PERSPECTIVE article
Front. Phys.
Sec. Interdisciplinary Physics
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1641727
This article is part of the Research TopicAI for Physics and Physics for AIView all articles
Is the end of Insight in sight?
Provisionally accepted
- 1Department of Engineering, Roma Tre University, Rome, Italy
- 2Istituto Italiano di Tecnologia Center for Life Nano- & Neuro-Science, Rome, Italy
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The rise of deep learning challenges the longstanding scientific ideal of insight—the human ability to understand phenomena by uncovering underlying mechanisms. From a physics perspective, we examine this tension through a case study: a physics-informed neural network (PINN) trained on rarefied gas dynamics governed by the Boltzmann equation. Despite strong physical constraints and a system with clear mechanistic structure, the trained network's weight distributions remain close to Gaussian, showing no coarse-grained signature of the underlying physics. This result contrasts with theoretical expectations that such networks might retain structural features akin to discrete dynamical systems. We argue that high predictive accuracy does not imply interpretable internal representations and that explainability in physics-informed AI may not always be achievable—or necessary. These findings highlight a growing divergence between models that predict well and those that offer insight.
Keywords: explainable artificial intelligence (XAI), Physics-informed neural networks (pinns), Interpretability, Boltzmann Equation, Rarefied Gas Dynamics, machine learning, random matrix theory
Received: 05 Jun 2025; Accepted: 16 Sep 2025.
Copyright: © 2025 Tucny, Durve and Succi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Jean-Michel Tucny, jeanmichel.tucny@uniroma3.it
Sauro Succi, sauro.succi@iit.it
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.