Efficiently embedding and/or integrating mechanistic information with data-driven models is essential if it is desired to simultaneously take advantage of both engineering principles and data-science. Further the opportunity for hybridization occurs in many scenarios, such as the development of a faster model of an accurate high-fidelity computer model; the correction of a mechanistic model that does not fully-capture the physical phenomena of the system; or the integration of a data-driven component approximating an unknown correlation within a mechanistic model. At the same time, different techniques have been proposed and applied in different literatures to achieve this hybridization, such as hybrid modeling, physics-informed Machine Learning (ML) and model calibration. In this paper we review the methods, challenges, applications and algorithms of these three research areas and discuss them in the context of the different hybridization scenarios. Moreover, we provide a comprehensive comparison of the hybridization techniques with respect to their differences and similarities, as well as advantages and limitations and future perspectives. Finally, we apply and illustrate hybrid modeling, physics-informed ML and model calibration via a chemical reactor case study.
Bradley, William, et al. "Perspectives on the integration between first-principles and data-driven modeling." Computers and Chemical Engineering, vol. 166, Jun. 2022. https://doi.org/10.1016/j.compchemeng.2022.107898
Bradley, William, Kim, Jinhyeun, Kilwein, Zachary, Blakely, Logan, Eydenberg, Michael, Jalvin, Jordan, Laird, Carl, & Boukouvala, Fani (2022). Perspectives on the integration between first-principles and data-driven modeling. Computers and Chemical Engineering, 166. https://doi.org/10.1016/j.compchemeng.2022.107898
Bradley, William, Kim, Jinhyeun, Kilwein, Zachary, et al., "Perspectives on the integration between first-principles and data-driven modeling," Computers and Chemical Engineering 166 (2022), https://doi.org/10.1016/j.compchemeng.2022.107898
@article{osti_1889102,
author = {Bradley, William and Kim, Jinhyeun and Kilwein, Zachary and Blakely, Logan and Eydenberg, Michael and Jalvin, Jordan and Laird, Carl and Boukouvala, Fani},
title = {Perspectives on the integration between first-principles and data-driven modeling},
annote = {Efficiently embedding and/or integrating mechanistic information with data-driven models is essential if it is desired to simultaneously take advantage of both engineering principles and data-science. Further the opportunity for hybridization occurs in many scenarios, such as the development of a faster model of an accurate high-fidelity computer model; the correction of a mechanistic model that does not fully-capture the physical phenomena of the system; or the integration of a data-driven component approximating an unknown correlation within a mechanistic model. At the same time, different techniques have been proposed and applied in different literatures to achieve this hybridization, such as hybrid modeling, physics-informed Machine Learning (ML) and model calibration. In this paper we review the methods, challenges, applications and algorithms of these three research areas and discuss them in the context of the different hybridization scenarios. Moreover, we provide a comprehensive comparison of the hybridization techniques with respect to their differences and similarities, as well as advantages and limitations and future perspectives. Finally, we apply and illustrate hybrid modeling, physics-informed ML and model calibration via a chemical reactor case study.},
doi = {10.1016/j.compchemeng.2022.107898},
url = {https://www.osti.gov/biblio/1889102},
journal = {Computers and Chemical Engineering},
issn = {ISSN 0098-1354},
volume = {166},
place = {United States},
publisher = {Elsevier},
year = {2022},
month = {06}}
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); National Network for Manufacturing Innovation (NNMI); National Science Foundation (NSF); Georgia Tech
OSTI ID:
1889102
Report Number(s):
SAND2022-12844J; 710091
Journal Information:
Computers and Chemical Engineering, Journal Name: Computers and Chemical Engineering Vol. 166; ISSN 0098-1354
ASME 2002 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Volume 2: 28th Design Automation Conferencehttps://doi.org/10.1115/DETC2002/DAC-34092