PREDICTION OF CARBON DIOXIDE EMISSIONS FROM MOTOR VEHICLES USING GATED RECURRENT UNITS AND DENSITY-BASED SPATIAL CLUSTERING OF APPLICATIONS WITH NOISE
DOI:
https://doi.org/10.15282/Keywords:
Climate Change, CO2 emissions, Deep learning, DBSCAN, Gated Recurrent UnitsAbstract
Extreme climatic conditions resulting from climate change pose significant challenges to mankind, prompting urgent action across various fronts. With vehicle emissions contributing substantially to carbon dioxide emissions, there is a pressing need for efficient prediction methods for informed mitigation strategies. While some research has been carried out on predicting carbon dioxide using machine learning, there have been few studies that explore Recurrent Neural Networks particularly those that can be modelled with a smaller dataset to improve emissions prediction. The study aimed to improve the prediction of carbon dioxide emissions by employing a new approach. The study was conducted on a Canadian dataset with 7,385 samples featuring motor vehicle parameters. Therefore, this research employs a deep learning model known as Gated Recurrent Units (GRU) for predictive modelling coupled with another algorithm called the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for robust outlier detection and subsequent removal. Other algorithms that were used for preprocessing include label encoding and min-max normalisation. The study was evaluated using four metrics, namely root MSE (RMSE), mean square error (MSE), mean absolute error (MAE) and determination coefficient (R2). Compared with the highest-performing results from prior studies, our approach achieved a 4.59% increase in R² and a 2.14% increase in R, alongside reductions in MSE and RMSE by 0.0008766 and 0.0015804, respectively. Thus, showing superior handling of data irregularities and temporal patterns. These results highlight the potential for improved emissions predictions, which can be instrumental in refining carbon tax calculations and informing environmental policy. Future works will involve expanding the dataset to include the age of the motor vehicle and using hybrid deep learning models.
Downloads
References
[1] H. Jin, “Prediction of direct carbon emissions of Chinese provinces using artificial neural networks,” PLOS ONE, vol. 16, no. 5, Art. no. e0236685, 2021, https://doi.org/10.1371/journal.pone.0236685.
[2] I. H. Shah, M. A. Manzoor, W. Jinhui, et al., “Comprehensive review: Effects of climate change and greenhouse gases emission relevance to environmental stress on horticultural crops and management,” Journal of Environmental Management, vol. 351, Art. no. 119978, 2024, https://doi.org/10.1016/j.jenvman.2023.119978.
[3] T. R. Bajracharya, S. R. Shakya, and A. Sharma, “Climate change and sustainable energy systems,” in Handbook of Energy and Environmental Security. Amsterdam, The Netherlands: Elsevier, 2022, pp. 531–545, https://doi.org/10.1016/B978-0-12-824084-7.24001-0.
[4] A. Goswami, H. S. Kapoor, R. K. Jangir, et al., “Impact of economic growth, trade openness, urbanization and energy consumption on carbon emissions: A study of India,” Sustainability, vol. 15, no. 11, Art. no. 9025, 2023, https://doi.org/10.3390/su15119025.
[5] S. Aminzadegan, M. Shahriari, F. Mehranfar, and B. Abramović, “Factors affecting the emission of pollutants in different types of transportation: A literature review,” Energy Reports, vol. 8, pp. 2508–2529, 2022, https://doi.org/10.1016/j.egyr.2022.01.161.
[6] M. Emami Javanmard, Y. Tang, Z. Wang, and P. Tontiwachwuthikul, “Forecast energy demand, CO₂ emissions and energy resource impacts for the transportation sector,” Applied Energy, vol. 338, Art. no. 120830, 2023, https://doi.org/10.1016/j.apenergy.2023.120830.
[7] V. L. Bartlett, H. Doernberg, M. Mooghali, et al., “Published research on the human health implications of climate change between 2012 and 2021: A cross-sectional study,” BMJ Medicine, vol. 3, no. 1, Art. no. e000627, 2024, https://doi.org/10.1136/bmjmed-2023-000627.
[8] H. Boogaard, A. P. Patton, R. W. Atkinson, et al., “Long-term exposure to traffic-related air pollution and selected health outcomes: A systematic review and meta-analysis,” Environment International, vol. 164, Art. no. 107262, 2022, https://doi.org/10.1016/j.envint.2022.107262.
