Exploring decomposition of temporal patterns to facilitate learning of neural networks for ground-level daily maximum 8-hour average ozone prediction

Exposure to ground-level ozone is a concern for both humans and vegetation, so accurate prediction of ozone time series is of great importance. However, conventional as well as emerging methods have deficiencies in predicting time series when a superposition of differently pronounced oscillations on various time scales is present. In this paper, we propose a meteorologically motivated filtering method of time series data, which can separate oscillation patterns, in combination with different multibranch neural networks. To avoid phase shifts introduced by using a causal filter, we combine past observation data with a climatological estimate about the future to be able to apply a noncausal filter in a forecast setting. In addition, the forecast in the form of the expected climatology provides some a priori information that can support the neural network to focus not merely on learning a climatological statistic. We apply this method to hourly data obtained from over 50 different monitoring stations in northern Germany situated in rural or suburban surroundings to generate a prediction for the daily maximum 8-hr average values of ground-level ozone 4 days into the future. The data preprocessing with time filters enables simpler neural networks such as fully connected networks as well as more sophisticated approaches such as convolutional and recurrent neural networks to better recognize long-term and short-term oscillation patterns like the seasonal cycle and thus leads to an improvement in the forecast skill, especially for a lead time of more than 48 hr, compared to persistence, climatological reference, and other reference models. Impact Statement Exposure to ground-level ozone harms humans and vegetation, but the prediction of ozone time series, especially by machine learning, encounters problems due to the superposition of different oscillation patterns from long-term to short-term scales. Decomposing the input time series into long-term and short-term signals with the help of climatology and statistical filtering techniques can improve the prediction of various neural network architectures due to an improved recognition of different temporal patterns. More reliable and accurate forecasts support decision-makers and individuals in taking timely and necessary countermeasures to air pollution episodes.