Green Finance and Carbon Emissions: A Nonlinear and Interaction Analysis Using Bayesian Additive Regression Trees

2025-10-22

AI Summary

This study investigates the nonlinear impact of green finance on provincial carbon emission intensity in China and its interaction with climate-related physical risk. Method: Using provincial panel data from 2011–2022, we construct indices for green finance and climate physical risk, and employ the Bayesian additive regression trees (BART) model to capture complex nonlinear relationships, enhanced by SHAP values for interpretability. Results: Green finance exerts a statistically significant inverted-U-shaped effect on carbon emission intensity, with stronger abatement effects in high-energy-consumption regions—highlighting pronounced regional heterogeneity. Climate physical risk does not significantly moderate this relationship, suggesting green finance functions as a robust, standalone decarbonization policy instrument. The study’s key contribution lies in being the first to integrate BART and SHAP to uncover nonlinear threshold effects of green finance, empirically validating its structural efficacy under heterogeneous energy-consumption conditions—thereby providing micro-level evidence to inform precision-targeted green finance policy design.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Reasoning under Uncertainty: Causality
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: The sharing economy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

As a core policy tool for China in addressing climate risks, green finance plays a strategically important role in shaping carbon mitigation outcomes. This study investigates the nonlinear and interaction effects of green finance on carbon emission intensity (CEI) using Chinese provincial panel data from 2000 to 2022. The Climate Physical Risk Index (CPRI) is incorporated into the analytical framework to assess its potential role in shaping carbon outcomes. We employ Bayesian Additive Regression Trees (BART) to capture complex nonlinear relationships and interaction pathways, and use SHapley Additive exPlanations values to enhance model interpretability. Results show that the Green Finance Index (GFI) has a statistically significant inverted U-shaped effect on CEI, with notable regional heterogeneity. Contrary to expectations, CPRI does not show a significant impact on carbon emissions. Further analysis reveals that in high energy consumption scenarios, stronger green finance development contributes to lower CEI. These findings highlight the potential of green finance as an effective instrument for carbon intensity reduction, especially in energy-intensive contexts, and underscore the importance of accounting for nonlinear effects and regional disparities when designing and implementing green financial policies.

Problem

• Analyzing nonlinear effects of green finance on carbon emissions
• Investigating interaction between climate risk and emission intensity
• Assessing regional heterogeneity in green finance effectiveness

Innovation

• Bayesian Additive Regression Trees for nonlinear analysis
• SHAP values for enhancing model interpretability
• Climate Physical Risk Index in analytical framework