Blind testing of shoreline evolution models

Journal article (2020)

Authors

Jennifer Montaño The University of Auckland
Giovanni Coco The University of Auckland
Déborah Idier Bureau de Recherches Géologiques et Minières (BRGM)
Bonnie C. Ludka Scripps Institution of Oceanography
Sina Masoud-Ansari The University of Auckland
Fernando J. Méndez University of Cantabria
A. Brad Murray Duke University
Nathaniel G. Plant St. Petersburg Coastal and Marine Science Center
Katherine M. Ratliff Duke University
Arthur Robinet Bureau de Recherches Géologiques et Minières (BRGM), CEA
A. Rueda University of Cantabria
José A. Á. Antolínez University of Cantabria
Joshua A. Simmons University of New South Wales
K. D. Splinter University of New South Wales
S. A. Stephens National Institute of Water and Atmospheric Research (NIWA)
I. H. Townend University of Southampton
Sean Vitousek University of Illinois at Chicago, North Central Climate Science Centre
Kilian Vos University of New South Wales
Tomas Beuzen University of New South Wales
Karin R. Bryan University of Waikato
Laura Cagigal The University of Auckland, University of Cantabria
Mark Davidson Plymouth University
Evan B. Goldstein University of North Carolina
Raimundo Ibaceta University of New South Wales
Affiliation
External organisation
More Info
expand_more

Published Date

01-12-2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Affiliation

External organisation

Abstract

Beaches around the world continuously adjust to daily and seasonal changes in wave and tide conditions, which are themselves changing over longer time-scales. Different approaches to predict multi-year shoreline evolution have been implemented; however, robust and reliable predictions of shoreline evolution are still problematic even in short-term scenarios (shorter than decadal). Here we show results of a modelling competition, where 19 numerical models (a mix of established shoreline models and machine learning techniques) were tested using data collected for Tairua beach, New Zealand with 18 years of daily averaged alongshore shoreline position and beach rotation (orientation) data obtained from a camera system. In general, traditional shoreline models and machine learning techniques were able to reproduce shoreline changes during the calibration period (1999–2014) for normal conditions but some of the model struggled to predict extreme and fast oscillations. During the forecast period (unseen data, 2014–2017), both approaches showed a decrease in models’ capability to predict the shoreline position. This was more evident for some of the machine learning algorithms. A model ensemble performed better than individual models and enables assessment of uncertainties in model architecture. Research-coordinated approaches (e.g., modelling competitions) can fuel advances in predictive capabilities and provide a forum for the discussion about the advantages/disadvantages of available models.