IDEAS home Printed from https://ideas.repec.org/a/gam/jforec/v7y2025i1p9-d1596301.html
   My bibliography  Save this article

Comparative Analysis of Physics-Guided Bayesian Neural Networks for Uncertainty Quantification in Dynamic Systems

Author

Listed:
  • Xinyue Xu

    (Department of Architectural Engineering, Pennsylvania State University, State College, PA 16802, USA)

  • Julian Wang

    (Department of Architectural Engineering, Pennsylvania State University, State College, PA 16802, USA)

Abstract

Uncertainty quantification (UQ) is critical for modeling complex dynamic systems, ensuring robustness and interpretability. This study extends Physics-Guided Bayesian Neural Networks (PG-BNNs) to enhance model robustness by integrating physical laws into Bayesian frameworks. Unlike Artificial Neural Networks (ANNs), which provide deterministic predictions, and Bayesian Neural Networks (BNNs), which handle uncertainty probabilistically but struggle with generalization under sparse and noisy data, PG-BNNs incorporate the laws of physics, such as governing equations and boundary conditions, to enforce physical consistency. This physics-guided approach improves generalization across different noise levels while reducing data dependency. The effectiveness of PG-BNNs is validated through a one-degree-of-freedom vibration system with multiple noise levels, serving as a representative case study to compare the performance of Monte Carlo (MC) dropout ANNs, BNNs, and PG-BNNs across interpolation and extrapolation domains. Model accuracy is assessed using Mean Squared Error (MSE), Mean Absolute Percentage Error (MAE), and Coefficient of Variation of Root Mean Square Error (CVRMSE), while UQ is evaluated through 95% Credible Intervals (CIs), Mean Prediction Interval Width (MPIW), the Quality of Confidence Intervals (QCI), and Coverage Width-based Criterion (CWC). Results demonstrate that PG-BNNs can achieve high accuracy and good adherence to physical laws simultaneously, compared to MC dropout ANNs and BNNs, which confirms the potential of PG-BNNs in engineering applications related to dynamic systems.

