Open AccessPrediction of Environmental Conditions for Maritime Navigation using a Network of Sensors: A Practical Application of Graph Neural Networks
Author(s) -
Caio Fabricio Deberaldini Netto,
Eduardo A. Tannuri,
Denis Deratani Mauá,
Fábio Gagliardi Cozman
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/kdmile.2020.11981
Subject(s) - computer science , sort , artificial neural network , domain (mathematical analysis) , graph , task (project management) , process (computing) , graphical model , artificial intelligence , machine learning , data mining , theoretical computer science , information retrieval , engineering , systems engineering , mathematical analysis , mathematics , operating system
This paper describes a real application of graphical neural networks (GNNs) in the dynamic estimation of spatially distributed buoys that are of central importance in maritime navigation. We describe the techniques we used to process both data and background knowledge about the domain, indicating why GNNs are particularly well suited for this sort of task. We report our empirical results, demonstrating that GNNs profitably use the avaible relational structure.