Deep learning neural network potential for simulating gaseous adsorption in metal–organic frameworks. Issue 13 (7th June 2022)

• Record Type: Journal Article
• Authors: Yang, Chi-Ta; Pandey, Ishan; Trinh, Dan; Chen, Chau-Chyun; Howe, Joshua D.; Lin, Li-Chiang
• Is Part Of: Materials advances. Volume 3:Issue 13(2022)
• Page Start: 5299
• Page End: 5303
• Publication Date: 2022-06-07
• Subjects: 620.11
• DOI: 10.1039/d1ma01152a
• Languages: English
• ISSNs: 2633-5409

Abstract

Abstract : This study proposes ab initio neural network force fields with physically motivated features to offer superior accuracy in describing adsorbate–adsorbent interactions of nonpolar (CO2 ) and polar (H2 O and CO) molecules in metal–organic frameworks with open-metal sites. Abstract : This study proposes ab initio neural network force fields with physically motivated features to offer superior accuracy in describing adsorbate–adsorbent interactions of nonpolar (CO2 ) and polar (H2 O and CO) molecules in metal–organic frameworks with open-metal sites. Effects of the neural network architecture and features are also investigated for developing accurate models.