Journal of Marine Systems, volume 186, pages 29-36

An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts

Odonncha Fearghal 1
Zhang Yushan 2
Chen Bei 1
James Scott C. 3
1
 
IBM Research -- Ireland
2
 
University of Notre dame, USA
3
 
Baylor University, USA
Publication typeJournal Article
Publication date2018-10-01
Quartile SCImago
Q1
Quartile WOS
Q1
Impact factor2.8
ISSN09247963, 18791573
Ecology, Evolution, Behavior and Systematics
Aquatic Science
Oceanography
Abstract
This study investigates near-shore circulation and wave characteristics applied to a case-study site in Monterey Bay, California. We integrate physics-based models to resolve wave conditions together with a machine-learning algorithm that combines forecasts from multiple, independent models into a single “best-estimate” prediction of the true state. The Simulating WAves Nearshore (SWAN) physics-based model is used to compute wind-augmented waves. Ensembles are developed based on multiple simulations perturbing data input to the model. A learning-aggregation technique uses historical observations and model forecasts to calculate a weight for each ensemble member. We compare the weighted ensemble predictions with measured data to evaluate performance against present state-of-the-art. Finally, we discuss how this framework that integrates data-driven and physics-based approaches can outperform either technique in isolation.

Citations by journals

1
2
3
4
5
Applied Ocean Research
Applied Ocean Research, 5, 13.89%
Applied Ocean Research
5 publications, 13.89%
Ocean Engineering
Ocean Engineering, 5, 13.89%
Ocean Engineering
5 publications, 13.89%
Journal of Marine Systems
Journal of Marine Systems, 2, 5.56%
Journal of Marine Systems
2 publications, 5.56%
Computers and Geosciences
Computers and Geosciences, 1, 2.78%
Computers and Geosciences
1 publication, 2.78%
Procedia Computer Science
Procedia Computer Science, 1, 2.78%
Procedia Computer Science
1 publication, 2.78%
Geophysical Research Letters
Geophysical Research Letters, 1, 2.78%
Geophysical Research Letters
1 publication, 2.78%
Frontiers in Earth Science
Frontiers in Earth Science, 1, 2.78%
Frontiers in Earth Science
1 publication, 2.78%
Applied Sciences (Switzerland)
Applied Sciences (Switzerland), 1, 2.78%
Applied Sciences (Switzerland)
1 publication, 2.78%
Fluids
Fluids, 1, 2.78%
Fluids
1 publication, 2.78%
Remote Sensing
Remote Sensing, 1, 2.78%
Remote Sensing
1 publication, 2.78%
Frontiers in Marine Science
Frontiers in Marine Science, 1, 2.78%
Frontiers in Marine Science
1 publication, 2.78%
Journal of Earth System Science
Journal of Earth System Science, 1, 2.78%
Journal of Earth System Science
1 publication, 2.78%
Natural Hazards
Natural Hazards, 1, 2.78%
Natural Hazards
1 publication, 2.78%
Water Resources Management
Water Resources Management, 1, 2.78%
Water Resources Management
1 publication, 2.78%
Nature Reviews Physics
Nature Reviews Physics, 1, 2.78%
Nature Reviews Physics
1 publication, 2.78%
Ecological Informatics
Ecological Informatics, 1, 2.78%
Ecological Informatics
1 publication, 2.78%
Ocean Modelling
Ocean Modelling, 1, 2.78%
Ocean Modelling
1 publication, 2.78%
Marine Structures
Marine Structures, 1, 2.78%
Marine Structures
1 publication, 2.78%
Journal of Computational Physics
Journal of Computational Physics, 1, 2.78%
Journal of Computational Physics
1 publication, 2.78%
Environmental Modelling and Software
Environmental Modelling and Software, 1, 2.78%
Environmental Modelling and Software
1 publication, 2.78%
Coastal Engineering
Coastal Engineering, 1, 2.78%
Coastal Engineering
1 publication, 2.78%
Quarterly Journal of the Royal Meteorological Society
Quarterly Journal of the Royal Meteorological Society, 1, 2.78%
Quarterly Journal of the Royal Meteorological Society
1 publication, 2.78%
Lecture Notes in Computer Science
Lecture Notes in Computer Science, 1, 2.78%
Lecture Notes in Computer Science
1 publication, 2.78%
Energies
Energies, 1, 2.78%
Energies
1 publication, 2.78%
Earth and Space Science
Earth and Space Science, 1, 2.78%
Earth and Space Science
1 publication, 2.78%
Journal of Fluid Mechanics
Journal of Fluid Mechanics, 1, 2.78%
Journal of Fluid Mechanics
1 publication, 2.78%
1
2
3
4
5

Citations by publishers

5
10
15
20
Elsevier
Elsevier, 20, 55.56%
Elsevier
20 publications, 55.56%
Springer Nature
Springer Nature, 5, 13.89%
Springer Nature
5 publications, 13.89%
Multidisciplinary Digital Publishing Institute (MDPI)
Multidisciplinary Digital Publishing Institute (MDPI), 4, 11.11%
Multidisciplinary Digital Publishing Institute (MDPI)
4 publications, 11.11%
Wiley
Wiley, 3, 8.33%
Wiley
3 publications, 8.33%
Frontiers Media S.A.
Frontiers Media S.A., 2, 5.56%
Frontiers Media S.A.
2 publications, 5.56%
Cambridge University Press
Cambridge University Press, 1, 2.78%
Cambridge University Press
1 publication, 2.78%
5
10
15
20
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Odonncha F. et al. An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts // Journal of Marine Systems. 2018. Vol. 186. pp. 29-36.
GOST all authors (up to 50) Copy
Odonncha F., Zhang Y., Chen B., James S. C. An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts // Journal of Marine Systems. 2018. Vol. 186. pp. 29-36.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1016/j.jmarsys.2018.05.006
UR - https://doi.org/10.1016%2Fj.jmarsys.2018.05.006
TI - An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts
T2 - Journal of Marine Systems
AU - Odonncha, Fearghal
AU - Zhang, Yushan
AU - Chen, Bei
AU - James, Scott C.
PY - 2018
DA - 2018/10/01 00:00:00
PB - Elsevier
SP - 29-36
VL - 186
SN - 0924-7963
SN - 1879-1573
ER -
BibTex
Cite this
BibTex Copy
@article{2018_Odonncha,
author = {Fearghal Odonncha and Yushan Zhang and Bei Chen and Scott C. James},
title = {An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts},
journal = {Journal of Marine Systems},
year = {2018},
volume = {186},
publisher = {Elsevier},
month = {oct},
url = {https://doi.org/10.1016%2Fj.jmarsys.2018.05.006},
pages = {29--36},
doi = {10.1016/j.jmarsys.2018.05.006}
}
Found error?