Scientific Machine Learning

Scientific machine learning blends scientific computing and machine learning.

We focus on an approach that has been termed as “physics-informed machine learning” or, more properly, “thermodynamics-informed machine learning”.

With the irruption of the so-called fourth paradigm of science a growing interest is detected on the machine learning of scientific laws. A plethora of methods have been developed that are able to produce more or less accurate predictions about the response of physical systems in previously unseen situations by employing techniques ranging from classical regression to the most sophisticated deep learning methods.


  1. Structure-preserving neural networks. Q. Hernandez, A. Badias, D. Gonzalez, F. Chinesta, E. Cueto. Submitted, 2020. [Arxiv preprint]
  2. Physically sound, self-learning digital twins for sloshing fluids. B. Moya, I. Alfaro, D. Gonzalez, F. Chinesta, E. Cueto. Submitted, 2020.
  3. Learning non-Markovian physics from data. D. Gonzalez, F. Chinesta, E. Cueto. Submitted, 2019.
  4. A data-driven learning method for constitutive modeling: application to vascular hyperelastic soft tissues. D. Gonzalez, A. Garcia-Gonzalez, F. Chinesta, E. Cueto. Submitted, 2019.
  5. Learning Physics from Data: a Thermodynamic Interpretation. F. Chinesta, E. Cueto, M. Grmela, B. Moya, M. Pavelka. Submitted, 2019. [ArXiv preprint]
  6. Incremental Dynamic Mode Decomposition: A reduced-model learner operating at the low-data limit. A. Reille, N. Hascoet, Ch. Ghnatios, A. Ammar, E. Cueto, J.-L. Duval, F. Chinesta, R. Keunings. Comptes Rendus Mécanique, 347 (11), 780-792, 2019. [Download PDF of draft]
  7. Data-driven GENERIC modeling of poroviscoelastic materials. Chady Ghnatios, Iciar Alfaro, David González, Francisco Chinesta and Elias Cueto. Entropy 21 (12), 1165, 2019. [Download PDF from publisher (Open Access)]
  8. Some applications of compressed sensing in computational mechanics. Model order reduction, manifold learning, data-driven applications and nonlinear dimensionality reduction. R. Ibanez, E. Abisset-Chavanne, E. Cueto, A. Ammar, J.-L. Duval, F. Chinesta. Computational Mechanics, 64:1259–1271, 2019. [Download PDF of draft]
  9. Hybrid Constitutive Modeling: Data-driven learning of corrections to plasticity models. R. Ibañez, E. Abisset-Chavanne, D. Gonzalez, J. L. Duval, E. Cueto, F. Chinesta, International Journal of Material Forming, 12(4), 717–725, 2019. [Download PDF of draft]
  10. Learning slosh dynamics by means of data. B. Moya, D. Gonzalez, I. Alfaro, F. Chinesta, E. Cueto. Computational Mechanics, 64, Issue 2, pp 511–52, 2019. [Download PDF of draft]
  11. Thermodynamically consistent data-driven computational mechanics. D. González, F. Chinesta, E. Cueto. Continuum Mechanics and Thermodynamics, 31 (1), pp 239–253, 2019. [Download PDF of draft]
  12. Learning corrections for hyperelastic models from data. David Gonzalez, Francisco Chinesta and Elias Cueto. Frontiers Materials. volume 6, article 14, 2019. [Download PDF of draft, Download from publisher (Open Access)]


Funding Institutions