PuSH - Publication Server of Helmholtz Zentrum München

Vinuesa, R.* ; Cinnella, P.* ; Rabault, J.* ; Azizpour, H.* ; Bauer, S. ; Brunton, B.W.* ; Elofsson, A.* ; Jarlebring, E.* ; Kjellström, H.* ; Markidis, S.* ; Marlevi, D.* ; García‐Martínez, J.* ; Brunton, S.L.*

Decoding complexity through machine learning is redefining scientific discovery.

Commun. Phys. 9:168 (2026)
Publ. Version/Full Text DOI
Open Access Gold
Creative Commons Lizenzvertrag
As scientific instruments and the literature generate ever larger volumes of data, machine learning (ML)has become essential for organizing, analyzing and interpreting complex information. This Perspectiveexamines how ML accelerates discovery across disciplines, with examples such as brain mapping andexoplanet detection. It also considers situations with different levels of prior knowledge about theunderlying phenomenon, outlining strategies to address limitations and exploit ML effectively.Although growing reliance on ML raises challenges for research practice and validation, it is reshapingscientific methods and expanding what can be studied. We also highlight foundation models as apromising route to faster, broader scientific discovery.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Review
Keywords Exploit ; Scientific Discovery ; Perspective (graphical) ; Key (lock) ; Foundation (evidence) ; Scientific Literature; Ai; Foundation; Symmetry; Models; Age
ISSN (print) / ISBN 2399-3650
e-ISSN 2399-3650
Journal Communications Physics
Quellenangaben Volume: 9, Issue: 1, Pages: , Article Number: 168 Supplement: ,
Publisher Springer
Publishing Place Heidelberger Platz 3, Berlin, 14197, Germany
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Royal Institute of Technology