The use of genetic programming to develop a predictor of swash excursion on sandy beaches
Marinella Passarella1,Evan B. Goldstein2,Sandro De Muro1,and Giovanni Coco3Marinella Passarella et al.Marinella Passarella1,Evan B. Goldstein2,Sandro De Muro1,and Giovanni Coco3
1Department of Chemical and Geological Sciences, Coastal and Marine
Geomorphology Group (CMGG), Università degli Studi di Cagliari, 09124 Cagliari, Italy
2Department of Geological Sciences, University of North Carolina at Chapel Hill, 104 South Rd, Mitchell Hall, Chapel Hill, NC 27599, USA
3School of Environment, Faculty of Science, University of Auckland, Auckland, 1142, New Zealand
1Department of Chemical and Geological Sciences, Coastal and Marine
Geomorphology Group (CMGG), Università degli Studi di Cagliari, 09124 Cagliari, Italy
2Department of Geological Sciences, University of North Carolina at Chapel Hill, 104 South Rd, Mitchell Hall, Chapel Hill, NC 27599, USA
3School of Environment, Faculty of Science, University of Auckland, Auckland, 1142, New Zealand
Received: 23 Jun 2017 – Discussion started: 04 Oct 2017 – Revised: 11 Dec 2017 – Accepted: 20 Dec 2017 – Published: 28 Feb 2018
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.