Articles | Volume 20, issue 13
Research article
13 Jul 2020
Research article |  | 13 Jul 2020

Improving the prediction of an atmospheric chemistry transport model using gradient-boosted regression trees

Peter D. Ivatt and Mathew J. Evans

Data sets

ATom: Merged Atmospheric Chemistry, Trace Gases, and Aerosols S. C. Wofsy, S. Afshar, H. M. Allen, E. C. Apel, E. C. Asher, B. Barletta, J. Bent, H. Bian, B. C. Biggs, D. R. Blake, N. Blake, I. Bourgeois, C. A. Brock, W. H. Brune, J. W. Budney, T. P. Bui, A. Butler, P. Campuzano-Jost, C. S. Chang, M. Chin, R. Commane, G. Correa, J. D. Crounse, P. D. Cullis, B. C. Daube, D. A. Day, J. M. Dean-Day, J. E. Dibb, J. P. DiGangi, G. S. Diskin, M. Dollner, J. W. Elkins, F. Erdesz, A. M. Fiore, C. M. Flynn, K. D. Froyd, D. W. Gesler, S. R. Hall, T. F. Hanisco, R. A. Hannun, A. J. Hills, E. J. Hintsa, A. Hoffman, R. S. Hornbrook, L. G. Huey, S. Hughes, J. L. Jimenez, B. J. Johnson, J. M. Katich, R. F. Keeling, M. J. Kim, A. Kupc, L. R. Lait, J.-F. Lamarque, J. Liu, K. McKain, R. J. Mclaughlin, S. Meinardi, D. O. Miller, S. A. Montzka, F. L. Moore, E. J. Morgan, D. M. Murphy, L. T. Murray, B. A. Nault, J. A. Neuman, P. A. Newman, J. M. Nicely, X. Pan, W. Paplawsky, J. Peischl, M. J. Prather, D. J. Price, E. Ray, J. M. Reeves, M. Richardson, A. W. Rollins, K. H. Rosenlof, T. B. Ryerson, E. Scheuer, G. P. Schill, J. C. Schroder, J. P. Schwarz, J. M. St. Clair, S. D. Steenrod, B. B. Stephens, S. A. Strode, C. Sweeney, D. Tanner, A. P. Teng, A. B. Thames, C. R. Thompson, K. Ullmann, P. R. Veres, N. Vieznor, N. L. Wagner, A. Watt, R. Weber, B. Weinzierl, P. O. Wennberg, C. J. Williamson, J. C. Wilson, G. M. Wolfe, C. T. Woods, and L. H. Zeng

Air Quality System Data Mart US Environmental Protection Agency

World Meteorological Organization-Global Atmosphere Watch Program (WMO-GAW) JMA and NASA-WFF

XGBoost: A Scalable Tree Boosting System T. Chen and C. Guestrin

Short summary
We investigate the potential of using a decision tree algorithm to identify and correct the tropospheric ozone bias in a chemical transport model. We train the algorithm on 2010–2015 ground and column observation data and test the algorithm on the 2016–2017 data using the ground data as well as independent flight data. We find the algorithm is successfully able to identify and correct the bias, improving the model performance.
Final-revised paper