Abstract
The ozone concentration at ground level is a pivotal indicator of air quality, as elevated ozone levels can lead to adverse effects on the environment. In this study various machine learning models for ground-level ozone forecasting are optimised using a Bayesian technique. Predictions are obtained 24 h in advance using historical ozone data and related environmental variables, including meteorological measurements and other air quality indicators. The results indicated that the Extra Trees model emerges as the optimal solution, showcasing competitive performance alongside reasonable training times. Furthermore, an explainable artificial intelligence technique is applied to enhance the interpretability of model predictions, providing insights into the contribution of input features to the predictions computed by the model. The features identified as important, namely \(PM_{10}\), air temperature and \(CO_2\) concentration, are validated as key factors in the literature to forecast ground-level ozone concentration.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hashim, B.M., Al-Naseri, S.K., Al-Maliki, A., Al-Ansari, N.: Impact of COVID-19 lockdown on NO2, O3, PM2.5 and PM10 concentrations and assessing air quality changes in Baghdad, Iraq. Sci. Total Environ. 754, 141978 (2021)
Yafouz, A., Ahmed, A.N., Zaini, N.A., El-Shafie, A.: \(O_3\) concentration forecasting based on artificial intelligence techniques: a systematic review. Water Air Soil Pollut. 232, 1–29 (2021)
Fan, K., Dhammapala, R., Harrington, K., Lamastro, R., Lamb, B., Lee, Y.: Development of a machine learning approach for local-scale \(O_3\) forecasting: application to Kennewick, WA. Front. Big Data 5, 781309 (2022)
Damon, J., Guillas, S.: The inclusion of exogenous variables in functional autoregressive \(O_3\) forecasting. Environmetrics 13(7), 759–774 (2002)
Gradišar, D., Grašič, B., Božnar, M.Z., Mlakar, P., Kocijan, J.: Improving of local ozone forecasting by integrated models. Environ. Sci. Pollut. Res. 23, 18439–18450 (2016)
Cobourn, W.G., Dolcine, L., French, M., Hubbard, M.C.: A comparison of nonlinear regression and neural network models for ground-level \(O_3\) forecasting. J. Air Waste Manag. Assoc. 50(11), 1999–2009 (2000)
Oliveira Santos, V., Costa Rocha, P.A., Scott, J., Van Griensven Thé, J., Gharabaghi, B.: Spatiotemporal air pollution forecasting in houston-TX: a case study for \(O_3\) using deep graph neural networks. Atmosphere 14(2), 308 (2023)
Sun, H., et al.: Improvement of PM\(_{2.5}\) and \(O_3\) forecasting by integration of 3D numerical simulation with deep learning techniques. Sustain. Cities Soc. 75, 103372 (2021)
Palaniyappan Velumani, R., Xia, M., Han, J., Wang, C., Lau, A.K., Qu, H.: AQX: explaining air quality forecast for verifying domain knowledge using feature importance visualization. In: 27th International Conference on Intelligent User Interfaces, pp. 720–733 (2022)
Troncoso-García, A.R., Brito, I.S., Troncoso, A., Martínez-Álvarez, F.: Explainable hybrid deep learning and Coronavirus Optimization Algorithm for improving evapotranspiration forecasting. Comput. Electron. Agric. 215, 108387 (2023)
Troncoso-García, A.R., Troncoso, A., Martínez-Ballesteros, M., Martínez-Álvarez, F.: Evolutionary computation to explain deep learning models for time series forecasting. In: Proceedings of the ACM/SIGAPP Symposium on Applied Computing, pp. 433–436 (2023)
Martínez-Ballesteros, M., Troncoso, A., Martínez-Álvarez, F., Riquelme, J.C.: Improving a multi-objective evolutionary algorithm to discover quantitative association rules. Knowl. Inf. Syst. 49, 481–509 (2016)
Troncoso-García, A.R., Martínez-Ballesteros, M., Martínez-Álvarez, F., Troncoso, A.: A new approach based on association rules to add explainability to time series forecasting models. Inf. Fusion 94, 169–180 (2023)
Gómez-Losada, A., Asencio-Cortés, G., Martínez-Álvarez, F., Riquelme, J.C.: A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information. Environ. Model. Softw. 110, 52–61 (2018)
Anav, A., et al.: Legislative and functional aspects of different metrics used for \(O_3\) risk assessment to forests. Environ. Pollut. 295, 118690 (2022)
Acknowledgements
The authors would like to thank the Spanish Ministry of Science and Innovation for the support within the projects PID2020-117954RB-C21 and TED2021-131311B-C22.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Troncoso-García, A.R., Jiménez-Navarro, M.J., Martínez-Álvarez, F., Troncoso, A. (2024). Ground-Level Ozone Forecasting Using Explainable Machine Learning. In: Alonso-Betanzos, A., et al. Advances in Artificial Intelligence. CAEPIA 2024. Lecture Notes in Computer Science(), vol 14640. Springer, Cham. https://doi.org/10.1007/978-3-031-62799-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-62799-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-62798-9
Online ISBN: 978-3-031-62799-6
eBook Packages: Computer ScienceComputer Science (R0)