Vehicle Carbon Emissions Detector Using Recurrent Neural Network
Keywords:
Carbon emissions, Machine learning, Vehicle pollution, RNN, LSTMAbstract
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.
Downloads
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.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Articles published in the Academic Research Journal of Science and Technology (ARJST will be Open-Access articles distributed under the terms and conditions of the Creative Commons Attribution-Noncommercial 4.0 International (CC BY-NC 4.0). This allows for immediate free access to the work and permits any user to read, download, copy, distribute, print, search, or link to the full texts of articles, crawl them for indexing, pass them as data to software, or use them for any other lawful purpose.
This open-access article is distributed under the terms and conditions of the Creative Commons Attribution-Noncommercial 4.0 International (CC BY-NC 4.0).
