Comparative Studies of Different Imputation Methods for Recovering Streamflow Observation

Faulty field sensors cause unreliability in the observed data that needed to calibrate and assess hydrology models. However, it is illogical to ignore abnormal or missing values if there are limited data available. This study addressed this problem by applying data imputation to replace incorrect values and recover missing streamflow information in the dataset of the Samho gauging station at Taehwa River (TR), Korea from 2004 to 2006. Soil and Water Assessment Tool (SWAT) and two machine learning techniques, Artificial Neural Network (ANN) and Self Organizing Map (SOM), were employed to estimate streamflow using reasonable flow datasets of Samho station from 2004 to 2009. The machine learning models were generally better at capturing high flows, while SWAT was better at simulating low flows.

[1]  Fernando Bação,et al.  Applications of Different Self‐Organizing Map Variants to Geographical Information Science Problems , 2008 .

[2]  Y. Pachepsky,et al.  Prediction of contamination potential of groundwater arsenic in Cambodia, Laos, and Thailand using artificial neural network. , 2011, Water research.

[3]  Lifeng Xi,et al.  Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods , 2007 .

[4]  John R. Williams,et al.  LARGE AREA HYDROLOGIC MODELING AND ASSESSMENT PART I: MODEL DEVELOPMENT 1 , 1998 .

[5]  Mi-Hyun Park,et al.  The modified SWAT model for predicting fecal coliforms in the Wachusett Reservoir Watershed, USA. , 2012, Water Research.

[6]  Y. Pachepsky,et al.  Effect of streambed bacteria release on E. coli concentrations: Monitoring and modeling with the modified SWAT , 2010 .

[7]  Adebayo Adeloye,et al.  Replacing outliers and missing values from activated sludge data using kohonen self-organizing map , 2007 .

[8]  A. Bonafe,et al.  Neural Networks For Daily Mean FlowForecasting , 1970 .

[9]  Peder Hjorth,et al.  Imputation of missing values in a precipitation–runoff process database , 2009 .

[10]  Jamshid Piri,et al.  Application of ANN and ANFIS models for reconstructing missing flow data , 2010, Environmental monitoring and assessment.

[11]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[12]  Chuntian Cheng,et al.  Daily Reservoir Runoff Forecasting Method Using Artificial Neural Network Based on Quantum-behaved Particle Swarm Optimization , 2015 .

[13]  S. O. Prasher,et al.  Use of Artificial Neural Networks in Transient Drainage Design , 1996 .

[14]  W. C. Lennox,et al.  Comparative Studies in Problems of Missing Extreme Daily Streamflow Records , 2009 .

[15]  Adebayo J. Adeloye.  The relative utility of regression and artificial neural networks models for rapidly predicting the capacity of water supply reservoirs , 2009, Environ. Model. Softw..

[16]  J. R. Wallis,et al.  A daily hydroclimatological data set for the continental United States , 1991 .

[17]  Adebayo Adeloye,et al.  Infilling of missing rainfall and streamflow data in the Shire River basin, Malawi – A self organizing map approach , 2012 .

[18]  Sangman Jeong,et al.  Evaluation of physical fish habitat quality enhancement designs in urban streams using a 2D hydrodynamic model , 2010 .

[19]  Jeffrey G. Arnold,et al.  Automatic calibration of a distributed catchment model , 2001 .

[20]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[21]  R. Hirsch.  A Comparison of Four Streamflow Record Extension Techniques , 1982 .

[22]  Raghavan Srinivasan,et al.  Development and Integration of Sub-hourly Rainfall–Runoff Modeling Capability Within a Watershed Model , 2010 .

[23]  Christian W. Dawson,et al.  Hydrological modelling using artificial neural networks , 2001 .

[24]  A. M. Kalteh,et al.  Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application , 2008, Environ. Model. Softw..

[25]  Juha Vesanto,et al.  Neural Network Tool for Data Mining: SOM Toolbox , 2000 .

[26]  Deva K. Borah,et al.  Storm Event and Continuous Hydrologic Modeling for Comprehensive and Efficient Watershed Simulations , 2007 .

[27]  Hong Guo,et al.  Prediction of effluent concentration in a wastewater treatment plant using machine learning models. , 2015, Journal of environmental sciences.

[28]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

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

[30]  P. Gyau-Boakye,et al.  Filling gaps in runoff time series in West Africa , 1994 .

[31]  Robert M. Hirsch,et al.  An evaluation of some record reconstruction techniques , 1979 .

[32]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[33]  Pan Liu,et al.  Daily Runoff Forecasting Model Based on ANN and Data Preprocessing Techniques , 2015 .

[34]  D Stephenson,et al.  Infilling streamflow data using feed-forward back-propagation (BP) artificial neural networks: Application of standard BP and pseudo Mac Laurin power series BP techniques , 2007 .

[35]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[36]  Indrajeet Chaubey,et al.  SENSITIVITY ANALYSIS, CALIBRATION, AND VALIDATIONS FOR A MULTISITE AND MULTIVARIABLE SWAT MODEL 1 , 2005 .

[37]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.