Articles | Volume 5, issue 2
https://doi.org/10.5194/ascmo-5-147-2019
https://doi.org/10.5194/ascmo-5-147-2019
21 Nov 2019
 | 21 Nov 2019

Automated detection of weather fronts using a deep learning neural network

James C. Biard and Kenneth E. Kunkel

Related authors

Observations for Model Intercomparison Project (Obs4MIPs): status for CMIP6
Duane Waliser, Peter J. Gleckler, Robert Ferraro, Karl E. Taylor, Sasha Ames, James Biard, Michael G. Bosilovich, Otis Brown, Helene Chepfer, Luca Cinquini, Paul J. Durack, Veronika Eyring, Pierre-Philippe Mathieu, Tsengdar Lee, Simon Pinnock, Gerald L. Potter, Michel Rixen, Roger Saunders, Jörg Schulz, Jean-Noël Thépaut, and Matthias Tuma
Geosci. Model Dev., 13, 2945–2958, https://doi.org/10.5194/gmd-13-2945-2020,https://doi.org/10.5194/gmd-13-2945-2020, 2020
Short summary

Related subject area

Atmospheric science
A generalized Spatio-Temporal Threshold Clustering method for identification of extreme event patterns
Vitaly Kholodovsky and Xin-Zhong Liang
Adv. Stat. Clim. Meteorol. Oceanogr., 7, 35–52, https://doi.org/10.5194/ascmo-7-35-2021,https://doi.org/10.5194/ascmo-7-35-2021, 2021
Short summary
Nonlinear time series models for the North Atlantic Oscillation
Thomas Önskog, Christian L. E. Franzke, and Abdel Hannachi
Adv. Stat. Clim. Meteorol. Oceanogr., 6, 141–157, https://doi.org/10.5194/ascmo-6-141-2020,https://doi.org/10.5194/ascmo-6-141-2020, 2020
Short summary
Comparing forecast systems with multiple correlation decomposition based on partial correlation
Rita Glowienka-Hense, Andreas Hense, Sebastian Brune, and Johanna Baehr
Adv. Stat. Clim. Meteorol. Oceanogr., 6, 103–113, https://doi.org/10.5194/ascmo-6-103-2020,https://doi.org/10.5194/ascmo-6-103-2020, 2020
Short summary
Postprocessing ensemble forecasts of vertical temperature profiles
David Schoenach, Thorsten Simon, and Georg Johann Mayr
Adv. Stat. Clim. Meteorol. Oceanogr., 6, 45–60, https://doi.org/10.5194/ascmo-6-45-2020,https://doi.org/10.5194/ascmo-6-45-2020, 2020
Short summary
Using wavelets to verify the scale structure of precipitation forecasts
Sebastian Buschow and Petra Friederichs
Adv. Stat. Clim. Meteorol. Oceanogr., 6, 13–30, https://doi.org/10.5194/ascmo-6-13-2020,https://doi.org/10.5194/ascmo-6-13-2020, 2020
Short summary

Cited articles

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., and Ghemawat, S.: TensorFlow: Large-scale machine learning on heterogeneous systems, available at: https://www.tensorflow.org/ (last access: April 2019), 2015. 
American Meteorological Society Glossary of Meteorology: Front, available at: http://glossary.ametsoc.org/wiki/Fronts, last access: 27 March 2019. 
Biard, J. C.: Coded Surface Bulletin (JSON format), Zenodo, https://doi.org/10.5281/zenodo.2646544, 2019a. 
Biard, J. C.: Coded Surface Bulletin (netCDF format), Zenodo, https://doi.org/10.5281/zenodo.2651361, 2019b. 
Biard, J. C. and Kunkel, K. E.: DL-FRONT MERRA-2 weather front probability maps over North America, Zenodo, https://doi.org/10.5281/zenodo.2641072, 2019a. 
Download
Short summary
A deep learning convolutional neural network (DL-FRONT) was around 90 % successful in determining the locations of weather fronts over North America when compared against front locations determined manually by forecasters. DL-FRONT detects fronts using maps of air pressure, temperature, humidity, and wind from historical observations or climate models. DL-FRONT makes it possible to do science that was previously impractical because manual front identification would take too much time.