A Deep Learning Parameterization for Ozone Dry Deposition Velocities
Abstract
Abstract The loss of ozone to terrestrial and aquatic systems, known as dry deposition, is a highly uncertain process governed by turbulent transport, interfacial chemistry, and plant physiology. We demonstrate the value of using Deep Neural Networks (DNN) in predicting ozone dry deposition velocities. We find that a feedforward DNN trained on observations from a coniferous forest site (Hyytiälä, Finland) can predict hourly ozone dry deposition velocities at a mixed forest site (Harvard Forest, Massachusetts) more accurately than modern theoretical models, with a reduction in the normalized mean bias (0.05 versus ~0.1). The same DNN model, when driven by assimilated meteorology at 2° × 2.5° spatial resolution, outperforms the Wesely scheme as implemented in the GEOS‐Chem model. With more available training data from other climate and ecological zones, this methodology could yield a generalizable DNN suitable for global models.
- Authors:
-
- Department of Civil and Environmental Engineering Massachusetts Institute of Technology Cambridge MA USA
- Earth Signals and Systems Group, Department of Earth, Atmospheric, and Planetary Sciences Massachusetts Institute of Technology Cambridge MA USA
- Institute for Atmospheric and Earth System Research/Physics, Faculty of Science University of Helsinki Helsinki Finland
- School of Engineering and Applied Sciences Harvard University Cambridge MA USA
- Publication Date:
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1491211
- Resource Type:
- Publisher's Accepted Manuscript
- Journal Name:
- Geophysical Research Letters
- Additional Journal Information:
- Journal Name: Geophysical Research Letters Journal Volume: 46 Journal Issue: 2; Journal ID: ISSN 0094-8276
- Publisher:
- American Geophysical Union (AGU)
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Silva, S. J., Heald, C. L., Ravela, S., Mammarella, I., and Munger, J. W. A Deep Learning Parameterization for Ozone Dry Deposition Velocities. United States: N. p., 2019.
Web. doi:10.1029/2018GL081049.
Silva, S. J., Heald, C. L., Ravela, S., Mammarella, I., & Munger, J. W. A Deep Learning Parameterization for Ozone Dry Deposition Velocities. United States. https://doi.org/10.1029/2018GL081049
Silva, S. J., Heald, C. L., Ravela, S., Mammarella, I., and Munger, J. W. Wed .
"A Deep Learning Parameterization for Ozone Dry Deposition Velocities". United States. https://doi.org/10.1029/2018GL081049.
@article{osti_1491211,
title = {A Deep Learning Parameterization for Ozone Dry Deposition Velocities},
author = {Silva, S. J. and Heald, C. L. and Ravela, S. and Mammarella, I. and Munger, J. W.},
abstractNote = {Abstract The loss of ozone to terrestrial and aquatic systems, known as dry deposition, is a highly uncertain process governed by turbulent transport, interfacial chemistry, and plant physiology. We demonstrate the value of using Deep Neural Networks (DNN) in predicting ozone dry deposition velocities. We find that a feedforward DNN trained on observations from a coniferous forest site (Hyytiälä, Finland) can predict hourly ozone dry deposition velocities at a mixed forest site (Harvard Forest, Massachusetts) more accurately than modern theoretical models, with a reduction in the normalized mean bias (0.05 versus ~0.1). The same DNN model, when driven by assimilated meteorology at 2° × 2.5° spatial resolution, outperforms the Wesely scheme as implemented in the GEOS‐Chem model. With more available training data from other climate and ecological zones, this methodology could yield a generalizable DNN suitable for global models.},
doi = {10.1029/2018GL081049},
journal = {Geophysical Research Letters},
number = 2,
volume = 46,
place = {United States},
year = {Wed Jan 16 00:00:00 EST 2019},
month = {Wed Jan 16 00:00:00 EST 2019}
}
https://doi.org/10.1029/2018GL081049
Web of Science
Works referenced in this record:
A new algorithm to design compact two-hidden-layer artificial neural networks
journal, November 2001
- Islam, Md. Monirul; Murase, K.
- Neural Networks, Vol. 14, Issue 9
The Elements of Statistical Learning
book, January 2001
- Hastie, Trevor; Friedman, Jerome; Tibshirani, Robert
- Springer Series in Statistics
Statistical pattern recognition: a review
journal, January 2000
- Jain, A. K.; Duin, P. W.
