A Deep Learning Parameterization for Ozone Dry Deposition Velocities

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.