Scholarlink

<p>Uncertainty quantification (UQ) to detect samples with large expected errors (outliers) is applied to reactive molecular potential energy surfaces (PESs). Three methods–Ensembles, deep evidential regression (DER), and Gaussian Mixture Models (GMM)—were applied to the H-transfer reaction between <i>syn</i>-Criegee and vinyl hydroxyperoxide. The results indicate that ensemble models provide the best results for detecting outliers, followed by GMM. For example, from a pool of 1000 structures with the largest uncertainty, the detection quality for outliers is ~90% and ~50%, respectively, if 25 or 1000 structures with large errors are sought. On the contrary, the limitations of the statistical assumptions of DER greatly impact its prediction capabilities. Finally, a structure-based indicator was found to be correlated with large average error, which may help to rapidly classify new structures into those that provide an advantage for refining the neural network.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Outlier-detection for reactive machine learned potential energy surfaces

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月15日

查看全文
  • Luis Itza Vazquez-Salazar,
  • Silvan Käser,
  • Markus Meuwly

摘要

Uncertainty quantification (UQ) to detect samples with large expected errors (outliers) is applied to reactive molecular potential energy surfaces (PESs). Three methods–Ensembles, deep evidential regression (DER), and Gaussian Mixture Models (GMM)—were applied to the H-transfer reaction between syn-Criegee and vinyl hydroxyperoxide. The results indicate that ensemble models provide the best results for detecting outliers, followed by GMM. For example, from a pool of 1000 structures with the largest uncertainty, the detection quality for outliers is ~90% and ~50%, respectively, if 25 or 1000 structures with large errors are sought. On the contrary, the limitations of the statistical assumptions of DER greatly impact its prediction capabilities. Finally, a structure-based indicator was found to be correlated with large average error, which may help to rapidly classify new structures into those that provide an advantage for refining the neural network.