Asymmetric Error Functions for Reducing the Underestimation of Local Scour around Bridge Piers: Application to Neural Networks Models

AbstractMany of the empirical formulas used for the prediction of the expected scour depth at piers are excessively conservative, providing substantial overestimations. On the other hand, the recently proposed neural networks methods generally issue accurate predictions but also high percentages of underpredictions, due to the use of a symmetric error function for their parameterization. A novel error function is proposed in this paper for optimizing neural networks, giving more weight to underestimation than to overestimation discrepancies, in order to obtain safer design predictions. The performances of the proposed model on independent field records are compared with those of a conventionally trained neural network and with those of a set of widely used formulas. The asymmetric error function (that might be applied to parameterize any other model or equation, as a proficient alternative to least-square errors or envelope curves) allows researchers to obtain predictions closer to the measurements than t...

[1]  Clive W. J. Granger,et al.  Outline of forecast theory using generalized cost functions , 1999 .

[2]  Terry W. Sturm,et al.  Effect of Sediment Size Scaling on Physical Modeling of Bridge Pier Scour , 2009 .

[3]  Robert Ettema,et al.  SCOUR AT BRIDGE PIERS , 1980 .

[4]  Sven F. Crone,et al.  Utility based data mining for time series analysis: cost-sensitive learning for neural network predictors , 2005, UBDM '05.

[5]  Mufeed Odeh,et al.  Large scale clear-water local pier scour experiments , 2004 .

[6]  Roy E. Trent,et al.  Economics of Floods, Scour, and Bridge Failures , 1993 .

[7]  Jean-Louis Briaud,et al.  SRICOS: Prediction of Scour Rate in Cohesive Soils at Bridge Piers , 1999 .

[8]  Clive W. J. Granger,et al.  A Decision_Theoretic Approach to Forecast Evaluation , 2000 .

[9]  Bruce W. Melville,et al.  Evaluation of Existing Equations for Local Scour at Bridge Piers , 2014 .

[10]  V. R. Schneider,et al.  Local Scour Around Bridge Piers , 1969 .

[11]  Dong-Sheng Jeng,et al.  Bayesian neural networks for prediction of equilibrium and time-dependent scour depth around bridge piers , 2007, Adv. Eng. Softw..

[12]  Elena Toth,et al.  Prediction of local scour depth at bridge piers under clear-water and live-bed conditions: comparison of literature formulae and artificial neural networks , 2011 .

[13]  Jihn-Sung Lai,et al.  Houfeng Bridge Failure in Taiwan , 2012 .

[14]  B. Melville.  PIER AND ABUTMENT SCOUR: INTEGRATED APPROACH , 1997 .

[15]  J. Lai,et al.  Field Measurements and Simulation of Bridge Scour Depth Variations during Floods , 2008 .

[16]  Donald D. Carpenter,et al.  A critical evaluation of bridge scour for Michigan specific conditions , 2011 .

[17]  Alessio Radice,et al.  Analysis of the time‐averaged properties of sediment motion in a local scour process , 2009 .

[18]  Jean-Louis Briaud,et al.  Stochastic Flow Analysis for Predicting River Scour of Cohesive Soils , 2006 .

[19]  Sarfaraz A. Ansari,et al.  Ultimate Depth of Scour Around Bridge Piers , 1994 .

[20]  Paolo Gardoni,et al.  Observational Method for Estimating Future Scour Depth at Existing Bridges , 2010 .

[21]  P A Johnson,et al.  Comparison of Pier-Scour Equations Using Field Data , 1995 .

[22]  C R Neill,et al.  Guide to bridge hydraulics , 1973 .

[23]  David S. Mueller,et al.  Field Observations and Evaluations of Streambed Scour at Bridges , 2005 .

[24]  Yee-Meng Chiew,et al.  LOCAL SCOUR AT BRIDGE PIERS , 1984 .

[25]  William Miller,et al.  Live-Bed Local Pier Scour Experiments , 2006 .

[26]  Stanley R. Davis,et al.  Evaluating scour at bridges. , 1995 .

[27]  Stephen R. Holnbeck,et al.  Evaluation of pier-scour equations for coarse-bed streams , 2004 .

[28]  F. Diebold,et al.  Forecast Evaluation and Combination , 1996 .

[29]  J. Sterling Jones,et al.  COMPARISON OF PREDICTION EQUATIONS FOR BRIDGE PIER AND ABUTMENT SCOUR , 1984 .

[30]  H. W. Shen,et al.  Local Scour Around Cylindrical Piers , 1977 .

[31]  António H. Cardoso,et al.  Clear-water scour at comparatively large cylindrical piers , 2013 .

