Scholarlink

<p>Machine learning models are increasingly deployed in critical energy infrastructure, where domain experts require transparent explanations for decision-making. SHAP (SHapley Additive exPlanations) has become a popular method for energy systems applications. However, energy data exhibit inherent correlations due to physical constraints, operational relationships, and market dynamics, posing challenges for interpreting SHAP-based explanations. This work investigates how feature correlations influence SHAP-based explanations using controlled synthetic experiments and real-world power grid data. Our analysis shows that only correlation-aware methods can attribute importance to economically linked features, such as solar generation in predicting fossil fuels, which may reflect genuine systemic interdependencies that are valuable for prediction and scientific understanding. Our findings highlight the tradeoff between <i>true to the model</i> explanations that reflect model behavior and <i>true to the data</i> approaches that consider real-world dependencies. In complex energy systems with circular dependencies, temporal dynamics, and hidden constraints, explanation validity cannot be universally defined. We emphasize the need for practitioners’ awareness of the trade-offs between model analysis, scientific discovery, and operational understanding.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Correlations Matter in Explanations for Energy Systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月30日

查看全文
  • Alexandra Nikoltchovska,
  • Sebastian Pütz,
  • Markus Götz,
  • Benjamin Schäfer

摘要

Machine learning models are increasingly deployed in critical energy infrastructure, where domain experts require transparent explanations for decision-making. SHAP (SHapley Additive exPlanations) has become a popular method for energy systems applications. However, energy data exhibit inherent correlations due to physical constraints, operational relationships, and market dynamics, posing challenges for interpreting SHAP-based explanations. This work investigates how feature correlations influence SHAP-based explanations using controlled synthetic experiments and real-world power grid data. Our analysis shows that only correlation-aware methods can attribute importance to economically linked features, such as solar generation in predicting fossil fuels, which may reflect genuine systemic interdependencies that are valuable for prediction and scientific understanding. Our findings highlight the tradeoff between true to the model explanations that reflect model behavior and true to the data approaches that consider real-world dependencies. In complex energy systems with circular dependencies, temporal dynamics, and hidden constraints, explanation validity cannot be universally defined. We emphasize the need for practitioners’ awareness of the trade-offs between model analysis, scientific discovery, and operational understanding.