Exploring Mega‐Nourishment Interventions Using Long Short‐Term Memory (LSTM) Models and the Sand Engine Surface MATLAB Framework

• Published in: Geophysical research letters 2024-02, Vol.51 (4), p.n/a
• Main Authors: Kumar, Pavitra, Leonardi, Nicoletta
• Format: Article
• Language: English
• Subjects: Adaptability; Artificial intelligence; Bathymetric changes; Climate change; Coastal protection; Coastal zone management; Computer software; Decision making; Engines; Environmental protection; Evolution; Flooding; Floods; Maintenance costs; Matlab; Sand
• ISSN: 0094-8276; 1944-8007
• DOI: 10.1029/2023GL106042

Coastal protection is of paramount importance because erosion and flooding affect millions of people living along the coast and can largely influence countries' economy. The implementation of nature‐based solutions for coastal protection, such as sand engines, has become more popular due to these interventions' adaptability to climate change. This study explores synergies between Artificial Intelligence (AI) and hydro‐morphodynamic models for the creation of efficient decision‐making tools for the choice of optimal sand engines configurations. Specifically, we investigate the use of long‐short‐term memory (LSTM) models as predictive tools for the morphological evolution of sand engines. We developed different LSTM models to predict time series of bathymetric changes across the sand engine as well as the time‐decline in the sand engine volume as a function of external forces and intervention size. Finally, a MATLAB framework was developed to return LSTM model results based on users' inputs about sand engine size and external forcings. Plain Language Summary Sand engines are a type of coastal protection where a large volume of sand is added to the coastline to protect low‐lying areas from erosion and flooding. Sand engines, like other Nature‐based solutions, are gaining popularity due to their potentially lower maintenance costs compared to other concrete‐based coastal protection strategies and a number of co‐benefits. However, there are currently no design guidelines or decision‐making tools for sand engines. Here we address this gap in the state of knowledge and use Artificial Intelligence (AI) techniques to analyze the evolution of sand engines under different waves and external forcings. AI models are also used to predict the volume of sand being transferred by the waves from the location of deposition to the surrounding areas. To facilitate the use of AI models, this study proposes a computer software, sand engine surface, which includes all the AI models developed in this study, predicting the evolution of sand engine and volume of sand being transported. Key Points This study presents models to predicts the evolution of Sand Engine over time in terms of Volumetric changes and Morphological changes All our Long Short Term Memory models' results are accessible through Sand Engine Surface Application Sand Engine Surface is MATLAB framework providing results about time‐dependent morphological changes of sand engines based on users' inputs