EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed and Explainable Graph Neural Networks for Generalizable Urban Building Energy Modeling

Rudai Shan, Hao Ning, Qianhui Xu, Xuehua Su, Mengjin Guo, Xiaohan Jia

Applied Sciences · 11.08.2025 · 15 (16) · 8854

DOI: 10.3390/app15168854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 11.08.2025. Verfasst von Rudai Shan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Liaoning Provincial Natural Science Foundation Joint Fund, the Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban building energy prediction is a critical challenge for sustainable city planning and large-scale retrofit prioritization. However, traditional data-driven models struggle to capture real urban environments’ spatial and morphological complexity. In this study, we systematically benchmark a range of graph-based neural networks (GNNs)—including graph convolutional network (GCN), GraphSAGE, and several physics-informed graph attention network (GAT) variants—against conventional artificial neural network (ANN) baselines, using both shape coefficient and energy use intensity (EUI) stratification across three distinct residential districts. Extensive ablation and cross-district generalization experiments reveal that models explicitly incorporating interpretable physical edge features, such as inter-building distance and angular relation, achieve significantly improved prediction accuracy and robustness over standard approaches. Among all models, GraphSAGE demonstrates the best overall performance and generalization capability. At the same time, the effectiveness of specific GAT edge features is found to be district-dependent, reflecting variations in local morphology and spatial logic. Furthermore, explainability analysis shows that the integration of domain-relevant spatial features enhances model interpretability and provides actionable insight for urban retrofit and policy intervention. The results highlight the value of physics-informed GNNs (PINN) as a scalable, transferable, and transparent tool for urban energy modeling, supporting evidence-based decision making in the context of aging residential building upgrades and sustainable urban transformation.

Förderung

  • the Liaoning Provincial Natural Science Foundation Joint Fund
  • the Fundamental Research Funds for the Central Universities

Zitieren

APA

Shan, R., Ning, H., Xu, Q., Su, X., Guo, M., & Jia, X. (2025). Physics-Informed and Explainable Graph Neural Networks for Generalizable Urban Building Energy Modeling. Applied Sciences, 15(16), 8854. https://doi.org/10.3390/app15168854

Vancouver

Shan R, Ning H, Xu Q, Su X, Guo M, Jia X. Physics-Informed and Explainable Graph Neural Networks for Generalizable Urban Building Energy Modeling. Applied Sciences. 2025;15(16):8854. doi:10.3390/app15168854

BibTeX
@article{Shan2025,
  author = {Shan, Rudai and Ning, Hao and Xu, Qianhui and Su, Xuehua and Guo, Mengjin and Jia, Xiaohan},
  title = {Physics-Informed and Explainable Graph Neural Networks for Generalizable Urban Building Energy Modeling},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {8854},
  doi = {10.3390/app15168854}
}
Kostenlos starten →