[9] A. H. Al-Nefaie and T. H. H. Aldhyani, “Predicting CO₂ emissions from traffic vehicles for sustainable and smart environment using a deep learning model,” Sustainability, vol. 15, no. 9, Art. no. 7615, 2023, https://doi.org/10.3390/su15097615.
[10] R. Zhang, Y. Wang, Y. Pang, et al., “A deep learning micro-scale model to estimate the CO₂ emissions from light-duty diesel trucks based on real-world driving,” Atmosphere, vol. 13, no. 9, Art. no. 1466, 2022, https://doi.org/10.3390/atmos13091466.
[11] O. S. Azeez, B. Pradhan, H. Z. M. Shafri, et al., “Modeling of CO emissions from traffic vehicles using artificial neural networks,” Applied Sciences, vol. 9, no. 2, Art. no. 313, 2019, https://doi.org/10.3390/app9020313.
[12] A. S. Chadha, Y. Shinde, N. Sharma, and P. K. De, “Predicting CO₂ emissions by vehicles using machine learning,” in Data Management, Analytics and Innovation. Singapore: Springer, 2023, pp. 197–207, https://doi.org/10.1007/978-981-19-2600-6_14.
[13] S. Shah, S. Thakar, K. Jain, B. Shah, and S. Dhage, “A comparative study of machine learning and deep learning techniques for prediction of CO₂ emission in cars,” 2022, arXiv:2211.08268.
[14] T. Jia, P. Zhang, and B. Chen, “A microscopic model of vehicle CO₂ emissions based on deep learning: A spatiotemporal analysis of taxicabs in Wuhan, China,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 10, pp. 18446–18455, 2022, https://doi.org/10.1109/TITS.2022.3151655.
[15] M. Ghahramani and F. Pilla, “Analysis of carbon dioxide emissions from road transport using taxi trips,” IEEE Access, vol. 9, pp. 98573–98580, 2021, https://doi.org/10.1109/ACCESS.2021.3096279.
[16] N. D. Rivera-Campoverde, J. L. Muñoz-Sanz, and B. del Valle Arenas-Ramirez, “Estimation of pollutant emissions in real driving conditions based on data from OBD and machine learning,” Sensors, vol. 21, no. 19, Art. no. 6344, 2021, https://doi.org/10.3390/s21196344.
[17] X. Li, A. Ren, and Q. Li, “Exploring patterns of transportation-related CO₂ emissions using machine learning methods,” Sustainability, vol. 14, no. 8, Art. no. 4588, 2022, https://doi.org/10.3390/su14084588.
[18] Y. Natarajan, G. Wadhwa, K. R. Sri Preethaa, and A. Paul, “Forecasting carbon dioxide emissions of light-duty vehicles with different machine learning algorithms,” Electronics, vol. 12, no. 10, Art. no. 2288, 2023, https://doi.org/10.3390/electronics12102288.
[19] R. Abdulmalik and G. Srivastava, “Forecasting of transportation-related CO₂ emissions in Canada with different machine learning algorithms,” Advances in Artificial Intelligence and Machine Learning, vol. 3, no. 3, pp. 1295–1312, 2023, https://doi.org/10.54364/AAIML.2023.1176.
[20] H. Mangla, A. Sharma, and S. Shivangi, “Fuel emission detection using machine learning,” International Journal of Advances in Engineering and Management, vol. 3, no. 6, pp. 2471–2476, 2021.
[21] M. Mądziel, “Liquified petroleum gas-fuelled vehicle CO₂ emission modelling based on portable emission measurement system, on-board diagnostics data and gradient-boosting machine learning,” Energies, vol. 16, no. 6, Art. no. 2754, 2023, https://doi.org/10.3390/en16062754.
[22] S. D. Bappon, A. Dey, S. M. Sabuj, and A. Das, “Toward a machine learning approach to predict the CO₂ rating of fuel-consuming vehicles in Canada,” in Proceedings of the 25th International Conference on Computer and Information Technology (ICCIT), 2022, pp. 384–389, https://doi.org/10.1109/ICCIT57492.2022.10054732.
