Over het archief
Het OWA, het open archief van het Waterbouwkundig Laboratorium heeft tot doel alle vrij toegankelijke onderzoeksresultaten van dit instituut in digitale vorm aan te bieden. Op die manier wil het de zichtbaarheid, verspreiding en gebruik van deze onderzoeksresultaten, alsook de wetenschappelijke communicatie maximaal bevorderen.
Dit archief wordt uitgebouwd en beheerd volgens de principes van de Open Access Movement, en het daaruit ontstane Open Archives Initiative.
Basisinformatie over ‘Open Access to scholarly information'.
Implementing Deep Learning Techniques in Port Agitation Studies Under the Context of Climate Change
Ioannou, R.; Portillo Juan, N.; Olalde Rodriguez, J.; Negro Valdecantos, V.; Troch, P. (2025). Implementing Deep Learning Techniques in Port Agitation Studies Under the Context of Climate Change. J. Mar. Sci. Eng. 13(11): 2083. https://dx.doi.org/10.3390/jmse13112083
In: Journal of Marine Science and Engineering. MDPI: Basel. ISSN 2077-1312; e-ISSN 2077-1312, meer
|  |
| Author keywords |
port agitation;climate change;artificial intelligence;Mediterranean Sea;artificial neural networks;surrogate model;MILDwave;impacts;harbor;sea;adaptation;operability |
| Auteurs | | Top |
- Ioannou, R.
- Portillo Juan, N.
- Olalde Rodriguez, J.
|
- Negro Valdecantos, V.
- Troch, P., meer
|
|
| Abstract |
Climate change is impacting atmospheric patterns and therefore wave conditions, with ports being among the most affected infrastructures, making it crucial to ensure their operability under changing climatic conditions. Most scientific studies on climate change focus on coastal erosion and flooding, whereas research on its impact on port operability remains relatively scarce. This challenge could be tackled with the emergence of Artificial Intelligence (AI), where alternative modeling approaches can be developed. Thus, a novel AI-based model specifically designed for studying port agitation is introduced herein. By integrating a hybrid deep learning approach, combining Feedforward Neural Networks (FFNNs) to model wave climate and Convolutional Neural Networks (CNNs) for port image analysis, port agitation has been successfully predicted compared to linear wave propagation models. This marks the first instance of utilizing image processing tools to analyze port agitation, resulting in a model with a remarkably low error rate, while offering a significant reduction in computational time compared to traditional wave propagation models, reducing computational time by a factor of four to ten. The accuracy of the proposed model has been investigated and validated for the Port of Valencia, located in the Spanish section of the Mediterranean Sea. |
IMIS is ontwikkeld en wordt gehost door het VLIZ.
