EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting the Carbon Footprint of Building Material Using Machine Learning: Production Phase, Secondary Material Use, and Recycling Potential

Karol Skiba iD, Aleksandra Mach iD, Joanna Sagan iD, Roman Kinasz iD

Materials · 02.11.2026 · 19 (21) · 4666

DOI: 10.3390/ma19214666 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 02.11.2026. Verfasst von Karol Skiba und 3 weiteren Autor:innen. Beteiligte Einrichtung: AGH Doctoral School, AGH University of Krakow, Al, Mickiewicza 30, 30-059 Krakow, Poland. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AGH University of Krakow.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Environmental product declarations (EPDs) provide carbon footprint data for construction products. This study evaluated machine learning predictions of global warming potential (GWP–total) for the production stage (A1–A3) and module D from EPD resource-use and waste indicators, focusing on secondary material use (SM). After interquartile range removal of target outliers, the analysis used 2214 A1–A3 records and 1765 EPDs with module D data from ÖKOBAUDAT. Extreme Gradient Boosting (XGBoost), Random Forest, and Support Vector Regression (SVR) were tuned by 5-fold cross-validation; predictor importance was assessed with Shapley Additive Explanations values and ablation. XGBoost achieved the highest test coefficient of determination (R2) 0.963 for A1–A3, 0.791 for module D, with relative mean absolute errors of 13% and 27%, respectively. Its advantage over Random Forest was mostly within bootstrap uncertainty. Total use of non-renewable primary energy resources (PENRT) dominated A1–A3 predictions, whereas radioactive waste disposed (RWD), total use of renewable primary energy resources (PERT), and SM gained importance for module D. Removing SM changed module D R2 by −0.03 (95% confidence interval: −0.07 to 0.00). Grouped validation reduced module D R2 to approximately 0.4 for unseen groups. The models may support plausibility checks and estimation of missing module D values.

Schlagwörter

Stichwörter der Autor:innen

EPDLCAMLbuilding materialscarbon footprintenvironmental product declarationsglobal warming potentiallife cycle assessmentmachine learningmodule Drecycling potentialsecondary materials

Autor:innen und Institutionen

  • AGH Doctoral School, AGH University of Krakow, Al, Mickiewicza 30, 30-059 Krakow, Poland.
  • Faculty of Civil Engineering and Resource Management, AGH University of Krakow, Al, Mickiewicza 30, 30-059 Krakow, Poland.

ORCID-Profile: Karol Skiba, Aleksandra Mach, Joanna Sagan, Roman Kinasz

Förderung

  • AGH University of Krakow

Zitieren

APA

Skiba, K., Mach, A., Sagan, J., & Kinasz, R. (2026). Predicting the Carbon Footprint of Building Material Using Machine Learning: Production Phase, Secondary Material Use, and Recycling Potential. Materials, 19(21), 4666. https://doi.org/10.3390/ma19214666

Vancouver

Skiba K, Mach A, Sagan J, Kinasz R. Predicting the Carbon Footprint of Building Material Using Machine Learning: Production Phase, Secondary Material Use, and Recycling Potential. Materials. 2026;19(21):4666. doi:10.3390/ma19214666

BibTeX
@article{Skiba2026,
  author = {Skiba, Karol and Mach, Aleksandra and Sagan, Joanna and Kinasz, Roman},
  title = {Predicting the Carbon Footprint of Building Material Using Machine Learning: Production Phase, Secondary Material Use, and Recycling Potential},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {21},
  pages = {4666},
  doi = {10.3390/ma19214666}
}
Kostenlos starten →