Suggested Citation

  • Xinyue Xu & Julian Wang, 2025. "Comparative Analysis of Physics-Guided Bayesian Neural Networks for Uncertainty Quantification in Dynamic Systems," Forecasting, MDPI, vol. 7(1), pages 1-21, February.
    • Handle: RePEc:gam:jforec:v:7:y:2025:i:1:p:9-:d:1596301
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2571-9394/7/1/9/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2571-9394/7/1/9/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gokhale, Gargya & Claessens, Bert & Develder, Chris, 2022. "Physics informed neural networks for control oriented thermal modeling of buildings," Applied Energy, Elsevier, vol. 314(C).
    2. Christopher Nemeth & Paul Fearnhead, 2021. "Stochastic Gradient Markov Chain Monte Carlo," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 116(533), pages 433-450, January.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Hu, Guoqing & You, Fengqi, 2024. "AI-enabled cyber-physical-biological systems for smart energy management and sustainable food production in a plant factory," Applied Energy, Elsevier, vol. 356(C).
    2. Liang, Xinbin & Zhu, Xu & Chen, Siliang & Jin, Xinqiao & Xiao, Fu & Du, Zhimin, 2023. "Physics-constrained cooperative learning-based reference models for smart management of chillers considering extrapolation scenarios," Applied Energy, Elsevier, vol. 349(C).
    3. Loaiza-Maya, Rubén & Nibbering, Didier & Zhu, Dan, 2024. "Hybrid unadjusted Langevin methods for high-dimensional latent variable models," Journal of Econometrics, Elsevier, vol. 241(2).
    4. Di Natale, L. & Svetozarevic, B. & Heer, P. & Jones, C.N., 2023. "Towards scalable physically consistent neural networks: An application to data-driven multi-zone thermal building models," Applied Energy, Elsevier, vol. 340(C).
    5. Mukun Yuan & Jian Liu & Zheyuan Chen & Qingda Guo & Mingzhe Yuan & Jian Li & Guangping Yu, 2024. "Predicting Energy Consumption for Hybrid Energy Systems toward Sustainable Manufacturing: A Physics-Informed Approach Using Pi-MMoE," Sustainability, MDPI, vol. 16(17), pages 1-27, August.
    6. Ruben Loaiza-Maya & Didier Nibbering & Dan Zhu, 2023. "Hybrid unadjusted Langevin methods for high-dimensional latent variable models," Papers 2306.14445, arXiv.org.
    7. Katiane S. Conceição & Marinho G. Andrade & Victor Hugo Lachos & Nalini Ravishanker, 2024. "Bayesian Inference for Zero-Modified Power Series Regression Models," Mathematics, MDPI, vol. 13(1), pages 1-30, December.
    8. Xiao, Tianqi & You, Fengqi, 2023. "Building thermal modeling and model predictive control with physically consistent deep learning for decarbonization and energy optimization," Applied Energy, Elsevier, vol. 342(C).
    9. Xiao, Tianqi & You, Fengqi, 2024. "Physically consistent deep learning-based day-ahead energy dispatching and thermal comfort control for grid-interactive communities," Applied Energy, Elsevier, vol. 353(PB).
    10. Guo, Fangzhou & Li, Ao & Yue, Bao & Xiao, Ziwei & Xiao, Fu & Yan, Rui & Li, Anbang & Lv, Yan & Su, Bing, 2024. "Improving the out-of-sample generalization ability of data-driven chiller performance models using physics-guided neural network," Applied Energy, Elsevier, vol. 354(PA).
    11. Viorica Rozina Chifu & Tudor Cioara & Cristina Bianca Pop & Ionut Anghel & Andrei Pelle, 2024. "Physics-Informed Neural Networks for Heat Pump Load Prediction," Energies, MDPI, vol. 18(1), pages 1-20, December.
    12. Taboga, Vincent & Gehring, Clement & Cam, Mathieu Le & Dagdougui, Hanane & Bacon, Pierre-Luc, 2024. "Neural differential equations for temperature control in buildings under demand response programs," Applied Energy, Elsevier, vol. 368(C).
    13. Zhang, Qingang & Zeng, Wei & Lin, Qinjie & Chng, Chin-Boon & Chui, Chee-Kong & Lee, Poh-Seng, 2023. "Deep reinforcement learning towards real-world dynamic thermal management of data centers," Applied Energy, Elsevier, vol. 333(C).
    14. Di Natale, L. & Svetozarevic, B. & Heer, P. & Jones, C.N., 2022. "Physically Consistent Neural Networks for building thermal modeling: Theory and analysis," Applied Energy, Elsevier, vol. 325(C).
    15. Massimiliano Manfren & Karla M. Gonzalez-Carreon & Patrick A. B. James, 2024. "Interpretable Data-Driven Methods for Building Energy Modelling—A Review of Critical Connections and Gaps," Energies, MDPI, vol. 17(4), pages 1-22, February.
    16. Ariel Neufeld & Matthew Ng Cheng En & Ying Zhang, 2024. "Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems," Papers 2403.09532, arXiv.org, revised Mar 2025.
    17. Guo, Yanhua & Wang, Ningbo & Shao, Shuangquan & Huang, Congqi & Zhang, Zhentao & Li, Xiaoqiong & Wang, Youdong, 2024. "A review on hybrid physics and data-driven modeling methods applied in air source heat pump systems for energy efficiency improvement," Renewable and Sustainable Energy Reviews, Elsevier, vol. 204(C).
    18. Rickard Brännvall & Jonas Gustafsson & Fredrik Sandin, 2023. "Modular and Transferable Machine Learning for Heat Management and Reuse in Edge Data Centers," Energies, MDPI, vol. 16(5), pages 1-24, February.
    19. Chen, Dong & Chui, Chee-Kong & Lee, Poh Seng, 2025. "Adaptive physically consistent neural networks for data center thermal dynamics modeling," Applied Energy, Elsevier, vol. 377(PD).
    20. Xiao-Kai Meng & Yan-Bing Jia & Zhi-Heng Liu & Zhi-Qiang Yu & Pei-Jie Han & Zhu-Mao Lu & Tao Jin, 2022. "High-Voltage Cable Condition Assessment Method Based on Multi-Source Data Analysis," Energies, MDPI, vol. 15(4), pages 1-16, February.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jforec:v:7:y:2025:i:1:p:9-:d:1596301. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.