Multi-Step Ahead Ex-Ante Forecasting of Air Pollutants Using Machine Learning

Snezhana Gocheva-Ilieva (), Atanas Ivanov, Hristina Kulina and Maya Stoimenova-Minova
Additional contact information
Snezhana Gocheva-Ilieva: Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria
Atanas Ivanov: Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria
Hristina Kulina: Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria
Maya Stoimenova-Minova: Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria

Mathematics, 2023, vol. 11, issue 7, 1-26

Abstract: In this study, a novel general multi-step ahead strategy is developed for forecasting time series of air pollutants. The values of the predictors at future moments are gathered from official weather forecast sites as independent ex-ante data. They are updated with new forecasted values every day. Each new sample is used to build- a separate single model that simultaneously predicts future pollution levels. The sought forecasts were estimated by averaging the actual predictions of the single models. The strategy was applied to three pollutants—PM 10 , SO 2 , and NO 2 —in the city of Pernik, Bulgaria. Random forest (RF) and arcing (Arc-x4) machine learning algorithms were applied to the modeling. Although there are many highly changing day-to-day predictors, the proposed averaging strategy shows a promising alternative to single models. In most cases, the root mean squared errors (RMSE) of the averaging models (aRF and aAR) for the last 10 horizons are lower than those of the single models. In particular, for PM 10 , the aRF’s RMSE is 13.1 vs. 13.8 micrograms per cubic meter for the single model; for the NO 2 model, the aRF exhibits 21.5 vs. 23.8; for SO 2, the aAR has 17.3 vs. 17.4; for NO 2 , the aAR’s RMSE is 22.7 vs. 27.5, respectively. Fractional bias is within the same limits of (−0.65, 0.7) for all constructed models.

Keywords: air pollution; machine learning; random forest; arcing; ARIMA errors; MIMO averaging strategy; multi-step ahead prediction; unmeasured forecast (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/7/1566/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/7/1566/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:7:p:1566-:d:1105289

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().