Rob Schepper, Rafael Almar, Erwin W. J. Bergsma, Sierd de Vries, Ad Reniers, Mark Davidson, Kristen D Splinter 

Understanding and predicting shoreline changes is paramount to coastal managers to anticipate potential threats. These shoreline changes are often driven by complex processes at multiple timescales. In this paper, a new approach to model wave-driven, cross-shore shoreline change incorporating multiple timescales is introduced. As a base we use the equilibrium shoreline prediction model ShoreFor that accounts for a single timescale only. High resolution data collected at four distinctly different study-sites is used to train the new data driven model. The four data-sets together cover sites that are mid latitude storm-dominated, under the influence of tropical cyclones and monsoons, and equatorial storm-free dominated by seasonal climate variability. In addition to the direct forcing approach used in most models, here two additional terms are introduced: 1) a time-upscaling and 2) a time-downscaling approach. The upscaling approach accounts for the persistent effect of short term events, such as storms, on the shoreline position. The downscaling approach accounts for the effect of long term shoreline modulation on shorter event impacts. The multi-timescale model shows considerable improvement compared to the direct-forcing approach in the original ShoreFor model at the four contrasted sites.