IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany

• Published in: Geoscientific Model Development Vol. 14; no. 1; pp. 1 - 25
• Main Authors: Kleinert, Felix, Leufen, Lukas H, Schultz, Martin G
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 04.01.2021; Copernicus Publications
• Subjects: Advection; Air exposure; Air pollution; Analysis; Application programming interface; Artificial neural networks; Cable television broadcasting industry; Chemical reactions; Climate models; Deep learning; Emission measurements; Environmental aspects; Feature selection; Humidity; Lead time; Machine learning; Neural networks; Nitrogen; Nitrogen oxide; Nitrogen oxides; Outdoor air quality; Ozone; Photochemicals; Pollutants; Predictions; Railway stations; Rural environments; Time series; Training; Trends; Variables; Weather; Wind; United States; Germany
• ISSN: 1991-9603; 1991-959X; 1991-962X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-14-1-2021

The prediction of near-surface ozone concentrations is important for supporting regulatory procedures for the protection of humans from high exposure to air pollution. In this study, we introduce a data-driven forecasting model named “IntelliO3-ts”, which consists of multiple convolutional neural network (CNN) layers, grouped together as inception blocks. The model is trained with measured multi-year ozone and nitrogen oxide concentrations of more than 300 German measurement stations in rural environments and six meteorological variables from the meteorological COSMO reanalysis. This is by far the most extensive dataset used for time series predictions based on neural networks so far. IntelliO3-ts allows the prediction of daily maximum 8 h average (dma8eu) ozone concentrations for a lead time of up to 4 d, and we show that the model outperforms standard reference models like persistence models. Moreover, we demonstrate that IntelliO3-ts outperforms climatological reference models for the first 2 d, while it does not add any genuine value for longer lead times. We attribute this to the limited deterministic information that is contained in the single-station time series training data. We applied a bootstrapping technique to analyse the influence of different input variables and found that the previous-day ozone concentrations are of major importance, followed by 2 m temperature. As we did not use any geographic information to train IntelliO3-ts in its current version and included no relation between stations, the influence of the horizontal wind components on the model performance is minimal. We expect that the inclusion of advection–diffusion terms in the model could improve results in future versions of our model.