• Skip to primary navigation
  • Skip to main content
  • Skip to footer

Climate Attribution

  • Home
  • Search
    • Climate Change Attribution
    • Extreme Event Attribution
    • Impact Attribution
    • Source Attribution
    • Court Attribution
  • About
    • Contact
    • Sitemap
  • Related Resources
    • Conference – January 9-10, 2025
  • Subscribe

Greenhouse Gases Emissions: Estimating Corporate Non-Reported Emissions Using Interpretable Machine Learning

Summary/Abstract

This study addresses the gap in corporate greenhouse gas emissions reporting by developing a machine learning-based model that estimates unreported Scope 1 and Scope 2 emissions. The model combines transparency with high accuracy, allowing for detailed insights into the factors influencing emissions estimates across various sectors and countries. This research is significant for stakeholders needing reliable data for making informed environmental and investment decisions.

Assael, J., Heurtebize, T., Carlier, L., & Soupé, F. (2023). Greenhouse Gases Emissions: Estimating Corporate Non-Reported Emissions Using Interpretable Machine Learning. Sustainability, 15(4), 3391. DOI: 10.3390/su15043391.

View Resource
February 2023
Jérémi Assael, Thibaut Heurtebize, Laurent Carlier, François Soupé
Sustainability
Peer-reviewed Study
Global
Source Attribution
Source Attribution → Corporate Emissions

Footer

This website provides educational information. It does not, nor is it intended to, provide legal advice. No attorney-client relationship is established by use of this site. Consult with an attorney for any needed legal advice. There is no warranty of accuracy, adequacy or comprehensiveness. Those who use information from this website do so at their own risk.

© 2026 Sabin Center for Climate Change Law
Made with by Satellite Jones