Identifiable learning of dissipative dynamics
Researchers have developed a new neural network framework designed to analyze non-equilibrium dissipative systems in science and engineering. The method allows for the quantification of entropy production and irreversibility in complex data trajectories.
Why it matters
This advancement provides a new data-driven tool for understanding complex physical systems, potentially impacting fields from polymer science to machine learning.
Nature Communications ( 2026 ) Cite this article
We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in