River suspended sediment modelling using the CART model: A comparative study of machine learning techniques.

Suspended sediment load (SSL) modelling is an important issue in integrated environmental and water resources management, as sediment affects water quality and aquatic habitats. Although classification and regression tree (CART) algorithms have been applied successfully to ecological and geomorphological modelling, their applicability to SSL estimation in rivers has not yet been investigated. In this study, we evaluated use of a CART model to estimate SSL based on hydro-meteorological data. We also compared the accuracy of the CART model with that of the four most commonly used models for time series modelling of SSL, i.e. adaptive neuro-fuzzy inference system (ANFIS), multi-layer perceptron (MLP) neural network and two kernels of support vector machines (RBF-SVM and P-SVM). The models were calibrated using river discharge, stage, rainfall and monthly SSL data for the Kareh-Sang River gauging station in the Haraz watershed in northern Iran, where sediment transport is a considerable issue. In addition, different combinations of input data with various time lags were explored to estimate SSL. The best input combination was identified through trial and error, percent bias (PBIAS), Taylor diagrams and violin plots for each model. For evaluating the capability of the models, different statistics such as Nash-Sutcliffe efficiency (NSE), Kling-Gupta efficiency (KGE) and percent bias (PBIAS) were used. The results showed that the CART model performed best in predicting SSL (NSE=0.77, KGE=0.8, PBIAS<±15), followed by RBF-SVM (NSE=0.68, KGE=0.72, PBIAS<±15). Thus the CART model can be a helpful tool in basins where hydro-meteorological data are readily available.

[1]  Biswajeet Pradhan,et al.  Suitability estimation for urban development using multi-hazard assessment map. , 2017, The Science of the total environment.

[2]  Philip M. Haygarth,et al.  Agriculture, phosphorus and eutrophication: a European perspective , 2007 .

[3]  Rebecca A. O'Leary,et al.  Classification and Regression Tree and Spatial Analyses Reveal Geographic Heterogeneity in Genome Wide Linkage Study of Indian Visceral Leishmaniasis , 2010, PloS one.

[4]  N R Temkin,et al.  Classification and regression trees (CART) for prediction of function at 1 year following head trauma. , 1995, Journal of neurosurgery.

[5]  Dieu Tien Bui,et al.  A novel hybrid artificial intelligence approach for flood susceptibility assessment , 2017, Environ. Model. Softw..

[6]  H. Feng,et al.  Nutrient fluxes across sediment-water interface in Bohai Bay Coastal Zone, China. , 2017, Marine pollution bulletin.

[7]  Bahram Choubin,et al.  Application of several data-driven techniques to predict a standardized precipitation index , 2016 .

[8]  J. Refsgaard.  Parameterisation, calibration and validation of distributed hydrological models , 1997 .

[9]  C. Sutton.  Classification and Regression Trees, Bagging, and Boosting , 2005 .

[10]  M. Vafakhah,et al.  Evaluating the support vector machine for suspended sediment load forecasting based on gamma test , 2016, Arabian Journal of Geosciences.

[11]  G. De’ath,et al.  CLASSIFICATION AND REGRESSION TREES: A POWERFUL YET SIMPLE TECHNIQUE FOR ECOLOGICAL DATA ANALYSIS , 2000 .

[12]  Sajjad Ahmad,et al.  Suspended sediment load prediction of river systems: An artificial neural network approach , 2011 .

[13]  Bahram Choubin,et al.  Combined gamma and M-test-based ANN and ARIMA models for groundwater fluctuation forecasting in semiarid regions , 2017, Environmental Earth Sciences.

[14]  S. Abbas,et al.  Exploring CO2 Sources and Sinks Nexus through Integrated Approach: Insight from Pakistan , 2013 .

[15]  Vilas Nitivattananon,et al.  Green waste to biogas: Renewable energy possibilities for Thailand's green markets , 2012 .

[16]  Changxing Shi,et al.  Sediment rating curves in the Ningxia-Inner Mongolia reaches of the upper Yellow River and their implications , 2012 .

[17]  G. Migiros,et al.  Pinios (Peneus) River (Central Greece): Hydrological — Geomorphological elements and changes during the quaternary , 2011 .

[18]  Desmond E. Walling,et al.  The sedimentation of salmonid spawning gravels in the Hampshire Avon catchment, UK: implications for the dissolved oxygen content of intragravel water and embryo survival , 2007 .

[19]  L. Nowell,et al.  Influence of sediment chemistry and sediment toxicity on macroinvertebrate communities across 99 wadable streams of the Midwestern USA. , 2017, The Science of the total environment.

[20]  Kim Falinski,et al.  Sediment delivery modeling in practice: Comparing the effects of watershed characteristics and data resolution across hydroclimatic regions. , 2017, The Science of the total environment.

