EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Invisible footprints, visible insights: machine learning reveals Scope 3 emissions

Szu-Yung Wang, Nian-Zu Ye

Frontiers in Sustainability · 09.09.2025 · 6

DOI: 10.3389/frsus.2025.1649150 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Sustainability, online erschienen am 09.09.2025. Verfasst von Szu-Yung Wang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Scope 3 greenhouse gas emissions are critical to firms’ carbon footprints yet are often difficult to quantify due to limited direct data, motivating predictive modeling approaches.

Methods

We developed and compared four machine learning algorithms (K-nearest neighbors, random forest, AdaBoost, and XGBoost) to estimate corporate Scope 3 emissions using readily available financial and sustainability performance data. We leverage 10,449 listed firm-level data from 2014 to 2023, covering major industries such as semiconductor, steel, textile, and building materials, evaluating performance of each model by a held-out test set with metrics including R 2 , mean absolute percentage error (MAPE), and root mean squared logarithmic error (RMSLE).

Results

XGBoost achieved the highest accuracy (R 2 = 0.85, MAPE = 15%, RMSLE = 0.20), outperforming random forest (R 2 = 0.80, MAPE = 20%) and AdaBoost (R 2 = 0.78), while K-NN had the lowest accuracy (R 2 = 0.60). The results demonstrate that ensemble tree-based models substantially improve Scope 3 emission prediction accuracy over simpler models.

Discussion

Notably, random forest’s interpretable feature importance provided insight into key emission drivers with only a slight accuracy trade-off, highlighting the balance between predictive accuracy and model interpretability.

Zitieren

APA

Wang, S., & Ye, N. (2025). Invisible footprints, visible insights: machine learning reveals Scope 3 emissions. Frontiers in Sustainability, 6. https://doi.org/10.3389/frsus.2025.1649150

Vancouver

Wang S, Ye N. Invisible footprints, visible insights: machine learning reveals Scope 3 emissions. Frontiers in Sustainability. 2025;6. doi:10.3389/frsus.2025.1649150

BibTeX
@article{Wang2025,
  author = {Wang, Szu-Yung and Ye, Nian-Zu},
  title = {Invisible footprints, visible insights: machine learning reveals Scope 3 emissions},
  journal = {Frontiers in Sustainability},
  year = {2025},
  volume = {6},
  doi = {10.3389/frsus.2025.1649150}
}
Kostenlos starten →