Neural Modelling of CO2 Emissions from a Selected Vehicle
Source abstract
Abstract
The article addresses the problem of modelling instantaneous CO2 emissions from a specific motor vehicle equipped with an internal combustion engine. The article’s concept is based on a review of current research, which led to the identification of a list of variables essential to constructing the numerical model. Data was collected through recording selected vehicle parameters during test drives using the OBD diagnostic interface. The article describes the model development process and presents the results of CO2 emission modelling using MLP neural networks. The performance of various architectures was examined, considering the number of hidden layers (1, 2, 3), the number of neurons in each layer (from 10 to 267), and different activation functions (such as sigmoid, hyperbolic tangent, and ReLU). Consistency in the values of the MSE, RMSE, and MAE indicators during both validation and testing phases demonstrates the accuracy of the models. High R2 values of around 0.8 confirm that MLP networks can effectively model CO2 emissions from motor vehicles.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Vehicle emissions and performance · Engine and Fuel Emissions · Mechanical and Thermal Properties Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Security, Logistics and Management, Military University of Technology, 00-908 Warsaw, Poland
Funding
Military University of Technology
References (40)
Show source-provided references
1. Reducing greenhouse gas emissions of a heterogeneous vehicle fleet10.1007/s10696-013-9180-9 ↗
2. Application of the life cycle assessment method in public bus transport
3. The uniqueness of pollutant emission and fuel consumption test results for road vehicles tested on a chassis dynamometer
4. Modelowanie emisji z wykorzystaniem symulacji mikroskopowych
5. Rykała, M., Grzelak, M., Rykała, Ł., Voicu, D., and Stoica, R.-M. (2023). Modeling Vehicle Fuel Consumption Using a Low-Cost OBD-II Interface. Energies, 16.10.3390/en16217266 ↗
6. Matijošius, J., Žvirblis, T., Rimkus, A., Stravinskas, S., and Kilkevičius, A. (2026). Emissions, reliability and maintenance aspects of a dual-fuel engine (diesel-natural gas) using HVO additive and ANCOVA modeling. Eksploat. Niezawodn. Maint. Reliab., 28.10.17531/ein/208439 ↗
7. Estimation of CO2 emissions from vehicles using machine learning and multi-model investigation
8. Brzezinski, M., Kijek, M., Gontarczyk, M., Rykala, L., and Zelkowski, J. (2017, January 20–22). Fuzzy Modeling of Evaluation Logistic Systems. Proceedings of the 21st International Conference, Transport Means, Juodkrante, Lithuania.
9. Donateo, T., and Filomena, R. (2020, January 15–16). Real time estimation of emissions in a diesel vehicle with neural networks. Proceedings of the E3S Web of Conferences, EDP Sciences, 75th National ATI Congress, Rome, Italy.10.1051/e3sconf/202019706020 ↗
10. Degradation generation and prediction based on machine learning methods: A comparative study
11. Deep learning model based CO2 emissions prediction using vehicle telematics sensors data10.1109/TIV.2021.3102400 ↗
12. Alam, G.M.I., Arfin Tanim, S., Sarker, S.K., Watanobe, Y., Islam, R., Mridha, M.F., and Nur, K. (2025). Deep learning model based prediction of vehicle CO2 emissions with eXplainable AI integration for sustainable environment. Sci. Rep., 15.10.1038/s41598-025-87233-y ↗
13. Selvam, H.P., Li, Y., Wang, P., Northrop, W.F., and Shekhar, S. (2021). Vehicle emissions prediction with physics-aware ai models: Preliminary results. arXiv.