[21]  Simin Qu,et al.  A semi-physical sediment yield model for estimation of suspended sediment in loess region , 2017 .

[22]  Dirk Wenske,et al.  Assessment of sediment delivery from successive erosion on stream-coupled hillslopes via a time series of topographic surveys in the central high mountain range of Taiwan , 2012 .

[23]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[24]  J. Martín-Vide,et al.  Suspended sediment load at the lowermost Ebro River (Catalonia, Spain) , 2015 .

[25]  C. Penn,et al.  Streambanks: A net source of sediment and phosphorus to streams and rivers. , 2016, Journal of environmental management.

[26]  Matjaž Mikoš,et al.  Trivariate Frequency Analyses of Peak Discharge, Hydrograph Volume and Suspended Sediment Concentration Data Using Copulas , 2014, Water Resources Management.

[27]  J. Orbach.  Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. , 1962 .

[28]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[29]  O. Kisi,et al.  Suspended sediment modeling using genetic programming and soft computing techniques , 2012 .

[30]  Bahram Choubin,et al.  An ensemble forecast of semi‐arid rainfall using large‐scale climate predictors , 2017 .

[31]  Juan B. Valdés,et al.  NONLINEAR MODEL FOR DROUGHT FORECASTING BASED ON A CONJUNCTION OF WAVELET TRANSFORMS AND NEURAL NETWORKS , 2003 .

[32]  B. Pradhan,et al.  Application of weights-of-evidence and certainty factor models and their comparison in landslide susceptibility mapping at Haraz watershed, Iran , 2013, Arabian Journal of Geosciences.

[33]  Ozgur Kisi,et al.  Evaluation of data driven models for river suspended sediment concentration modeling , 2016 .

[34]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[35]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[36]  Min Wu,et al.  Phosphorus storage dynamics and adsorption characteristics for sediment from a drinking water source reservoir and its relation with sediment compositions , 2014 .

[37]  G. Kitagawa,et al.  Information Criteria and Statistical Modeling , 2007 .

[38]  M. Abdo,et al.  Metal pollution assessment in the surface sediment of Lake Nasser, Egypt , 2014 .

[39]  H. Md. Azamathulla,et al.  ANFIS-based approach for predicting sediment transport in clean sewer , 2012, Appl. Soft Comput..

[40]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[41]  Patrice Bourdelais,et al.  What is vulnerability , 2006 .

[42]  Roman Timofeev,et al.  Classification and Regression Trees(CART)Theory and Applications , 2004 .

[43]  Geoffrey E. Hinton,et al.  A general framework for parallel distributed processing , 1986 .

[44]  D. Walling,et al.  An analysis of the factors contributing to the settling potential of fine fluvial sediment , 2008 .

[45]  Jan Adamowski,et al.  Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS , 2014, Expert Syst. Appl..

[46]  Turgay Partal,et al.  Estimation and forecasting of daily suspended sediment data using wavelet–neural networks , 2008 .

[47]  Kwok-Wing Chau,et al.  A comparison of various artificial intelligence approaches performance for estimating suspended sediment load of river systems: a case study in United States , 2015, Environmental Monitoring and Assessment.

[48]  Andrew N. Sharpley,et al.  Agricultural Phosphorus and Eutrophication , 1999 .

[49]  Anna Malagó,et al.  Modelling sediment fluxes in the Danube River Basin with SWAT. , 2017, The Science of the total environment.

[50]  Dina Makarynska,et al.  Combining deterministic modelling with artificial neural networks for suspended sediment estimates , 2015, Appl. Soft Comput..

[51]  S. Şahin.  An aridity index defined by precipitation and specific humidity , 2012 .

[52]  Xixi Lu,et al.  Sediment deposition and erosion during the extreme flood events in the middle and lower reaches of the Yangtze River , 2010 .

[53]  Hikmet Kerem Cigizoglu,et al.  Generalized regression neural network in modelling river sediment yield , 2006, Adv. Eng. Softw..

[54]  A. Karbassi,et al.  Impact of major organophosphate pesticides used in agriculture to surface water and sediment quality (Southern Caspian Sea basin, Haraz River) , 2011 .

[55]  B. Pradhan,et al.  Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran , 2012, Natural Hazards.

[56]  Hoshin Vijai Gupta,et al.  Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling , 2009 .

[57]  Saeid Janizadeh,et al.  Application of Several Data-Driven Techniques for Rainfall-Runoff Modeling , 2014 .

[58]  Vahid Nourani,et al.  Daily and monthly suspended sediment load predictions using wavelet based artificial intelligence approaches , 2015, Journal of Mountain Science.

[59]  Qiuwen Chen,et al.  Long-term precipitation forecast for drought relief using atmospheric circulation factors: a study on the Maharloo Basin in Iran , 2013 .

[60]  D. Bui,et al.  A novel hybrid arti fi cial intelligence approach for fl ood susceptibility assessment , 2018 .

