GLOBAL SHORELINE FORECASTING USING SATELLITE-DERIVED DATA AND INTERPRETABLE MACHINE LEARNING

Coastal development and climate change are changing the geography of our coasts, while more and more people are moving towards the coasts. Recent advances in artificial intelligence and remote sensing allow for the automatic analysis of observational data at a global scale. Symbolic Regression (SR) is a family of Machine Learning (ML) algorithms for constructing symbolic mathematical expressions which model the relations between inputs and outputs in training data. In this work, we make use of SR and a novel global-scale shoreline forecasting dataset in order to construct globally-applicable and interpretable shoreline forecasting models, and we demonstrate the potential of SR as an alternative data-driven method for coastal modelling and prediction tasks.