Abstract
The rapid increase in global vehicle usage has significantly contributed to rising carbon emissions, posing serious threats to the environment and human health. This study proposes a machine learning–based approach for detecting and predicting vehicle carbon emissions based on engine and vehicle parameters. Applying a Recurrent Neural Network (RNN) based Long Short-Term Memory (LSTM) model to estimate the real-time CO2 emissions is a highly effective approach, particularly since emission data from real-world driving cycles are sequential and time-dependent. While your original study uses a strong non-temporal model (Random Forest Regressor with R2=0.93), the LSTM model is better suited to capture the temporal dependencies in real-time data collected from sources like On-Board Diagnostics (OBD-II) ports.
Views & downloads
- Article views
- Full-text downloads
References
9 references- 1. Smith, John, and Thomas Brown. 2019. “Vehicle Emission Analysis Using Regression Techniques.” International Journal of Environmental Engineering 14, no. 2: 85–97.
- 2. Lee, Kwan, and Rakesh Kumar. 2020. “Decision Tree Modeling for CO₂ Emission Estimation.” Journal of Sustainable Transportation Analytics 9, no. 3: 112–126.
- 3. Johnson, Laura, Peter Williams, Yan Chen, and Maria Torres. 2021. “Machine Learning Approaches to Emission Prediction.” Environmental Data Science Review 7, no. 1: 33–52.
- 4. Ahmed, Farah, and Li Zhao. 2022. “Deep Learning for Environmental Data Analytics.” Journal of Advanced Environmental Informatics 5, no. 4: 201–218.
- 5. Patel, Meera, Vivek Singh, Suresh Rao, and Juan Silva. 2023. “Hybrid Ensemble Models for Vehicle Emission Detection.” International Journal of Intelligent Systems and Green Technology 12, no. 1: 59–78.
- 6. Mobasshir, A., T. Rahman, and M. Chowdhury. 2025. “Light Multilayer Perceptron Architecture for Real-Time Vehicle Emission Prediction with Explainable AI Integration.” Journal of Intelligent Transportation Analytics 18, no. 1: 45–62.
- 7. GreenNav Research Group. 2024. “Hybrid CNN–LSTM Deep Learning Framework for City-Level CO₂ Emission Forecasting Using Spatial–Temporal Traffic Data.” Sustainability 16, no. 4: 2210–2234.
- 8. Hassan, R., K. Priya, and D. Velasquez. 2025. “Comparative Evaluation of Machine Learning Algorithms for Vehicle Emission Prediction: A Study of 18 Models Including XGBoost and LightGBM.” ResearchGate Preprint, December 2025.
- 9. Zhang, Y., H. Lin, and P. Duarte. 2024. “MSCL-Attention: A Multi-Scale CNN–LSTM Network with Multi-Head Self-Attention for High-Precision CO₂ Emission Modeling.” Energies 17, no. 9: 1550–1578.