[61]  M. Ehteshami,et al.  Assessment quality of a nonuniform suspended sediment transport model under unsteady flow condition (case study: Aras River) , 2015 .

[62]  J. Hintze,et al.  Violin plots : A box plot-density trace synergism , 1998 .

[63]  Özgür Kisi,et al.  Constructing neural network sediment estimation models using a data-driven algorithm , 2008, Math. Comput. Simul..

[64]  J. Freer,et al.  Using hysteresis analysis of high-resolution water quality monitoring data, including uncertainty, to infer controls on nutrient and sediment transfer in catchments. , 2016, The Science of the total environment.

[65]  Lucia Nemčíková,et al.  Classification and Regression Trees in R , 2014 .

[66]  Yong-Huang Lin,et al.  The strategy of building a flood forecast model by neuro‐fuzzy network , 2006 .

[67]  Anònim Anònim.  Keys to Soil Taxonomy , 2010 .

[68]  Veysel Güldal,et al.  2D Unit Sediment Graph Theory , 2001 .

[69]  M. Çimen,et al.  Estimation of daily suspended sediments using support vector machines , 2008 .

[70]  P. Withers,et al.  Some effects of tramlines on surface runoff, sediment and phosphorus mobilization on an erosion‐prone soil , 2006 .

[71]  C. Yoshimura,et al.  Spatio-temporal patterns of soil erosion and suspended sediment dynamics in the Mekong River Basin. , 2016, The Science of the total environment.

[72]  K. Solaimani,et al.  Watershed classification by remote sensing indices: A fuzzy c-means clustering approach , 2017, Journal of Mountain Science.

[73]  Ozgur Kisi,et al.  Methods to improve the neural network performance in suspended sediment estimation , 2006 .

[74]  Zaher Mundher Yaseen,et al.  ANN Based Sediment Prediction Model Utilizing Different Input Scenarios , 2015, Water Resources Management.

[75]  Thorsten Wagener,et al.  A vulnerability driven approach to identify adverse climate and land use change combinations for critical hydrologic indicator thresholds: Application to a watershed in Pennsylvania, USA , 2014 .

[76]  A. Ahmadi,et al.  Daily suspended sediment load prediction using artificial neural networks and support vector machines , 2013 .

[77]  D. R. Jackson,et al.  Hillslope scale surface runoff, sediment and nutrient losses associated with tramline wheelings , 2010 .

[78]  J. D. de Vicente,et al.  A microcosm experiment to determine the consequences of magnetic microparticles application on water quality and sediment phosphorus pools. , 2017, The Science of the total environment.

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

[80]  Fabián A. Bombardelli,et al.  Theoretical/numerical model for the transport of non-uniform suspended sediment in open channels , 2011 .

[81]  B. Grizzetti,et al.  Modelling water and nutrient fluxes in the Danube River Basin with SWAT , 2017, The Science of the total environment.

[82]  Jie-Lun Chiang,et al.  Suspended sediment load estimate using support vector machines in Kaoping river basin , 2011, 2011 International Conference on Consumer Electronics, Communications and Networks (CECNet).

[83]  Muhammad Raza Ul Mustafa,et al.  A Comparison of Artificial Neural Networks for Prediction of Suspended Sediment Discharge in River- A Case Study in Malaysia , 2011 .

[84]  Hikmet Kerem Cigizoglu,et al.  Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data , 2007, Environ. Model. Softw..

[85]  Ghaffar Ali,et al.  How effectively low carbon society development models contribute to climate change mitigation and adaptation action plans in Asia , 2013 .

[86]  X. Xia,et al.  Effect of water-sediment regulation of the Xiaolangdi reservoir on the concentrations, characteristics, and fluxes of suspended sediment and organic carbon in the Yellow River. , 2016, The Science of the total environment.

[87]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .

[88]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[89]  G. Benito,et al.  Land use can offset climate change induced increases in erosion in Mediterranean watersheds , 2016 .

[90]  L. Gaspar,et al.  Combining catchment modelling and sediment fingerprinting to assess sediment dynamics in a Spanish Pyrenean river system. , 2016, The Science of the total environment.

[91]  D. Sear,et al.  The impact of fine sediment accumulation on the survival of incubating salmon progeny: implications for sediment management. , 2005, The Science of the total environment.

[92]  Ranvir Singh,et al.  Estimation of temporal variation of sediment yield from small catchments through the kinematic method , 1997 .

[93]  H. Pourghasemi,et al.  Evaluating the influence of geo-environmental factors on gully erosion in a semi-arid region of Iran: An integrated framework. , 2017, The Science of the total environment.

[94]  Tadashi Suetsugi,et al.  Comparison of regionalization approaches in parameterizing sediment rating curve in ungauged catchments for subsequent instantaneous sediment yield prediction , 2014 .