A Deep Learning Parameterization for Ozone Dry Deposition Velocities

Show full item record




Silva , S J , Heald , C L , Ravela , S , Mammarella , I & Munger , J W 2019 , ' A Deep Learning Parameterization for Ozone Dry Deposition Velocities ' , Geophysical Research Letters , vol. 46 , no. 2 , pp. 983-989 . https://doi.org/10.1029/2018GL081049

Title: A Deep Learning Parameterization for Ozone Dry Deposition Velocities
Author: Silva, S. J.; Heald, C. L.; Ravela, S.; Mammarella, I.; Munger, J. William
Contributor organization: INAR Physics
Micrometeorology and biogeochemical cycles
Institute for Atmospheric and Earth System Research (INAR)
Date: 2019-01-28
Language: eng
Number of pages: 7
Belongs to series: Geophysical Research Letters
ISSN: 0094-8276
DOI: https://doi.org/10.1029/2018GL081049
URI: http://hdl.handle.net/10138/303307
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 (Hyytiala, 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 similar to 0.1). The same DNN model, when driven by assimilated meteorology at 2 degrees x 2.5 degrees 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. Plain Language Summary Ozone in the lower atmosphere is a toxic pollutant and greenhouse gas. In this work, we use a machine learning technique known as deep learning, to simulate the loss of ozone to Earth's surface. We show that our deep learning simulation of this loss process outperforms existing traditional models and demonstrate the opportunity for using machine learning to improve our understanding of the chemical composition of the atmosphere.
Subject: 114 Physical sciences
1171 Geosciences
Peer reviewed: Yes
Rights: unspecified
Usage restriction: openAccess
Self-archived version: acceptedVersion

Files in this item

Total number of downloads: Loading...

Files Size Format View
Silva_et_al_2018_Geophysical_Research_Letters.pdf 941.1Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record