A hybrid model for predicting air quality combining Holt–Winters and Deep Learning Approaches: A novel method to identify ozone concentration peaks

Abstract

Ozone (O3) from the troposphere is one of the substances that has a strong effect on air pollution in the city of Tanger. Prediction of this pollutant can have positive improvements in air quality. This paper presents a new approach combining deep-learning algorithms and the Holt–Winters method in order to detect pollutant peaks and obtain a more accurate forecasting model. Given that LSTM is an extremely powerful algorithm, we hybridized with the Holt–Winters method to enhance the model. Making use of multiple accuracy metrics, the models' efficiency is investigated. Empirical findings reveal the superiority of the hybrid model by providing forecasts that are more accurate with an index of agreement equal to 0.91.