[23] O. Sami, Y. Elsheikh, and F. Almasalha, “The role of data preprocessing techniques in improving machine learning accuracy for predicting coronary heart disease,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, pp. 816–824, 2021, https://doi.org/10.14569/IJACSA.2021.0120695.
[24] M. K. Dahouda and I. Joe, “A deep-learned embedding technique for categorical features encoding,” IEEE Access, vol. 9, pp. 114381–114391, 2021, https://doi.org/10.1109/ACCESS.2021.3104357.
[25] N. Kosaraju, S. R. Sankepally, and K. Mallikharjuna Rao, “Categorical data: Need, encoding, selection of encoding method and its emergence in machine learning models—A practical review study on heart disease prediction dataset using Pearson correlation,” in Proceedings of International Conference on Data Science and Applications. Singapore: Springer, 2023, pp. 369–382, https://doi.org/10.1007/978-981-19-6631-6_26.
[26] S. Sinsomboonthong, “Performance comparison of new adjusted min-max with decimal scaling and statistical column normalization methods for artificial neural network classification,” International Journal of Mathematics and Mathematical Sciences, vol. 2022, Art. no. 3584406, 2022, https://doi.org/10.1155/2022/3584406.
[27] M. Z. Rodriguez, C. H. Comin, D. Casanova, et al., “Clustering algorithms: A comparative approach,” PLOS ONE, vol. 14, no. 1, Art. no. e0210236, 2019, https://doi.org/10.1371/journal.pone.0210236.
[28] H. E. G. Lopes and M. de S. Gosling, “Cluster analysis in practice: Dealing with outliers in managerial research,” Revista de Administração Contemporânea, vol. 25, no. 1, Art. no. e200081, 2021, https://doi.org/10.1590/1982-7849rac2021200081.
[29] G. Yigit and M. F. Amasyali, “Simple but effective GRU variants,” in Proceedings of the 2021 International Conference on Innovations in Intelligent Systems and Applications (INISTA), 2021, pp. 1–6, https://doi.org/10.1109/INISTA52262.2021.9548535.
[30] M. Hasnain, S. R. Jeong, M. F. Pasha, and I. Ghani, “Performance anomaly detection in web services: An RNN-based approach using dynamic quality of service features,” Computers, Materials & Continua, vol. 64, no. 2, pp. 729–752, 2020, https://doi.org/10.32604/cmc.2020.010394.
[31] T. P. Carvalho, F. A. A. M. N. Soares, R. Vita, et al., “A systematic literature review of machine learning methods applied to predictive maintenance,” Computers & Industrial Engineering, vol. 137, Art. no. 106024, 2019, https://doi.org/10.1016/j.cie.2019.106024.
[32] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): When to use them or not,” Geoscientific Model Development, vol. 15, no. 14, pp. 5481–5487, 2022, https://doi.org/10.5194/gmd-15-5481-2022.
[33] A. Zameer, F. Jaffar, F. Shahid, et al., “Short-term solar energy forecasting: Integrated computational intelligence of LSTMs and GRU,” PLOS ONE, vol. 18, no. 10, Art. no. e0285410, 2023, https://doi.org/10.1371/journal.pone.0285410.
[34] T. O. Kvalseth, “Note on the R² measure of goodness of fit for nonlinear models,” Bulletin of the Psychonomic Society, vol. 21, no. 1, pp. 79–80, 1983, https://doi.org/10.3758/BF03329960.
[35] N. Haut, W. Banzhaf, and B. Punch, “Correlation versus RMSE loss functions in symbolic regression tasks,” in Genetic Programming Theory and Practice XIX, L. Trujillo, S. M. Winkler, S. Silva, and W. Banzhaf, Eds. Cham, Switzerland: Springer, 2023, pp. 31–55, https://doi.org/10.1007/978-981-19-8460-0_2.
[36] G. S. Handelman, H. K. Kok, R. V. Chandra, et al., “Peering into the black box of artificial intelligence: Evaluation metrics of machine learning methods,” AJR American Journal of Roentgenology, vol. 212, no. 1, pp. 38–43, 2019, https://doi.org/10.2214/AJR.18.20224.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