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Issue 1
Using machine learning to build temperature-based ozone parameterizations for climate sensitivity simulations
journal, October 2018
- Nowack, Peer; Braesicke, Peter; Haigh, Joanna
- Environmental Research Letters, Vol. 13, Issue 10
Atmospheric deposition of reactive nitrogen oxides and ozone in a temperate deciduous forest and a subarctic woodland: 1. Measurements and mechanisms
journal, May 1996
- Munger, J. William; Wofsy, Steven C.; Bakwin, Peter S.
- Journal of Geophysical Research: Atmospheres, Vol. 101, Issue D7
Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: an analysis of data from the Global Burden of Diseases Study 2015
journal, May 2017
- Cohen, Aaron J.; Brauer, Michael; Burnett, Richard
- The Lancet, Vol. 389, Issue 10082
Deep learning to represent subgrid processes in climate models
journal, September 2018
- Rasp, Stephan; Pritchard, Michael S.; Gentine, Pierre
- Proceedings of the National Academy of Sciences, Vol. 115, Issue 39
XGBoost: A Scalable Tree Boosting System
conference, January 2016
- Chen, Tianqi; Guestrin, Carlos
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
Variations of Box Plots
journal, February 1978
- McGill, Robert; Tukey, John W.; Larsen, Wayne A.
- The American Statistician, Vol. 32, Issue 1
Parameterization of surface resistances to gaseous dry deposition in regional-scale numerical models
journal, January 1989
- Wesely, M. L.
- Atmospheric Environment (1967), Vol. 23, Issue 6
Interannual variability in ozone removal by a temperate deciduous forest: INTERANNUAL VARIABILITY IN OZONE REMOVAL
journal, January 2017
- Clifton, O. E.; Fiore, A. M.; Munger, J. W.
- Geophysical Research Letters, Vol. 44, Issue 1
Regularization Paths for Generalized Linear Models via Coordinate Descent
journal, January 2010
- Friedman, Jerome; Hastie, Trevor; Tibshirani, Robert
- Journal of Statistical Software, Vol. 33, Issue 1
The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2)
journal, July 2017
- Gelaro, Ronald; McCarty, Will; Suárez, Max J.
- Journal of Climate, Vol. 30, Issue 14
What controls tropospheric ozone?
journal, February 2000
- Lelieveld, Jos; Dentener, Frank J.
- Journal of Geophysical Research: Atmospheres, Vol. 105, Issue D3
An evaluation of ozone dry deposition in global scale chemistry climate models
journal, January 2015
- Hardacre, C.; Wild, O.; Emberson, L.
- Atmospheric Chemistry and Physics, Vol. 15, Issue 11
PCA-Initialized Deep Neural Networks Applied to Document Image Analysis
conference, November 2017
- Seuret, Mathias; Alberti, Michele; Liwicki, Marcus
- 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
Modelling gaseous dry deposition in AURAMS: a unified regional air-quality modelling system
journal, January 2002
- Zhang, Leiming; Moran, Michael D.; Makar, Paul A.
- Atmospheric Environment, Vol. 36, Issue 3
Evaluation and Intercomparison of Five North American Dry Deposition Algorithms at a Mixed Forest Site
journal, July 2018
- Wu, Zhiyong; Schwede, Donna B.; Vet, Robert
- Journal of Advances in Modeling Earth Systems, Vol. 10, Issue 7
Investigating Dry Deposition of Ozone to Vegetation: Investigating Dry Deposition of Ozone to Vegetation
journal, January 2018
- Silva, Sam J.; Heald, Colette L.
- Journal of Geophysical Research: Atmospheres, Vol. 123, Issue 1
Ozone deposition into a boreal forest over a decade of observations: evaluating deposition partitioning and driving variables
journal, January 2012
- Rannik, Ü.; Altimir, N.; Mammarella, I.
- Atmospheric Chemistry and Physics, Vol. 12, Issue 24
Simulating ozone dry deposition at a boreal forest with a multi-layer canopy deposition model
journal, January 2017
- Zhou, Putian; Ganzeveld, Laurens; Rannik, Üllar
- Atmospheric Chemistry and Physics, Vol. 17, Issue 2
A review of the current status of knowledge on dry deposition
journal, January 2000
- Wesely, M.
- Atmospheric Environment, Vol. 34, Issue 12-14