Machine-Learning Models for Surface Ozone Forecast in Mexico City
Abstract
1. Introduction
2. Study Area and Data Description
3. Methodology
Algorithm 1 Data preprocessing; models training, evaluation, and upgradation | |
1. | Put the data of all the predictors in matrix X with the number of columns equal to the number of variables and the number of rows equal to the number of hours |
2. | Analyze matrix X day-wise (24 rows at a time) and discard any day with more than twelve missing values of any variable |
3. | Impute missing values in X by KNN imputer (setting number of neighbors as 15, weights as uniform, and metric as nan Euclidean) |
4. | Standardize each variable in the training data using Equation (1), and then, using the same mean and standard deviation, standardize each variable in the test data |
5. | Construct and from the training data with the following assumptions:#break#(i) is a stack of 2D arrays (each 2D array contains one-day data of the predictors, and the number of such arrays is one less than the number of days in the training dataset)#break#(ii) is a 2D array (each column in contains one-day ozone, and the contains day ozone, and and 2D arrays are the same in number) |
6. | Train machine-learning models in regression mode to learn a function that maps 2D array of to column of |
7. | Construct and for the first month of test data by applying the instructions given in step 5 |
8. | Feed to the trained models to get (first month ozone forecast), and calculate the accuracy of the trained models by applying accuracy metrics to the flattened and |
9. | Construct and for the () month test data applying instructions given is step 5, and train the models again on augmented training data containing month(s) more data |
10. | Feed to the trained models to get (th () month ozone forecast), and calculate the accuracy of the trained models by applying accuracy metrics to the flattened and |
3.1. Machine-Learning Models
3.1.1. Feedforward Neural Network (FNN)
3.1.2. Convolutional Neural Network (CNN)
3.1.3. Long Short-Term Memory (LSTM)
3.2. Performance Metrics
4. Results and Discussion
4.1. Local Scenario
4.2. Reginal Scenario
5. Conclusions and Recommendations
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Kim, S.-Y.; Kim, E.; Kim, W.J. Health Effects of Ozone on Respiratory Diseases. Tuberc. Respir. Dis. 2020, 83 (Suppl. S1), S6–S11. [Google Scholar] [CrossRef]
- Mills, G.; Buse, A.; Gimeno, B.; Bermejo, V.; Holland, M.; Emberson, L.; Pleijel, H. A synthesis of AOT40-based response functions and critical levels of ozone for agricultural and horticultural crops. Atmos. Environ. 2007, 41, 2630–2643. [Google Scholar] [CrossRef]
- Bell, M.L.; Peng, R.D.; Dominici, F. The exposure–response curve for ozone and risk of mortality and the adequacy of current ozone regulations. Environ. Health Perspect. 2006, 114, 532–536. [Google Scholar] [CrossRef]
- Holm, S.M.; Balmes, J.R. Systematic Review of Ozone Effects on Human Lung Function, 2013 Through 2020. Chest 2022, 161, 190–201. [Google Scholar] [CrossRef]
- Guan, Y.; Xiao, Y.; Wang, F.; Qiu, X.; Zhang, N. Health impacts attributable to ambient PM2.5 and ozone pollution in major Chinese cities at seasonal-level. J. Clean. Prod. 2021, 311, 127510. [Google Scholar] [CrossRef]
