Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree

Abstract In the present study, three types of artificial intelligence techniques, least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5T) are applied for modeling daily dissolved oxygen (DO) concentration using several water quality variables as inputs. The DO concentration and water quality variables data from three stations operated by the United States Geological Survey (USGS) were used for developing the three models. The water quality data selected consisted of daily measured of water temperature (TE, °C), pH (std. unit), specific conductance (SC, μS/cm) and discharge (DI cfs), are used as inputs to the LSSVM, MARS and M5T models. The three models were applied for each station separately and compared to each other. According to the results obtained, it was found that: (i) the DO concentration could be successfully estimated using the three models and (ii) the best model among all others differs from one station to another.

[1]  Mehmet Cakmakci,et al.  Fuzzy logic modeling of the dissolved oxygen fluctuations in Golden Horn , 2005 .

[2]  Lei-Lei Liu,et al.  Efficient system reliability analysis of soil slopes using multivariate adaptive regression splines-based Monte Carlo simulation , 2016 .

[3]  Fatih Evrendilek,et al.  Monitoring diel dissolved oxygen dynamics through integrating wavelet denoising and temporal neural networks , 2014, Environmental Monitoring and Assessment.

[4]  Daoliang Li,et al.  A hybrid WA-CPSO-LSSVR model for dissolved oxygen content prediction in crab culture , 2014, Eng. Appl. Artif. Intell..

[5]  Stefano Marsili-Libelli,et al.  Spatio-temporal dissolved oxygen dynamics in the Orbetello lagoon by fuzzy pattern recognition , 2009 .

[6]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[7]  Mohamad Javad Alizadeh,et al.  Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. , 2015, Marine pollution bulletin.

[8]  Ozgur Kisi,et al.  Modeling reference evapotranspiration using three different heuristic regression approaches , 2016 .

[9]  Nhat-Duc Hoang,et al.  Spatial prediction of rainfall-induced shallow landslides using hybrid integration approach of Least-Squares Support Vector Machines and differential evolution optimization: a case study in Central Vietnam , 2016, Int. J. Digit. Earth.

[10]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[11]  N. Mellios,et al.  Mathematical Modeling of Trophic State and Nutrient Flows of Lake Karla using the PCLake Model , 2015, Environmental Processes.

[12]  Ozgur Kisi,et al.  Least squares support vector machine for modeling daily reference evapotranspiration , 2012, Irrigation Science.

[13]  Ozgur Kisi.  Modeling discharge-suspended sediment relationship using least square support vector machine , 2012 .

[14]  Georgios D. Gikas,et al.  Water Quality of Drainage Canals and Assessment of Nutrient Loads Using QUAL2Kw , 2014, Environmental Processes.

[15]  Ozgur Kisi,et al.  Modeling of Dissolved Oxygen in River Water Using Artificial Intelligence Techniques , 2013 .

[16]  Ifigenia Kagalou,et al.  Key-Descriptors for the Functioning of a Mediterranean Reservoir: The Case of the New Lake Karla-Greece , 2014, Environmental Processes.

[17]  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.

[18]  B A Cox,et al.  A review of currently available in-stream water-quality models and their applicability for simulating dissolved oxygen in lowland rivers. , 2003, The Science of the total environment.

[19]  Juan D. Gomez,et al.  Predicting future monthly residential energy consumption using building characteristics and climate data: A statistical learning approach , 2016 .

[20]  Abbas Yeganeh-Bakhtiary,et al.  Wave runup prediction using M5′ model tree algorithm , 2016 .

[21]  Ozgur Kisi,et al.  An investigation on generalization ability of artificial neural networks and M5 model tree in modeling reference evapotranspiration , 2016, Theoretical and Applied Climatology.

[22]  E. Rotigliano,et al.  Exploring the effect of absence selection on landslide susceptibility models: A case study in Sicily, Italy , 2016 .

[23]  Ahmed El-Shafie,et al.  Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring , 2014, Environmental Science and Pollution Research.

[24]  Ozgur Kisi,et al.  Modeling of Dissolved Oxygen Concentration Using Different Neural Network Techniques in Foundation Creek, El Paso County, Colorado , 2012 .

