To best learn from data about large-scale complex systems, physics-based models representing the laws of nature must be integrated into the learning process. Inverse theory provides a crucial perspective for addressing the challenges of ill-posedness, uncertainty, nonlinearity and under-sampling.
This is a preview of subscription content, access via your institution
Relevant articles
Open Access articles citing this article.
-
Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials
npj Computational Materials Open Access 12 June 2023
-
A general framework for quantifying uncertainty at scale
Communications Engineering Open Access 10 December 2022
-
3D multi-physics uncertainty quantification using physics-based machine learning
Scientific Reports Open Access 19 October 2022
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$99.00 per year
only $8.25 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Coveney, P. V., Dougherty, E. R. & Highfield, R. R. Philos. Trans. R. Soc. A 374, 20160153 (2016).
Wigner, E. P. In Mathematics and Science 291–306 (World Scientific, 1990).
Engl, H. W., Hanke, M. & Neubauer, A. Regularization of Inverse Problems Vol. 375 (Springer, 1996).
Biegler, L. et al. Large-scale Inverse Problems and Quantification of Uncertainty (Wiley, 2011).
Isaac, T., Petra, N., Stadler, G. & Ghattas, O. J. Comput. Phys. 296, 348–368 (2015).
Oden, T., Moser, R. & Ghattas, O. SIAM News 43, 1–3 (2010).
Loose, N. & Heimbach, P. J. Adv. Model. Earth Sys. https://doi.org/10.1029/2020MS002386 (2021).
Bauer, P., Thorpe, A. & Brunet, G. Nature 525, 47–55 (2015).
Wunsch, C. In Encyclopedia of Ocean Sciences (eds Cochran, J. K. et al.) 502–512 (Elsevier, 2019).
Tarantola, A. Inverse Problem Theory and Methods for Model Parameter Estimation (SIAM, 2005).
Kaipio, J. & Somersalo, E. Statistical and Computational Inverse Problems (Springer, 2005).
Baydin, A. G., Pearlmutter, B. A., Radul, A. A. & Siskind, J. M. J. Mach. Learn. Res. 18, 1–43 (2018).
Bauer, P., Stevens, B. & Hazeleger, W. Nat. Clim. Change 11, 80–83 (2021).
Palmer, T. N., Buizza, R., Molteni, F., Chen, Y.-Q. & Corti, S. Philos. Trans. R. Soc. London A 348, 459–475 (1994).
Rüde, U., Willcox, K., McInnes, L. C. & De Sterck, H. SIAM Rev. 60, 707–754 (2018).
Acknowledgements
K.E.W. and O.G. acknowledge US Department of Energy grants DE-SC0019303 and DE-SC0021239. P.H. acknowledges NSF grant #1603903 and funding from NASA/ECCO through a JPL/Caltech subcontract.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Peer review information Nature Computational Science thanks the anonymous reviewers for their contribution to the peer review of this work. Fernando Chirigati was the primary editor on this Comment and managed its editorial process and peer review in collaboration with the rest of the editorial team.
Rights and permissions
About this article
Cite this article
Willcox, K.E., Ghattas, O. & Heimbach, P. The imperative of physics-based modeling and inverse theory in computational science. Nat Comput Sci 1, 166–168 (2021). https://doi.org/10.1038/s43588-021-00040-z
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-021-00040-z
This article is cited by
-
Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials
npj Computational Materials (2023)
-
Application of Artificial Intelligence in Static Formation Temperature Estimation
Arabian Journal for Science and Engineering (2023)
-
Physics-informed neural networks for predicting liquid dairy manure temperature during storage
Neural Computing and Applications (2023)
-
3D multi-physics uncertainty quantification using physics-based machine learning
Scientific Reports (2022)
-
A general framework for quantifying uncertainty at scale
Communications Engineering (2022)