Predicting shoreline change using deep learning methods

Coasts are changing and it’s important to be able to predict how the position of the shoreline moves over time.

We are supporting PhD researcher Tharindu Manamperi at Swansea University in his work on predicting shoreline change over multiple time scales using deep learning methods, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network-LSTM (CNN-LSTM) models.

Tharindu has published his first paper in Coastal Engineering, an international journal for coastal engineers and scientists: https://doi.org/10.1016/j.coastaleng.2025.104856

He found that deep learning techniques have the potential to reliably predict shoreline change. Tharindu’s research also highlighted the importance of data quality and resolution in improving the performance of the models.

Citation

Tharindu Manamperi, Alma Rahat, Doug Pender, Demetra Cristaudo, Rob Lamb, Harshinie Karunarathna, Predicting shoreline changes using deep learning techniques with Bayesian Optimisation, Coastal Engineering, 2025, 104856, ISSN 0378-3839. Available at: https://doi.org/10.1016/j.coastaleng.2025.104856

Funding and support

Tharindu’s research is supported by the UK & Engineering and Physical Sciences Research Council (EPSRC) – Doctoral Training Partnerships (DTP) (EP/W524694/1) and JBA Trust (project No. W22-1128),

Tharindu is supervised by Professor Harshinie Karunarathna and Dr Alma Rahat (Swansea University), and Dr Doug Pender and Dr Demetra Cristaudo (JBA Consulting)