- Nuvolone, D.; Petri, D.; Voller, F. The effects of ozone on human health. Environ. Sci. Pollut. Res. 2017, 25, 8074–8088. [Google Scholar] [CrossRef]
- Atkinson, R. Atmospheric chemistry of VOCs and NOx. Atmos. Environ. 2000, 34, 2063–2101. [Google Scholar] [CrossRef]
- Jenkin, M.E.; Clemitshaw, K.C. Ozone and other secondary photochemical pollutants: Chemical processes governing their formation in the planetary boundary layer. Atmos. Environ. 2000, 34, 2499–2527. [Google Scholar] [CrossRef]
- Comrie, A.C.; Yarnal, B. Relationships between synoptic-scale atmospheric circulation and ozone concentrations in metropolitan Pittsburgh, Pennsylvania. Atmos. Environ. Part B Urban Atmos. 1992, 26, 301–312. [Google Scholar] [CrossRef]
- Davies, T.D.; Kelly, P.M.; Low, P.S.; Pierce, C.E. Surface ozone concentrations in Europe: Links with the regional-scale atmospheric circulation. J. Geophys. Res. Atmos. 1992, 97, 9819–9832. [Google Scholar] [CrossRef]
- Rappenglück, B.; Kourtidis, K.; Fabian, P. Measurements of ozone and peroxyacetyl nitrate (PAN) in Munich. Atmos. Environ. Part B Urban Atmos. 1993, 27, 293–305. [Google Scholar] [CrossRef]
- Dueñas, C.; Fernández, M.C.; Cañete, S.; Carretero, J.; Liger, E. Assessment of ozone variations and meteorological effects in an urban area in the Mediterranean Coast. Sci. Total Environ. 2002, 299, 97–113. [Google Scholar] [CrossRef]
- Elminir, H.K. Dependence of urban air pollutants on meteorology. Sci. Total Environ. 2005, 350, 225–237. [Google Scholar] [CrossRef]
- Solomon, P.; Cowling, E.; Hidy, G.; Furiness, C. Comparison of scientific findings from major ozone field studies in North America and Europe. Atmos. Environ. 2000, 34, 1885–1920. [Google Scholar] [CrossRef]
- Zhang, J.; Rao, S.T.; Daggupaty, S.M. Meteorological processes and ozone exceedances in the northeastern United States during the 12–16 July 1995 episode. J. Appl. Meteorol. 1998, 37, 776–789. [Google Scholar] [CrossRef]
- Alam, M.J.; Rappenglueck, B.; Retama, A.; Rivera-Hernández, O. Investigating the Complexities of VOC Sources in Mexico City in the Years 2016–2022. Atmosphere 2024, 15, 179. [Google Scholar] [CrossRef]
- Osibanjo, O.O.; Rappenglück, B.; Retama, A. Anatomy of the March 2016 severe ozone smog episode in Mexico-City. Atmos. Environ. 2021, 244, 117945. [Google Scholar] [CrossRef]
- Ahmad, M.; Rappenglück, B.; Osibanjo, O.O.; Retama, A. A machine learning approach to investigate the build-up of surface ozone in Mexico-City. J. Clean. Prod. 2022, 379, 134638. [Google Scholar] [CrossRef]
- Akther, T.; Rappenglueck, B.; Osibanjo, O.; Retama, A.; Rivera-Hernández, O. Ozone precursors and boundary layer meteorology before and during a severe ozone episode in Mexico City. Chemosphere 2023, 318, 137978. [Google Scholar] [CrossRef]
- Zielesny, A. From Curve Fitting to Machine Learning. In Intelligent Systems Reference Library; Springer International: Cham, Switzerland, 2016. [Google Scholar] [CrossRef]
- Bekesiene, S.; Meidute-Kavaliauskiene, I.; Vasiliauskiene, V. Accurate prediction of concentration changes in ozone as an air pollutant by multiple linear regression and artificial neural networks. Mathematics 2021, 9, 356. [Google Scholar] [CrossRef]
- Maleki, H.; Sorooshian, A.; Goudarzi, G.; Baboli, Z.; Tahmasebi Birgani, Y.; Rahmati, M. Air pollution prediction by using an artificial neural network model. Clean Technol. Environ. Policy 2019, 21, 1341–1352. [Google Scholar] [CrossRef]