[25]  Jordi Vives i Costa,et al.  Numerical model for a nineteenth-century hydrometric module , 2019 .

[26]  M. Keith,et al.  Investigating organic matter in Fanno Creek, Oregon, Part 1 of 3: estimating annual foliar biomass for a deciduous-dominant urban riparian corridor , 2014 .

[27]  B A Cox,et al.  A review of dissolved oxygen modelling techniques for lowland rivers. , 2003, The Science of the total environment.

[28]  Amir Ahmad,et al.  Model trees and sequential minimal optimization based support vector machine models for estimating minimum surface roughness value , 2015 .

[29]  Salim Heddam,et al.  Modelling hourly dissolved oxygen concentration (DO) using dynamic evolving neural-fuzzy inference system (DENFIS)-based approach: case study of Klamath River at Miller Island Boat Ramp, OR, USA , 2014, Environmental Science and Pollution Research.

[30]  S. E. Haupt,et al.  A model tree approach to forecasting solar irradiance variability , 2015 .

[31]  Ali Rahimikhoob,et al.  Comparison between M5 Model Tree and Neural Networks for Estimating Reference Evapotranspiration in an Arid Environment , 2014, Water Resources Management.

[32]  Ali Rahimikhoob,et al.  A Comparison Between Conventional and M5 Model Tree Methods for Converting Pan Evaporation to Reference Evapotranspiration for Semi-Arid Region , 2013, Water Resources Management.

[33]  Dimitri P. Solomatine,et al.  M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China , 2004 .

[34]  David K. Stevens,et al.  Using Bayesian networks to model watershed management decisions: an East Canyon Creek case study , 2005, WWW 2005.

[35]  Ali Behnood,et al.  Predicting modulus elasticity of recycled aggregate concrete using M5′ model tree algorithm , 2015 .

[36]  Viktor Pocajt,et al.  Modelling of dissolved oxygen in the Danube River using artificial neural networks and Monte Carlo Simulation uncertainty analysis , 2014 .

[37]  D. Papamichail,et al.  Cascade Correlation Artificial Neural Networks for Estimating Missing Monthly Values of Water Quality Parameters in Rivers , 2007 .

[38]  Salim Heddam,et al.  Use of Optimally Pruned Extreme Learning Machine (OP-ELM) in Forecasting Dissolved Oxygen Concentration (DO) Several Hours in Advance: a Case Study from the Klamath River, Oregon, USA , 2016, Environmental Processes.

[39]  M. Keith,et al.  Investigating organic matter in Fanno Creek, Oregon, Part 3 of 3: Identifying and quantifying sources of organic matter to an urban stream , 2014 .

[40]  O. Kisi,et al.  Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution , 2016 .

[41]  O. Kisi.  Pan evaporation modeling using least square support vector machine, multivariate adaptive regression splines and M5 model tree , 2015 .

[42]  Salim Heddam,et al.  Generalized regression neural network-based approach for modelling hourly dissolved oxygen concentration in the Upper Klamath River, Oregon, USA , 2014, Environmental technology.

[43]  P. J. García Nieto,et al.  Study of cyanotoxins presence from experimental cyanobacteria concentrations using a new data mining methodology based on multivariate adaptive regression splines in Trasona reservoir (Northern Spain). , 2011 .

[44]  Shuangyin Liu,et al.  Study of short-term water quality prediction model based on wavelet neural network , 2013, Math. Comput. Model..

[45]  Jasna Radulović,et al.  Neural network modeling of dissolved oxygen in the Gruža reservoir, Serbia , 2010 .

[46]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[47]  S. Mohan,et al.  Waste Load Allocation Using Machine Scheduling: Model Application , 2016, Environmental Processes.

[48]  M. Keith,et al.  Investigating organic matter in Fanno Creek, Oregon, Part 2 of 3: Sources, sinks, and transport of organic matter with fine sediment , 2014 .

[49]  Huihui Yu,et al.  Dissolved oxygen content prediction in crab culture using a hybrid intelligent method , 2016, Scientific Reports.

[50]  Jianzhou Wang,et al.  A hybrid technique for short-term wind speed prediction , 2015 .