2021
DOI: 10.31223/x54c73
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Modelling cross-shore shoreline change on multiple timescales and their interactions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 48 publications
(94 reference statements)
0
3
0
Order By: Relevance
“…ShoreFor has been used in multiple shoreline prediction studies and a number of extensions have been proposed to improve its performance by accounting for shoreline change over different time-scales (Schepper et al, 2021) as well as alongshore sediment transport processes (Tran and Barthélemy, 2020;Tran et al, 2021). We make use of the ShoreFor model as a base for our experiments on the use of CGP for shoreline forecasting in a GI setting, and we highlight the possibility of extending the base CGP-ShoreFor implementation to account for these additional processes.…”
Section: Shoreformentioning
confidence: 99%
“…ShoreFor has been used in multiple shoreline prediction studies and a number of extensions have been proposed to improve its performance by accounting for shoreline change over different time-scales (Schepper et al, 2021) as well as alongshore sediment transport processes (Tran and Barthélemy, 2020;Tran et al, 2021). We make use of the ShoreFor model as a base for our experiments on the use of CGP for shoreline forecasting in a GI setting, and we highlight the possibility of extending the base CGP-ShoreFor implementation to account for these additional processes.…”
Section: Shoreformentioning
confidence: 99%
“…(5) in which 𝑛 is the number of timesteps in the considered timeseries prior to the considered timestep, Ω 𝑛 is the dimensionless fall velocity at timestep 𝑛, and ϕ is the memory decay factor. This memory decay factor determines the number of antecedent timesteps that are considered (Davidson et al, 2013;Schepper et al, 2021). A large memory decay factor generates a slowly varying timeseries, considering and averaging many prior timesteps, while a small decay factor produces a timeseries with faster oscillations.…”
Section: Machine Learning Modelmentioning
confidence: 99%
“…Neural networks have been applied to coastal engineering problems in a few cases, e.g. wave overtopping has been predicted using neural networks (van Gent et al, 2007;Verhaeghe et al, 2008), and using GPEs (Pullen et al, 2018). Morphological changes, specifically beach volume changes, have however to our knowledge not previously been predicted using machine learning algorithms.…”
Section: Introductionmentioning
confidence: 99%