- Du, J.; Qiao, F.; Lu, P.; Yu, L. Forecasting ground-level ozone concentration levels using machine learning. Resour. Conserv. Recycl. 2022, 184, 106380. [Google Scholar] [CrossRef]
- Pan, Q.; Harrou, F.; Sun, Y. A comparison of machine learning methods for ozone pollution prediction. J. Big Data 2023, 10, 63. [Google Scholar] [CrossRef]
- Ghahremanloo, M.; Lops, Y.; Choi, Y.; Yeganeh, B. Deep Learning Estimation of Daily Ground-Level NO2 Concentrations From Remote Sensing Data. J. Geophys. Res. Atmos. 2021, 126, e2021JD034925. [Google Scholar] [CrossRef]
- Baghoolizadeh, M.; Rostamzadeh-Renani, M.; Dehkordi, S.A.H.H.; Rostamzadeh-Renani, R.; Toghraie, D. A prediction model for CO2 concentration and multi-objective optimization of CO2 concentration and annual electricity consumption cost in residential buildings using ANN and GA. J. Clean. Prod. 2022, 379, 134753. [Google Scholar] [CrossRef]
- Cheng, Y.; Zhu, Q.; Peng, Y.; Huang, X.-F.; He, L.-Y. Multiple strategies for a novel hybrid forecasting algorithm of ozone based on data-driven models. J. Clean. Prod. 2021, 326, 129451. [Google Scholar] [CrossRef]
- Gagliardi, R.V.; Andenna, C. A machine learning approach to investigate the surface ozone behavior. Atmosphere 2020, 11, 1173. [Google Scholar] [CrossRef]
- Eslami, E.; Choi, Y.; Lops, Y.; Sayeed, A. A real-time hourly ozone prediction system using deep convolutional neural network. Neural Comput. Appl. 2019, 32, 8783–8797. [Google Scholar] [CrossRef]
- Sayeed, A.; Choi, Y.; Eslami, E.; Lops, Y.; Roy, A.; Jung, J. Using a deep convolutional neural network to predict 2017 ozone concentrations, 24 hours in advance. Neural Netw. 2020, 121, 396–408. [Google Scholar] [CrossRef]
- Kleinert, F.; Leufen, L.H.; Schultz, M.G. IntelliO3-ts v1.0: A neural network approach to predict near-surface ozone concentrations in Germany. Geosci. Model Dev. 2021, 14, 1–25. [Google Scholar] [CrossRef]
- Yafouz, A.; Ahmed, A.N.; Zaini, N.A.; Sherif, M.; Sefelnasr, A.; El-Shafie, A. Hybrid deep learning model for ozone concentration prediction: Comprehensive evaluation and comparison with various machine and deep learning algorithms. Eng. Appl. Comput. Fluid Mech. 2021, 15, 902–933. [Google Scholar] [CrossRef]
- Aljanabi, M.; Shkoukani, M.; Hijjawi, M. Ground-level Ozone Prediction Using Machine Learning Techniques: A Case Study in Amman, Jordan. Int. J. Autom. Comput. 2020, 17, 667–677. [Google Scholar] [CrossRef]
- Liang, Y.C.; Maimury, Y.; Chen, A.H.L.; Juarez, J.R.C. Machine learning-based prediction of air quality. Appl. Sci. 2020, 10, 9151. [Google Scholar] [CrossRef]
- Wang, H.W.; Li, X.B.; Wang, D.; Zhao, J.; Peng, Z.R. Regional prediction of ground-level ozone using a hybrid sequence-to-sequence deep learning approach. J. Clean. Prod. 2020, 253, 119841. [Google Scholar] [CrossRef]
- Abirami, S.; Chitra, P. Regional air quality forecasting using spatiotemporal deep learning. J. Clean. Prod. 2021, 283, 125341. [Google Scholar] [CrossRef]
- Deng, T.; Manders, A.; Segers, A.; Bai, Y.; Lin, H. Temporal Transfer Learning for Ozone Prediction based on CNN-LSTM Model. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence, Vienna, Austria, 4–6 February 2021. [Google Scholar] [CrossRef]
