Improving multi-decadal coastal shoreline change predictions by including model parameter non-stationarity

Abstract

Our ability to predict sandy shoreline evolution resulting from future changes in regional wave climates is critical for the sustainable management of coastlines worldwide. To this end, the present generation of simple and efficient semi-empirical shoreline change models have shown good skill at predicting shoreline changes from seasons up to several years at a number of diverse sites around the world. However, a key limitation of these existing approaches is that they rely on time-invariant model parameters, and assume that beaches will evolve within constrained envelopes of variability based on past observations. This raises an interesting challenge because the expected future variability in key meteocean and hydrodynamic drivers of shoreline change are likely to violate this ‘stationary’ approach to longer-term shoreline change prediction. Using a newly available, multi-decadal (28-year) dataset of satellite-derived shorelines at the Gold Coast, Australia, this contribution presents the first attempt to improve multi-decadal shoreline change predictions by allowing the magnitude of the shoreline model parameters to vary in time. A data assimilation technique (Ensemble Kalman Filter, EnKF) embedded within the well-established ShoreFor shoreline change model is first applied to a 14-year training period of approximately fortnightly shoreline observations, to explore temporal variability in model parameters. Then, the magnitudes of these observed non-stationary parameters are modelled as a function of selected wave climate covariates, representing the underlying seasonal to interannual variability in wave forcing. These modelled time-varying parameters are then incorporated into the shoreline change model and tested over the complete 28-year dataset. This new inclusion of non-stationary model parameters that are directly modelled as a function of the underlying wave forcing and corresponding time scales of beach response, is shown to outperform the multi-decadal predictions obtained by applying the conventional stationary approach (RMSEnon-stationary = 11.1 m; RMSEstationary = 254.3 m). Based on these results, it is proposed that a non-stationary approach to shoreline change modelling can reduce the uncertainty associated with the misspecification of physical processes driving shoreline change and should be considered for future shoreline change predictions.

On the use of Convolutional Deep Learning to predict shoreline change

“…In previous works, diverse metrics have been used to evaluate shoreline models performance (e.g., Ibaceta et al, 2022;Jaramillo et al, 2020;Montaño et al, 2021), and although no consensus has been reached on a standard evaluation procedure, the current approach is to use a combination of absolute value error statistics, goodness-of-fitness statistics, and graphical results, as done in other water science areas (e.g., Biondi et al, 2012). For this contribution, of particular interest was the assessment of the models' capability to reproduce the shoreline variability (which we consider to be captured by the standard deviation).…”

Improving Shoreline Forecasting Models with Multi-Objective Genetic Programming

“…least-squares-fit). A large number of hybrid models have been developed in the literature (Davidson et al, 2013;Turki et al, 2013;Vitousek et al, 2017;Ibaceta et al, 2022). Compared to process-based models, hybrid models can be used to predict shoreline position over much longer time scales, however they are generally unable to generalize to previouslyunseen areas and require site-specific field data for model calibration.…”

Which data assimilation method to use and when: unlocking the potential of observations in shoreline modelling

“…The free model parameters to be tuned through DA should not change with variations in climate forcing (waves and water levels) because, by definition, they are independent of any other model input. In reality, however, this expectation may not hold (Ibaceta et al 2020(Ibaceta et al , 2022, and climate variability may consequently compromise the quality of the calibration process, due to hidden dependencies between the wave climate and the free model parameters that should be disentangled by the assimilation algorithm. Thus, shoreline forecasts may benefit from the incorporation of climate-dependent parametrizations, as the world's coasts are expected to be exposed to unprecedented drivers due to climate change (Toimil et al 2020b, Lobeto et al 2021.…”