FOWD: A Free Ocean Wave Dataset for Data Mining and Machine Learning
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
FOWD : A Free Ocean Wave Dataset for Data Mining and Machine Learning. / Hafner, Dion; Gemmrich, Johannes; Jochum, Markus.
In: Journal of Atmospheric and Oceanic Technology, Vol. 38, No. 7, 23.07.2021, p. 1305-1322.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - FOWD
T2 - A Free Ocean Wave Dataset for Data Mining and Machine Learning
AU - Hafner, Dion
AU - Gemmrich, Johannes
AU - Jochum, Markus
PY - 2021/7/23
Y1 - 2021/7/23
N2 - The occurrence of extreme (rogue) waves in the ocean is for the most part still shrouded in mystery, because the rare nature of these events makes them difficult to analyze with traditional methods. Modern data-mining and machine-learning methods provide a promising way out, but they typically rely on the availability of massive amounts of well-cleaned data. To facilitate the application of such data-hungry methods to surface ocean waves, we developed the Free Ocean Wave Dataset (FOWD), a freely available wave dataset and processing framework. FOWD describes the conversion of raw observations into a catalog that maps characteristic sea state parameters to observed wave quantities. Specifically, we employ a running-window approach that respects the nonstationary nature of the oceans, and extensive quality control to reduce bias in the resulting dataset. We also supply a reference Python implementation of the FOWD processing toolkit, which we use to process the entire Coastal Data Information Program (CDIP) buoy data catalog containing over 4 billion waves. In a first experiment, we find that, when the full elevation time series is available, surface elevation kurtosis and maximum wave height are the strongest univariate predictors for rogue wave activity. When just a spectrum is given, crest-trough correlation, spectral bandwidth, and mean period fill this role.
AB - The occurrence of extreme (rogue) waves in the ocean is for the most part still shrouded in mystery, because the rare nature of these events makes them difficult to analyze with traditional methods. Modern data-mining and machine-learning methods provide a promising way out, but they typically rely on the availability of massive amounts of well-cleaned data. To facilitate the application of such data-hungry methods to surface ocean waves, we developed the Free Ocean Wave Dataset (FOWD), a freely available wave dataset and processing framework. FOWD describes the conversion of raw observations into a catalog that maps characteristic sea state parameters to observed wave quantities. Specifically, we employ a running-window approach that respects the nonstationary nature of the oceans, and extensive quality control to reduce bias in the resulting dataset. We also supply a reference Python implementation of the FOWD processing toolkit, which we use to process the entire Coastal Data Information Program (CDIP) buoy data catalog containing over 4 billion waves. In a first experiment, we find that, when the full elevation time series is available, surface elevation kurtosis and maximum wave height are the strongest univariate predictors for rogue wave activity. When just a spectrum is given, crest-trough correlation, spectral bandwidth, and mean period fill this role.
KW - Wave properties
KW - Waves, oceanic
KW - Data mining
KW - Data processing
KW - Data quality control
KW - Data science
KW - Machine learning
KW - ROGUE WAVES
KW - KURTOSIS
U2 - 10.1175/JTECH-D-20-0185.1
DO - 10.1175/JTECH-D-20-0185.1
M3 - Journal article
VL - 38
SP - 1305
EP - 1322
JO - Journal of Atmospheric and Oceanic Technology
JF - Journal of Atmospheric and Oceanic Technology
SN - 0739-0572
IS - 7
ER -
ID: 275993811