CO 2 Emission and Energy Consumption Estimates in the COPERT Model—Conclusions from Chassis Dynamometer Tests and SANN Artificial Neural Network Models and Their Meaning for Transport Management
Olga Orynycz (),
Magdalena Zimakowska-Laskowska () and
Ewa Kulesza
Additional contact information
Olga Orynycz: Faculty of Engineering Management, Department of Production Management, Bialystok University of Technology, Wiejska Street 45A, 15-351 Bialystok, Poland
Magdalena Zimakowska-Laskowska: Environment Protection Centre, Motor Transport Institute, 03-301 Warsaw, Poland
Ewa Kulesza: Department of Mechanics and Applied Computer Science, Faculty of Mechanical Engineering, Bialystok University of Technology, Wiejska Street 45A, 15-351 Bialystok, Poland
Energies, 2025, vol. 18, issue 13, 1-20
Abstract:
This article aimed to assess the accuracy of the COPERT model in predicting CO 2 emissions and energy consumption in real operating conditions, represented by the WLTP homologation tests. Experimental data obtained for a Euro 6 vehicle were compared with the values estimated by the COPERT model, assuming identical speed conditions. MLP and SANN artificial neural networks were also used to create a model describing the complex relationships between emissions, speed, and energy consumption. The results indicate an apparent overestimation of CO 2 and energy consumption values by the COPERT model, especially in the low-speed range typical of urban traffic. The minimum energy consumption values were observed at speeds of 50–70 km/h, indicating the existence of an optimal drive system operation zone. The neural models showed high efficiency in predicting the tested parameters—the best results were obtained for the MLP 6-10-1 architecture, whose correlation coefficient exceeded 0.98 in the validation set. The paper highlights the need to calibrate the COPERT model using local experimental data and integrate artificial intelligence methods in modern emission inventories.
Keywords: CO 2 emission; energy consumption; COPERT model; artificial neural networks (MLP; SANN) (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
https://www.mdpi.com/1996-1073/18/13/3457/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/13/3457/ (text/html)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:13:p:3457-:d:1692014
Access Statistics for this article
Energies is currently edited by Ms. Agatha Cao
More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().