The use of genetic programming to develop a predictor of swash excursion on sandy beaches

Abstract. We use genetic programming (GP), a type of machine learning (ML) approach, to predict the total and infragravity swash excursion using previously published data sets that have been used extensively in swash prediction studies. Three previously published works with a range of new conditions are added to this data set to extend the range of measured swash conditions. Using this newly compiled data set we demonstrate that a ML approach can reduce the prediction errors compared to well-established parameterizations and therefore it may improve coastal hazards assessment (e.g. coastal inundation). Predictors obtained using GP can also be physically sound and replicate the functionality and dependencies of previous published formulas. Overall, we show that ML techniques are capable of both improving predictability (compared to classical regression approaches) and providing physical insight into coastal processes.

[1]  Hunt,et al.  Design of Seawalls and Breakwaters , 1959 .

[2]  Evan B. Goldstein,et al.  A machine learning approach for the prediction of settling velocity , 2014 .

[3]  W. Brambilla,et al.  An integrated sea-land approach for mapping geomorphological and sedimentological features in an urban microtidal wave-dominated beach: a case study from S Sardinia, western Mediterranean , 2017 .

[4]  Andrea Castelletti,et al.  An evaluation framework for input variable selection algorithms for environmental data-driven models , 2014, Environ. Model. Softw..

[5]  Roham Bakhtyar,et al.  Application of neuro-fuzzy approach in prediction of runup in swash zone , 2008 .

[6]  Evan B. Goldstein,et al.  Prediction of wave ripple characteristics using genetic programming , 2013 .

[7]  Amir Etemad-Shahidi,et al.  Predicting wave run-up on rubble-mound structures using M5 model tree , 2011 .

[8]  Giovanni Coco,et al.  Wave runup during extreme storm conditions , 2011 .

[9]  Andrew D. Short,et al.  Handbook of beach and shoreface morphodynamics , 1999 .

[10]  K. T. Holland,et al.  Runup kinematics on a natural beach , 1995 .

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

[12]  R. Holman,et al.  FIELD OBSERVATIONS OF BEACH CUSPS AND SWASH MOTIONS , 1996 .

[13]  Giovanni Coco,et al.  Observations of alongshore variability of swash motions on an intermediate beach , 2012 .

[14]  Paula Camus,et al.  Analysis of clustering and selection algorithms for the study of multivariate wave climate , 2011 .

[15]  Thomas G. Dietterich.  Overfitting and undercomputing in machine learning , 1995, CSUR.

[16]  J. Irish,et al.  An empirical model for infragravity swash on barred beaches , 2013 .

[17]  R. Holman,et al.  Swash zone sediment suspension and transport and the importance of bore‐generated turbulence , 2000 .

[18]  K. Bryan,et al.  Observations of wave energy fluxes and swash motions on a low‐sloping, dissipative beach , 2013 .

[19]  Gerhard Masselink,et al.  Swash-zone morphodynamics , 2006 .

[20]  Leonardo Vanneschi,et al.  Open issues in genetic programming , 2010, Genetic Programming and Evolvable Machines.

[21]  R. McCall,et al.  A new parameterisation for runup on gravel beaches , 2016 .

[22]  M. Vousdoukas,et al.  Performance of intertidal topography video monitoring of a meso-tidal reflective beach in South Portugal , 2011 .

[23]  B. G. Ruessink,et al.  Observations of swash under highly dissipative conditions , 1998 .

[24]  Evan B. Goldstein,et al.  A data‐driven approach to develop physically sound predictors: Application to depth‐averaged velocities on flows through submerged arrays of rigid cylinders , 2015 .

[25]  R. Holman,et al.  A simple model for the spatially-variable coastal response to hurricanes , 2007 .

[26]  Marco Wiering,et al.  Recurrent neural network modeling of nearshore sandbar behavior , 2007, Neural Networks.

[27]  M. Miche.  Le pouvoir réfléchissant des ouvrages maritimes exposés à l'action de la houle , 1951 .

[28]  Hilary F. Stockdon,et al.  Empirical parameterization of setup, swash, and runup , 2006 .

[29]  M. H. Kazeminezhad,et al.  A new method for the prediction of wave runup on vertical piles , 2015 .

[30]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[31]  Suzanne J.M.H. Hulscher,et al.  Regeneration of sand waves after dredging , 2002 .

[32]  Robert A. Holman,et al.  Setup and swash on a natural beach , 1985 .

[33]  Robert A. Holman,et al.  Wave run-up on a high-energy dissipative beach , 2004 .

[34]  Peter Ruggiero,et al.  Simulating extreme total water levels using a time-dependent, extreme value approach , 2014 .

[35]  Edward B. Thornton,et al.  Swash oscillations on a natural beach , 1982 .

[36]  José A. Jiménez,et al.  Probabilistic coastal vulnerability assessment to storms at regional scale – application to Catalan beaches (NW Mediterranean) , 2011 .

[37]  K. T. Holland,et al.  The statistical distribution of swash maxima on natural beaches , 1993 .

[38]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[39]  G. Cozannet,et al.  Brief communication "Evaluating European Coastal Evolution using Bayesian Networks" , 2012 .

[40]  Robert A. Holman,et al.  Extreme value statistics for wave run-up on a natural beach , 1986 .

[41]  Pedro M. Domingos.  A few useful things to know about machine learning , 2012, Commun. ACM.

[42]  Hilary F. Stockdon,et al.  The relative contribution of waves, tides, and nontidal residuals to extreme total water levels on U.S. West Coast sandy beaches , 2017 .

[43]  T. Baldock,et al.  Hydrodynamics and sediment transport in the swash zone: a review and perspectives , 2002 .

[44]  R. Pedreros,et al.  Wave Set-up and Run-up Variability on a Complex Barred Beach During Highly Dissipative Storm Conditions , 2016 .

[45]  George L. W. Perry,et al.  Identifying the controls on coastal cliff landslides using machine-learning approaches , 2016, Environ. Model. Softw..

[46]  Luis Pedro Almeida,et al.  Coastal vulnerability assessment based on video wave run-up observations at a mesotidal, steep-sloped beach , 2011, Ocean Dynamics.

[47]  Alec Torres-Freyermuth,et al.  The second international workshop on swash-zone processes , 2016 .

[48]  D. Callaghan,et al.  Assessment of runup predictions by empirical models on non-truncated beaches on the south-east Australian coast , 2017 .

[49]  Peter Ruggiero,et al.  The influence of seasonal to interannual nearshore profile variability on extreme water levels: Modeling wave runup on dissipative beaches , 2016 .

[50]  R. Guza,et al.  Effect of wave frequency and directional spread on shoreline runup , 2012 .

[51]  John J. Marra,et al.  Wave runup, extreme water levels and the erosion of properties backing beaches , 2001 .

[52]  R. Holman,et al.  Observations of wave runup, setup, and swash on natural beaches , 2011 .

[53]  Paolo Ciavola,et al.  Evaluation of coastal vulnerability to flooding: comparison of two different methodologies adopted by the Emilia-Romagna region (Italy) , 2015 .

[54]  Giovanni Coco,et al.  The effects of tides on swash statistics on an intermediate beach , 2011 .