- Juarez, E.K.; Petersen, M.R. A comparison of machine learning methods to forecast tropospheric ozone levels in Delhi. Atmosphere 2021, 13, 46. [Google Scholar] [CrossRef]
- Makarova, A.; Evstaf’eva, E.; Lapchenco, V.; Varbanov, P.S. Modelling tropospheric ozone variations using artificial neural networks: A case study on the Black Sea coast (Russian Federation). Clean. Eng. Technol. 2021, 5, 100293. [Google Scholar] [CrossRef]
- Yan, R.; Liao, J.; Yang, J.; Sun, W.; Nong, M.; Li, F. Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering. Expert Syst. Appl. 2021, 169, 114513. [Google Scholar] [CrossRef]
- Balamurugan, V.; Balamurugan, V.; Chen, J. Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm. Sci. Rep. 2022, 12, 5646. [Google Scholar] [CrossRef]
- Chen, B.; Wang, Y.; Huang, J.; Zhao, L.; Chen, R.; Song, Z.; Hu, J. Estimation of Near-Surface Ozone Concentration and Analysis of Main Weather Situation in China Based on Machine Learning Model and Himawari-8 Toar Data. SSRN Electron. J. 2022, 864, 160928. [Google Scholar] [CrossRef]
- Hafeez, A.; Taqvi, S.A.A.; Fazal, T.; Javed, F.; Khan, Z.; Amjad, U.S.; Rehman, F. Optimization on cleaner intensification of ozone production using Artificial Neural Network and Response Surface Methodology: Parametric and comparative study. J. Clean. Prod. 2020, 252, 119833. [Google Scholar] [CrossRef]
- Weng, X.; Forster, G.L.; Nowack, P. A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019. Atmos. Chem. Phys. 2022, 22, 8385–8402. [Google Scholar] [CrossRef]
- Zhan, J.; Liu, Y.; Ma, W.; Zhang, X.; Wang, X.; Bi, F.; Li, H. Ozone formation sensitivity study using machine learning coupled with the reactivity of volatile organic compound species. Atmos. Meas. Tech. 2022, 15, 1511–1520. [Google Scholar] [CrossRef]
- Zhang, J.; Li, S. Air quality index forecast in Beijing based on CNN-LSTM multi-model. Chemosphere 2022, 308, 136180. [Google Scholar] [CrossRef]
- Leufen, L.H.; Kleinert, F.; Schultz, M.G. O3ResNet: A Deep Learning–Based Forecast System to Predict Local Ground-Level Daily Maximum 8-Hour Average Ozone in Rural and Suburban Environments. Artif. Intell. Earth Syst. 2023, 2, e220085. [Google Scholar] [CrossRef]
- Méndez, M.; Merayo, M.G.; Núñez, M. Machine learning algorithms to forecast air quality: A survey. Artif. Intell. Rev. 2023, 56, 10031–10066. [Google Scholar] [CrossRef]
- Hosseinpour, F.; Kumar, N.; Tran, T.; Knipping, E. Using machine learning to improve the estimate of, U.S. background ozone. Atmos. Environ. 2024, 316, 120145. [Google Scholar] [CrossRef]
- Luo, Z.; Lu, P.; Chen, Z.; Liu, R. Ozone Concentration Estimation and Meteorological Impact Quantification in the Beijing-Tianjin-Hebei Region Based on Machine Learning Models. Earth Space Sci. 2024, 11. [Google Scholar] [CrossRef]
- Yan, X.; Guo, Y.; Zhang, Y.; Chen, J.; Jiang, Y.; Zuo, C.; Zhao, W.; Shi, W. Combining physical mechanisms and deep learning models for hourly surface ozone retrieval in China. J. Environ. Manag. 2024, 351, 119942. [Google Scholar] [CrossRef] [PubMed]
- Emmanuel, T.; Maupong, T.; Mpoeleng, D.; Semong, T.; Banyatsang, M.; Tabona, O. A Survey On Missing Data in Machine Learning. J. Big Data 2021, 8, 140. [Google Scholar] [CrossRef]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Akther, T.; Rappenglueck, B.; Karim, I.; Nelson, B.; Mayhew, A.W.; Retama, A.; Rivera-Hernández, O. Box-Modelling of O3 and its sensitivity towards VOCs and NOx in Mexico City under altered emission conditions. Environ. Sci. Technol. 2024. submitted. [Google Scholar]