14. Michailidis, E.T., Panagiotopoulou, A., and Papadakis, A. (2025). A Review of OBD-II-Based Machine Learning Applications for Sustainable, Efficient, Secure, and Safe Vehicle Driving. Sensors, 25.10.3390/s25134057 ↗
15. Application of Deep Learning Initiatives for CO2 Emissions Forecasting
16. Estimation of transport CO2 emissions using machine learning algorithm10.1016/j.trd.2024.104276 ↗
17. Forecasting CO2 emissions of fuel vehicles for an ecological world using ensemble learning, machine learning, and deep learning models10.7717/peerj-cs.2234 ↗
18. Using the relationship between vehicle fuel consumption and CO2 emissions to illustrate chemical principles10.1021/ed085p218 ↗
19. Fuel consumption and CO2 emissions from passenger cars in Europe–Laboratory versus real-world emissions10.1016/j.pecs.2016.12.004 ↗
20. Comparison of exhaust emission results obtained from Portable Emissions Measurement System (PEMS) and a laboratory system
21. Determining the environmental indicators for vehicles of different categories in relation to CO2 emission based on road tests10.19206/CE-2017-310 ↗
22. An impact assessment of functional systems in vehicles on CO2 emissions and fuel consumption10.1051/matecconf/201711800030 ↗
23. Driving style analysis based on information from the vehicle’s OBD system10.19206/CE-2019-330 ↗
24. Driving style analysis and driver classification using OBD data of a hybrid electric vehicle10.21307/tp-2020-050 ↗
25. Independent driving pattern factors and their influence on fuel-use and exhaust emission factors10.1016/S1361-9209(01)00003-7 ↗
26. Rykała, Ł., Rubiec, A., Przybysz, M., Krogul, P., Cieślik, K., Muszyński, T., and Rykała, M. (2023). Research on the Positioning Performance of GNSS with a Low-Cost Choke Ring Antenna. Appl. Sci., 13.10.3390/app13021007 ↗
27. Malon, K., Łopatka, J., Rykała, Ł., and Łopatka, M. (2018, January 10–12). Accuracy Analysis of UWB Based Tracking System for Unmanned Ground Vehicles. Proceedings of the 2018 New Trends in Signal Processing (NTSP), Demänovská Dolina, Slovakia.10.23919/NTSP.2018.8524118 ↗
28. Cellina, M., Strada, S., and Savaresi, S.M. (2023, January 24–28). Vehicle fuel consumption virtual sensing from GNSS and IMU measurements. Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain.10.1109/ITSC57777.2023.10422477 ↗
29. Research on the results of the WLTP procedure for a passenger vehicle
30. (2025, September 15). Feature Selection. Available online: https://www.mathworks.com/help/stats/feature-selection.html.
31. Building feature-based machine learning regression to quantify urban material stocks: A Hong Kong study10.1111/jiec.13348 ↗
32. (2025, September 15). Neural Networks: Activation functions. Available online: https://developers.google.com/machine-learning/crash-course/neural-networks/activation-functions?hl=pl.
33. Osowski, S., Cichocki, A., and Siwek, K. (2006). MATLAB w Zastosowaniu do Obliczeń Obwodowych i Przetwarzania Sygnałów, Oficyna Wydawnicza Politechniki Warszawskiej.
34. Rykała, M., and Rykała, Ł. (2021). Economic Analysis of a Transport Company in the Aspect of Car Vehicle Operation. Sustainability, 13.10.3390/su13010427 ↗
35. Osowski, S. (2013). Metody i narzędzia eksploracji danych, BTC.
36. Rykała, M. (2025). A Study of the CO2 Emissions of a Passenger Vehicle on a Selected Example Using Mathematical Methods. [Ph.D. Thesis, Military University of Technology].
37. Accuracy evaluation of multi-GNSS Doppler velocity estimation using android smartphones10.5194/isprs-archives-XLVI-3-W1-2022-89-2022 ↗
38. Experimental studies on the relationship between HDOP and position error in the GPS system
39. How many GNSS satellites are too many?10.1109/TAES.2012.6324666 ↗
40. Ragab, H., Givigi, S., and Noureldin, A. (May, January 28). Automotive speed estimation: Sensor types and error characteristics from obd-ii to adas. Proceedings of the 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Salt Lake City, UT, USA.10.1109/PLANS61210.2025.11028310 ↗