OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kantamneni, Subhash, Liu, Ziming, Tegmark, Max
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914787861987328
author Kantamneni, Subhash
Liu, Ziming
Tegmark, Max
author_facet Kantamneni, Subhash
Liu, Ziming
Tegmark, Max
contents Integrable partial differential equation (PDE) systems are of great interest in natural science, but are exceedingly rare and difficult to discover. To solve this, we introduce OptPDE, a first-of-its-kind machine learning approach that Optimizes PDEs' coefficients to maximize their number of conserved quantities, $n_{\rm CQ}$, and thus discover new integrable systems. We discover four families of integrable PDEs, one of which was previously known, and three of which have at least one conserved quantity but are new to the literature to the best of our knowledge. We investigate more deeply the properties of one of these novel PDE families, $u_t = (u_x+a^2u_{xxx})^3$. Our paper offers a promising schema of AI-human collaboration for integrable system discovery: machine learning generates interpretable hypotheses for possible integrable systems, which human scientists can verify and analyze, to truly close the discovery loop.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04484
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration
Kantamneni, Subhash
Liu, Ziming
Tegmark, Max
Machine Learning
Computational Physics
Integrable partial differential equation (PDE) systems are of great interest in natural science, but are exceedingly rare and difficult to discover. To solve this, we introduce OptPDE, a first-of-its-kind machine learning approach that Optimizes PDEs' coefficients to maximize their number of conserved quantities, $n_{\rm CQ}$, and thus discover new integrable systems. We discover four families of integrable PDEs, one of which was previously known, and three of which have at least one conserved quantity but are new to the literature to the best of our knowledge. We investigate more deeply the properties of one of these novel PDE families, $u_t = (u_x+a^2u_{xxx})^3$. Our paper offers a promising schema of AI-human collaboration for integrable system discovery: machine learning generates interpretable hypotheses for possible integrable systems, which human scientists can verify and analyze, to truly close the discovery loop.
title OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2405.04484