An Improvement on Estimated Drifter Tracking through Machine Learning and Evolutionary Search

Autor: Hwi-Yeon Cho, Yong-Wook Nam, Do-Youn Kim, Yong-Hyuk Kim, Seung-Hyun Moon
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Radial basis function network
010504 meteorology & atmospheric sciences
02 engineering and technology
Tracking (particle physics)
Machine learning
computer.software_genre
01 natural sciences
lcsh:Technology
Wind speed
Evolutionary computation
lcsh:Chemistry
Position (vector)
0202 electrical engineering
electronic engineering
information engineering
General Materials Science
Instrumentation
lcsh:QH301-705.5
0105 earth and related environmental sciences
Mathematics
Fluid Flow and Transfer Processes
business.industry
lcsh:T
Process Chemistry and Technology
Deep learning
General Engineering
deep learning
lcsh:QC1-999
Computer Science Applications
Drifter
machine learning
Flow velocity
lcsh:Biology (General)
lcsh:QD1-999
drifter trajectory
NCLS
lcsh:TA1-2040
evolutionary computation
020201 artificial intelligence & image processing
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
computer
lcsh:Physics
Zdroj: Applied Sciences
Volume 10
Issue 22
Applied Sciences, Vol 10, Iss 8123, p 8123 (2020)
ISSN: 2076-3417
DOI: 10.3390/app10228123
Popis: In this study, we estimated drifter tracking over seawater using machine learning and evolutionary search techniques. The parameters used for the prediction are the hourly position of the drifter, the wind velocity, and the flow velocity of each drifter position. Our prediction model was constructed through cross-validation. Trajectories were affected by wind velocity and flow velocity from the starting points of drifters. Mean absolute error (MAE) and normalized cumulative Lagrangian separation (NCLS) were used to evaluate various prediction models. Radial basis function network showed the lowest MAE of 0.0556, an improvement of 35.20% over the numerical model MOHID. Long short-term memory showed the highest NCLS of 0.8762, an improvement of 6.24% over MOHID.
Databáze: OpenAIRE
Externí odkaz: