2026-10-14T05:34:01Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34034161 2026-09-30T17:10:54Z category_1 category_146 category_7 category_873 category_734 category_931 portal_63 item_type_6 month_year_09_2026

Efficient and Transferable Machine Learning Potentials for Zn-Coordinated Zeolitic Imidazolate Frameworks Through Structural Diversity Sampling and Transfer Learning Shang-Wei Lin (9240043) Yen-Yung Wu (25144936) Li-Chiang Lin (1394398) Biophysics Space Science Medicine Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified yet accurately describing significant computational challenge md simulations powered equivariant allegro architecture enable rapid adaptation dynamic behavior remains capture framework flexibility structural diversity sampling fewer training configurations improved accuracy using structural transition level accuracy additional configurations whereas first unseen topologies subnanosecond resolution smooth overlap prohibitively expensive principles methods magnitude larger limited number induced gate governs many functional properties first developed cost associated building upon atomic positions also established 8 using 016 ev Zeolitic Imidazolate Frameworks (ZIFs) exhibit remarkable structural flexibility that governs many of their functional properties, yet accurately describing their dynamic behavior remains a significant computational challenge. Classical force fields often fail to capture framework flexibility, whereas first-principles methods are prohibitively expensive. In this work, high-fidelity machine learning potentials (MLPs) are first developed for ZIF-8 using the equivariant Allegro architecture. To reduce the cost associated with the development of MLPs, an active-learning-inspired structural selection strategy based on the smooth overlap of atomic positions (SOAP) is implemented, allowing DFT-level accuracy to be achieved with fewer training configurations. Benchmarking against currently available models demonstrates that, while those models also offer reasonable energy predictions, their force errors remain 1 order of magnitude larger than the specialized MLP developed herein with a force mean absolute error of as small as 0.016 eV/Å. Building upon these findings, a transferable MLP spanning diverse Zn-based ZIFs is further constructed. Moreover, a hierarchical transfer learning workflow is also established to enable rapid adaptation to unseen topologies with improved accuracy using only a limited number of additional configurations. As a demonstration, MD simulations powered by the developed MLP successfully capture methane-induced gate-opening in ZIF-8, resolving the structural transition at subnanosecond resolution. Overall, this work provides a transferable, DFT-accurate machine learning force field for Zn-based ZIFs. 2026-09-30T00:00:00Z Text Journal contribution 10.1021/acs.jctc.6c01271.s002 https://figshare.com/articles/journal_contribution/Efficient_and_Transferable_Machine_Learning_Potentials_for_Zn-Coordinated_Zeolitic_Imidazolate_Frameworks_Through_Structural_Diversity_Sampling_and_Transfer_Learning/34034161 CC BY-NC 4.0