[32]  Rkw Chee,et al.  LIVE-BED SCOUR AT BRIDGE PIERS , 1982 .

[33]  Sven F. Crone.  Training Artificial Neural Networks using Asymmetric Cost Functions , 2002 .

[34]  R. J. Garde,et al.  SCOUR AROUND BRIDGE PIERS , 1998 .

[35]  Bruce W. Melville,et al.  Scour at Wide Piers and Long Skewed Piers , 2011 .

[36]  F. Diebold,et al.  Further results on forecasting and model selection under asymmetric loss , 1996 .

[37]  Sujit K. Bose,et al.  Clear water scour at circular piers : a model , 1995 .

[38]  M. Hashem Pesaran,et al.  Decision‐Based Methods for Forecast Evaluation , 2007 .

[39]  Sydney Nsw,et al.  Neural Network assessment for scour depth around bridge piers , 2006 .

[40]  Kittur G. Ranga Raju,et al.  TEMPORAL, VARIATION OF SCOUR AROUND CIRCULAR BRIDGE PIERS , 1992 .

[41]  Martin C. Miller,et al.  Threshold of sediment motion under unidirectional currents , 1977 .

[42]  Emmett M. Laursen,et al.  Scour Around Bridge Piers and Abutments , 1956 .

[43]  Peter F. Lagasse,et al.  ASCE Compendium of Stream Stability and Bridge Scour Papers , 2001 .

[44]  Subhash C. Jain.  Maximum Clear-Water Scour Around Circular Piers , 1981 .

[45]  F. C. Hadipriono,et al.  ANALYSIS OF RECENT BRIDGE FAILURES IN THE UNITED STATES , 2003 .

[46]  Willi H. Hager,et al.  Generalized Approach for Clear-Water Scour at Bridge Foundation Elements , 2007 .

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

[48]  Hiroshi Nago,et al.  DESIGN METHOD OF TIME-DEPENDENT LOCAL SCOUR AT CIRCULAR BRIDGE PIER , 2003 .

[49]  R. W. Vance,et al.  SCOUR AROUND BRIDGE PIERS , 1980 .

[50]  Mario Jino,et al.  Machine Learning Methods and Asymmetric Cost Function to Estimate Execution Effort of Software Testing , 2010, 2010 Third International Conference on Software Testing, Verification and Validation.

[51]  H. Md. Azamathulla,et al.  Genetic Programming to Predict Bridge Pier Scour , 2010 .

[52]  Bernard Widrow,et al.  The basic ideas in neural networks , 1994, CACM.

[53]  David C. Froelich.  Analysis of Onsite Measurements of Scour at Piers , 1988 .

[54]  Ashish Kumar,et al.  Temporal Variation of Scour around Circular Compound Piers , 2012 .

[55]  Jorge E. Pagán-Ortiz.  Status of the Scour Evaluation of Bridges over Waterways in the United States , 1998 .

[56]  Dong-Sheng Jeng,et al.  Neural Network Modeling for Estimation of Scour Depth Around Bridge Piers , 2007 .

[57]  Sung-Uk Choi,et al.  PREDICTION OF LOCAL SCOUR AROUND BRIDGE PIERS USING ARTIFICIAL NEURAL NETWORKS 1 , 2006 .

[58]  Lloyd H.C. Chua,et al.  Predicting time-dependent pier scour depth with support vector regression , 2012 .

[59]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[60]  Negin Yousefpour,et al.  Determination of Unknown Foundation of Bridges for Scour Evaluation Using Artificial Neural Networks , 2011 .

[61]  Giuliano Di Baldassarre,et al.  BRIDGE PIER SCOUR: A REVIEW OF PROCESSES, MEASUREMENTS AND ESTIMATES , 2012 .

[62]  Subhasish Dey,et al.  Temporal Scales for Live-Bed Scour at Abutments , 2010 .

[63]  B. Melville,et al.  TIME SCALE FOR LOCAL SCOUR AT BRIDGE PIERS , 2000 .

[64]  Peggy A. Johnson,et al.  Vulnerability-Based Risk Assessment for Stream Instability at Bridges , 2011 .

[65]  Allan Timmermann,et al.  Estimation and Testing of Forecast Rationality under Flexible Loss , 2005 .

[66]  Francesco Ballio,et al.  On statistical properties of bed load sediment concentration , 2009 .

[67]  Bernard Bobée,et al.  Daily reservoir inflow forecasting using artificial neural networks with stopped training approach , 2000 .

[68]  W. Hager,et al.  Temporal Evolution of Clear-Water Pier and Abutment Scour , 2002 .