Outlier-detection for reactive machine learned potential energy surfaces.

• Tác giả: Silvan Käser, Markus Meuwly, Luis Itza Vazquez-Salazar
• Ngôn ngữ: eng
• Ký hiệu phân loại: 025.347 *Pictures and materials for projection
• Thông tin xuất bản: England : npj computational materials , 2025
• Bộ sưu tập: NCBI
• ID: 185387

Tóm tắt

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