45]  Mehmet Cakmakci,et al.  Adaptive neuro-fuzzy modelling of anaerobic digestion of primary sedimentation sludge , 2007, Bioprocess and biosystems engineering.

[46]  Tyler Wagner,et al.  A regional neural network ensemble for predicting mean daily river water temperature , 2014 .

[47]  A. Siviglia,et al.  RESPONSES OF BENTHIC INVERTEBRATES TO ABRUPT CHANGES OF TEMPERATURE IN FLUME SIMULATIONS , 2012 .

[48]  Roger C. Bales,et al.  Estimating Stream Temperature from Air Temperature: Implications for Future Water Quality , 2005 .

[49]  P. Rowiński,et al.  Dissolved oxygen and water temperature dynamics in lowland rivers over various timescales , 2015 .

[50]  G. Sahoo,et al.  Forecasting stream water temperature using regression analysis, artificial neural network, and chaotic non-linear dynamic models , 2009 .

[51]  Heinz G. Stefan,et al.  STREAM TEMPERATURE ESTIMATION FROM AIR TEMPERATURE , 1993 .

[52]  Heinz G. Stefan,et al.  Stream temperature/air temperature relationship : a physical interpretation , 1999 .

[53]  Desmond E. Walling,et al.  Water–air temperature relationships in a Devon river system and the role of flow , 2003 .

[54]  B. Majone,et al.  The role of stratification on lakes' thermal response: The case of Lake Superior , 2015 .

[55]  X. Wen,et al.  A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region , 2014 .

[56]  Ozgur Kisi,et al.  Extreme learning machines: a new approach for modeling dissolved oxygen (DO) concentration with and without water quality variables as predictors , 2017, Environmental Science and Pollution Research.

[57]  Martin W. Doyle,et al.  Human Impacts to River Temperature and Their Effects on Biological Processes: A Quantitative Synthesis 1 , 2011 .

[58]  Mohammad Ali Ghorbani,et al.  Estimating daily pan evaporation from climatic data of the State of Illinois, USA using adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) , 2011 .

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

[60]  Osman Sagdic,et al.  Comparison of adaptive neuro-fuzzy inference system and artificial neural networks for estimation of oxidation parameters of sunflower oil added with some natural byproduct extracts. , 2012, Journal of the science of food and agriculture.

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

[62]  M. Jensen,et al.  Temperature Modeling with HEC - RAS , 2004 .

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

[64]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[65]  Ozgur Kisi,et al.  Comparison of Two Different Adaptive Neuro-Fuzzy Inference Systems in Modelling Daily Reference Evapotranspiration , 2014, Water Resources Management.

[66]  Taha B. M. J. Ouarda,et al.  Predicting river water temperatures using stochastic models: case study of the Moisie River (Québec, Canada) , 2007 .

[67]  Thorsten Wagener,et al.  Investigating controls on the thermal sensitivity of Pennsylvania streams , 2012 .

[68]  D. Caissie,et al.  Study of stream temperature dynamics and corresponding heat fluxes within Miramichi River catchments (New Brunswick, Canada) , 2011 .

[69]  Salim Heddam,et al.  Modeling hourly dissolved oxygen concentration (DO) using two different adaptive neuro-fuzzy inference systems (ANFIS): a comparative study , 2013, Environmental Monitoring and Assessment.