跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2607.23753 · v2

On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement

首次提交 2026-07-27 00:58
版本更新 2026-11-15 02:15
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

PDE discovery aims to identify from data the governing law of a physical system. Constituting a cornerstone of scientific advancement, it has become during the past decade a major line of research in the rapidly evolving field of Physics-informed Machine Learning (PiML). Among the open problems to address in this domain, the post-hoc evaluation of discovered PDEs raises the particular difficulty of being multifaceted. Indeed, it requires jointly considering predictive accuracy, physical consistency, interpretability, and out-of-distribution generalization capacity, some of these properties being conflicting. Drawing on an extensive body of literature spanning ML, numerical analysis and symbolic regression, we establish in this article that the overwhelming majority of papers address only certain aspects of the overall evaluation task. To better understand their limitations when used in isolation from the others, we propose the first taxonomy of PDE evaluation metrics. Through experiments conducted on several PDEs, we observe that limiting the scope of the evaluation can lead to overstated conclusions as well as changes in the ranking of the identified equations. For this reason, we provide recommendations with the aim of promoting standardized and reliable practices. This results in Pde-Check, a simple rules-based protocol to guide practitioners according to the scenario under consideration, including whether or not the ground truth equation is available (recovery or discovery), whether data is available beyond the training time frame and/or under varying initial conditions, or whether physical priors is available. We argue that this paper is intended both for ML experts who design new PDE discovery algorithms and for users of these methods aiming, in real applications, to discover and validate well-founded scientific laws.and validate well-founded scientific laws.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-15 02:15 · 最新观测版本

On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement

PDE discovery aims to identify from data the governing law of a physical system. Constituting a cornerstone of scientific advancement, it has become during the past decade a major line of research in the rapidly evolving field of Physics-informed Machine Learning (PiML). Among the open problems to address in this domain, the post-hoc evaluation of discovered PDEs raises the particular difficulty of being multifaceted. Indeed, it requires jointly considering predictive accuracy, physical consistency, interpretability, and out-of-distribution generalization capacity, some of these properties being conflicting. Drawing on an extensive body of literature spanning ML, numerical analysis and symbolic regression, we establish in this article that the overwhelming majority of papers address only certain aspects of the overall evaluation task. To better understand their limitations when used in isolation from the others, we propose the first taxonomy of PDE evaluation metrics. Through experiments conducted on several PDEs, we observe that limiting the scope of the evaluation can lead to overstated conclusions as well as changes in the ranking of the identified equations. For this reason, we provide recommendations with the aim of promoting standardized and reliable practices. This results in Pde-Check, a simple rules-based protocol to guide practitioners according to the scenario under consideration, including whether or not the ground truth equation is available (recovery or discovery), whether data is available beyond the training time frame and/or under varying initial conditions, or whether physical priors is available. We argue that this paper is intended both for ML experts who design new PDE discovery algorithms and for users of these methods aiming, in real applications, to discover and validate well-founded scientific laws.and validate well-founded scientific laws.

查看此版本解读 →查看此版本原文 ↗