Author(s) | Study | Model(s) Applied | Study Area |
---|---|---|---|
[33] | O3 prediction | MLP, SVR, DTR, XGBoost | Amman, Jordan |
[34] | Air quality index prediction | RF, SVM, ANN | Zhongli, Fengshan, Changhua, Taiwan |
[35] | Regional prediction of ground-level O3 | Hybrid sequence-to-sequence deep learning approach | Beijing, China |
[36] | Air quality forecast (O3, PM10, PM2.5, SO2, NO2, CO, NH3, pb) | Hierarchical deep learning model | Delhi, India |
[37] | O3 prediction with temporal transfer learning | CNN-LSTM | Eisenhüttenstadt, Germany |
[38] | O3 concentrations prediction 1 to 24 h in the future | KNN, SVM, RF, LSTM, XGBoost, MLR, DT | Delhi, India |
[39] | Hourly O3 concentrations prediction | ANNs | Southern parts of Russia |
[40] | Multi-hour and multi-site air quality index forecasting | CNN, LSTM, CNN-LSTM | Beijing, China |
[41] | Urban O3 variability modeling | XGBoost | Munich, Germany |
[42] | Estimation of O3 concentrations | Deep forest | China |
[43] | Investigation of interacting effects of experimental parameters on O3 generation | ANN | - |
[44] | O3 pollution drivers Quantification | RFR, RR, MLR | China |
[45] | O3 formation sensitivity analysis | RF model | Beijing, China |
[46] | Air quality index forecast | CNN-LSTM | Beijing, China |
[47] | Local daily maximum 8-h average O3 prediction | CNN with residual blocks | Central Europe |
[48] | Machine-learning algorithms to forecast air quality: a survey | SVM, DT, RF, KNN, CNN, LSTM, GRU, EDNN | China, India, USA, Mexico, Australia, New Zealand |
[49] | Background O3 estimate improvement | MLR, RF | USA |
[50] | O3 concentrations estimation | RF, XGB, MLP, SVR, PR | Beijing–Tianjin–Hebei, China |
[51] | Hourly O3 retrieval | MLR and feedforward neural network | China |
Predictor | Available at | Abbreviation | Units | Resolution |
---|---|---|---|---|
Near-surface ozone | 14 stations | O3 | ppb | Hourly |
Nitrogen dioxide | 14 stations | NO2 | ppb | Hourly |
Nitric oxide | 14 stations | NO | ppb | Hourly |
Temperature | 14 stations | TEMP | °C | Hourly |
Relative humidity | 14 stations | RH | % | Hourly |
Surface wind speed | 14 stations | WS | m/s | Hourly |
Wind direction | 14 stations | WD | Degree | Hourly |
Ultraviolet A radiation | 04 stations | UV-A | W/m2 | Hourly |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ahmad, M.; Rappenglück, B.; Osibanjo, O.O.; Retama, A. Machine-Learning Models for Surface Ozone Forecast in Mexico City. Atmosphere 2025, 16, 931. https://doi.org/10.3390/atmos16080931
Ahmad M, Rappenglück B, Osibanjo OO, Retama A. Machine-Learning Models for Surface Ozone Forecast in Mexico City. Atmosphere. 2025; 16(8):931. https://doi.org/10.3390/atmos16080931
Chicago/Turabian StyleAhmad, Mateen, Bernhard Rappenglück, Olabosipo O. Osibanjo, and Armando Retama. 2025. "Machine-Learning Models for Surface Ozone Forecast in Mexico City" Atmosphere 16, no. 8: 931. https://doi.org/10.3390/atmos16080931
APA StyleAhmad, M., Rappenglück, B., Osibanjo, O. O., & Retama, A. (2025). Machine-Learning Models for Surface Ozone Forecast in Mexico City. Atmosphere, 16(8), 931. https://doi.org/10.3390/atmos16080931