Greenhouse gases emissions: estimating corporate non-reported emissions using interpretable machine learning

Paper: arXiv 2212.10844

Authors: Jeremi Assael, Thibaut Heurtebize, Laurent Carlier, François Soupé

Abstract

As of 2022, greenhouse gases (GHG) emissions reporting and auditing are not yet compulsory for all companies and methodologies of measurement and estimation are not unified. We propose a machine learning-based model to estimate scope 1 and scope 2 GHG emissions of companies not reporting them yet. Our model, specifically designed to be transparent and completely adapted to this use case, is able to estimate emissions for a large universe of companies. It shows good out-of-sample global performances as well as good out-of-sample granular performances when evaluating it by sectors, by countries or by revenues buckets. We also compare our results to those of other providers and find our estimates to be more accurate. Thanks to the proposed explainability tools using Shapley values, our model is fully interpretable, the user being able to understand which factors split explain the GHG emissions for each particular company.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 7.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper provides a highly practical and empirically rigorous approach to estimating non-reported corporate GHG emissions using interpretable machine learning. While the mathematical formulation relies on standard ML models and SHAP values rather than novel theoretical math, its granular cross-sector, cross-country, and revenue-bucket validation against existing providers makes it valuable for sustainable quantitative finance.

Research Flowchart

  flowchart TD
    A[Research Goal: Estimate non-reported Scope 1 & 2 GHG emissions] --> B[Input Data: Corporate financial metrics, sector, revenue, country]
    B --> C[Methodology: Train interpretable Machine Learning models]
    C --> D[Model Evaluation: Assess global, sectoral, country, and revenue-bucket performance]
    C --> E[Explainability Engine: Apply Shapley values SHAP for feature attribution]
    D --> F[Key Outcome: Superior out-of-sample accuracy vs. existing ESG providers]
    E --> G[Key Outcome: Fully transparent, company-specific emission drivers]