Understanding the European energy crisis through structural causal models

2025-05-31

AI Summary

This study investigates the causal mechanism behind France’s anomalous electricity price surge—highest in the EU—during the European energy crisis, despite its low natural gas dependency for power generation. We identify large-scale nuclear outages as a critical mediator: they substantially increase net electricity import demand, compelling deeper integration into the pan-European wholesale electricity market and thereby amplifying the transmission of natural gas price shocks to domestic prices. Methodologically, we pioneer a hybrid causal inference framework combining linear structural causal models (SCMs) with Shapley-flow-enhanced nonlinear tree models (XGBoost/LightGBM) to precisely quantify the indirect causal pathway: nuclear outages → heightened import dependence → price synchronization with gas-driven neighbors. Our findings resolve the apparent paradox of high price sensitivity despite low gas-fired generation share, delivering interpretable, policy-actionable causal insights for energy security planning.

Technology Category

Reasoning under Uncertainty: CausalityMachine Learning: Causal LearningGame Theory and Economic Paradigms: Cooperative Game Theory

Application Category

Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applicationsGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphsSocial Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Natural gas supplies in Europe were disrupted and energy prices soared in the context of Russia's invasion of Ukraine. Electricity prices in France experienced the largest relative increase among European countries, even though natural gas plays a negligible role in the French electricity system. In this article, we demonstrate the importance of causal statistical methods and propose causal graphs to investigate the French electricity market and pinpoint key influencing factors on electricity prices and net exports. We demonstrate that a causal approach resolves paradoxical results of simple correlation studies and enables a quantitative analysis of indirect causal effects. We introduce a linear structural causal model as well as non-linear tree-based machine learning combined with Shapley flows. The models elucidate the interplay of gas prices and the unavailability of nuclear power plants during the energy crisis: The high unavailability made France dependent on imports and linked prices to neighbouring countries.

Problem

• Analyzing France's electricity price surge despite low gas dependence
• Identifying key factors affecting electricity prices using causal models
• Quantifying indirect effects of gas prices and nuclear plant outages

Innovation

• Structural causal models for energy crisis analysis
• Combining causal graphs with machine learning
• Shapley flows for indirect effect quantification