The assessment of coastal erosion, and coastal processes in general, has become a pivotal task to be monitored for years, since such problem turned into a primary concern more and more over time. Indeed, it endangers not only the marine ecosystem (e.g., shoreline flora and fauna), but also anthropic activities taking place near the shore. Similarly, also infrastructures deployed in such contexts may be potentially harmed by coastal erosion. To this end, this work proposes a Machine Learning (ML) approach to track marine sediments. The ML models are trained and tested by resorting to a dataset collected throughout an already performed experiment of sediment tracking. It involved a set of ad-hoc tracers, that consisted of pebbles given with Radio Frequency Identification (RFID) tags. The results proved that the proposed ML models are able to estimate the tracers displacements achieving a Root Mean Squared Error (RMSE) of 1.69m and 1.09m respectively for x and y coordinates.

Machine Learning Techniques Applied to RFID-based Marine Sediment Tracking

Bertoni Duccio
Secondo
;
Sarti Giovanni
Ultimo
2023-01-01

Abstract

The assessment of coastal erosion, and coastal processes in general, has become a pivotal task to be monitored for years, since such problem turned into a primary concern more and more over time. Indeed, it endangers not only the marine ecosystem (e.g., shoreline flora and fauna), but also anthropic activities taking place near the shore. Similarly, also infrastructures deployed in such contexts may be potentially harmed by coastal erosion. To this end, this work proposes a Machine Learning (ML) approach to track marine sediments. The ML models are trained and tested by resorting to a dataset collected throughout an already performed experiment of sediment tracking. It involved a set of ad-hoc tracers, that consisted of pebbles given with Radio Frequency Identification (RFID) tags. The results proved that the proposed ML models are able to estimate the tracers displacements achieving a Root Mean Squared Error (RMSE) of 1.69m and 1.09m respectively for x and y coordinates.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/1225067
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact