Explainable AI for building energy retrofitting under data scarcity

2025-04-08

AI Summary

Addressing data scarcity and class imbalance in energy retrofitting of aging residential buildings, this paper proposes a multi-label retrofit recommendation framework jointly driven by Conditional Tabular GAN (CTGAN)-based synthetic data generation and SHAP-based interpretability. To enhance robustness for minority classes, CTGAN synthesizes high-fidelity tabular samples; a multilayer perceptron (MLP) then models complex, combinatorial retrofit options; finally, SHAP ensures decision transparency and quantifies feature-level attribution. Evaluated on empirical data from Latvia, the framework achieves average improvements of 54% in accuracy, recall, and F1-score, effectively mitigating data insufficiency while preserving physical plausibility and engineering credibility of recommendations. To our knowledge, this is the first work to deeply integrate conditional generative modeling with explainable AI (XAI) for building energy efficiency retrofit recommendation—establishing a novel paradigm for low-carbon decision-making under data-constrained conditions.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Feature Construction/Reformulation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Enhancing energy efficiency in residential buildings is a crucial step toward mitigating climate change and reducing greenhouse gas emissions. Retrofitting existing buildings, which account for a significant portion of energy consumption, is critical particularly in regions with outdated and inefficient building stocks. This study presents an Artificial Intelligence (AI) and Machine Learning (ML)-based framework to recommend energy efficiency measures for residential buildings, leveraging accessible building characteristics to achieve energy class targets. Using Latvia as a case study, the methodology addresses challenges associated with limited datasets, class imbalance and data scarcity. The proposed approach integrates Conditional Tabular Generative Adversarial Networks (CTGAN) to generate synthetic data, enriching and balancing the dataset. A Multi-Layer Perceptron (MLP) model serves as the predictive model performing multi-label classification to predict appropriate retrofit strategies. Explainable Artificial Intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), ensures transparency and trust by identifying key features that influence recommendations and guiding feature engineering choices for improved reliability and performance. The evaluation of the approach shows that it notably overcomes data limitations, achieving improvements up to 54% in precision, recall and F1 score. Although this study focuses on Latvia, the methodology is adaptable to other regions, underscoring the potential of AI in reducing the complexity and cost of building energy retrofitting overcoming data limitations. By facilitating decision-making processes and promoting stakeholders engagement, this work supports the global transition toward sustainable energy use in the residential building sector.

Problem

• Proposes AI framework for energy retrofitting with scarce data
• Uses synthetic data to address dataset limitations and imbalance
• Ensures transparency in retrofit recommendations via explainable AI

Innovation

• CTGAN generates synthetic data for scarcity
• MLP model predicts retrofit strategies
• SHAP provides explainable AI transparency