Development of hybrid machine learning and deep learning techniques for sea level rise projection in Dubai
Year: 2025
Type: article
Abstract: Sea level rise (SLR) is now a growing threat that endangers coastal environments and populations worldwide. This study develops and evaluates a hybrid deep learning model combining one-dimensional convolutional neural networks (Conv1D) and long short-term memory (LSTM) networks for near-term projection of SLR at five major locations along Dubai’s coastline. The model was trained on historical data from 2004 to 2019 and successfully forecasted sea levels through 2030. The results show an increase in sea levels at all sites by 2030, with the Mamzar area facing the highest average annual rise of 0.18 mm per year. Additionally, the study extends sea level forecasts to 2050 using a K-Nearest Neighbours (KNN) Regressor, an RF Regressor, and a simple Dense deep learning model. Among these methods, the Dense deep learning model demonstrated the best performance, achieving a mean squared error (MSE) of 0.2143.. The Conv1D-LSTM model achieved a projection accuracy with a mean squared error (MSE) of 0.21 and a mean absolute percentage error (MAPE) of 14.39%, validating its reliability. These projections indicate that Al Jadaf, Dhaw Wharfage, and Umm Sugeim are high-risk areas. The outcomes highlight the need for sustainable planning and SLR mitigation strategies.
Institution: American University of Sharjah
Language: English
Topic: Coastal and Marine Dynamics
Subfield: Earth-Surface Processes
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,790
Funder: American University of Sharjah
OpenAlex ID: W4417423349