Improving Shoreline Forecasting Models with Multi-Objective Genetic Programming

Mahmoud Al Najar , Rafael Almar, Erwin W. J. Bergsma, Jean-Marc Delvit, Dennis G. Wilson

Given the current context of climate change and increasing population densities at coastal zones, there is an increasing need to be able to predict the development of our coasts. Recent advances in artificial intelligence allow for automatic analysis of observational data. This work makes use of Symbolic Regression, a type of Machine Learning algorithm, to evolve interpretable shoreline forecasting models. Cartesian Genetic Programming (CGP) is used in order to encode and improve upon ShoreFor, a shoreline prediction model. Coupled with NSGA-II, the CGP individuals are evaluated and selected during evolution according to their predictive skills at five coastal sites. This work presents a comparison between the CGP-evolved models and the base ShoreFor model. In addition to its ability to produce well-performing models, the work demonstrates the usefulness of CGP as a research tool to gain insight into the behaviors of shorelines at different points around the globe.