Machine Learning-Based Predicting of the Equilibrium Cation Distribution in Faujasite-Type Zeolites | Sciact - CRIS-система Института катализа

Machine Learning-Based Predicting of the Equilibrium Cation Distribution in Faujasite-Type Zeolites Научная публикация

Журнал

Materials Chemistry and Physics
ISSN: 0254-0584 , E-ISSN: 1879-3312

Вых. Данные

Год: 2026, Том: 349, Номер: Part 2, Номер статьи : 131853, Страниц : 11 DOI: 10.1016/j.matchemphys.2025.131853

Ключевые слова

Zeolites; FAU; Cation distribution; Database; Replica-exchange Monte Carlo; Force field

Авторы

Grenev Ivan V. ^1,2 , Bobkov Matvey E. ^1,2 , Ivanov Anton D. ^1,2 , Uliankina Anastasiia I. ^1,3 , Shubin Aleksandr A. ^1,4

Организации

1	Boreskov Institute of Catalysis, Ac. Lavrentiev av. 5, Novosibirsk, 630090, Russia
2	Novosibirsk State University, Pirogova str. 1, Novosibirsk, 630090, Russia
3	Omsk State Technical University, Mira str. 11, Omsk, 644050, Russia
4	Institute of Solid State Chemistry and Mechanochemistry, Kutateladze str. 18, 630090 Novosibirsk, Russia

Информация о финансировании (1)

Российский научный фонд

24-71-10096

A surrogate predictive model for estimating the cationic site occupancy in faujasite-type (FAU) zeolites based on their chemical composition is presented. First, a reference experimental database containing structural data for 108 dehydrated FAU zeolites was compiled from literature sources. A quantitative criterion was introduced to assess the applicability of models predicting cationic site occupancy in reference zeolite frameworks. The canonical replica-exchange Monte Carlo method was used to generate a training data set. The best agreement between the simulated and experimental cationic site occupancies was achieved using a custom zeolite framework model with randomly distributed Al atoms and an extended DFT/CC-derived force field model. A set of descriptors was developed to translate the chemical composition of zeolite adsorbents into numerical parameters for modeling. The machine-learning surrogate model was trained on a simulation-derived database containing cation site occupancies for 250 monocationic and 3962 bicationic FAU zeolites generated using replica-exchange Monte Carlo simulations. Since surrogate predictive models are not limited by a set of force field parameters, they can be used to predict the cationic site occupancies in zeolites for a wide range of cations. The predictive ability of the surrogate model was demonstrated for a set of FAU zeolite frameworks from the reference database.

Grenev I.V. , Bobkov M.E. , Ivanov A.D. , Uliankina A.I. , Shubin A.A.
Machine Learning-Based Predicting of the Equilibrium Cation Distribution in Faujasite-Type Zeolites
Materials Chemistry and Physics. 2026. V.349. NPart 2. 131853 :1-11. DOI: 10.1016/j.matchemphys.2025.131853

Поступила в редакцию:	5 авг. 2025 г.
Принята к публикации:	26 нояб. 2025 г.
Опубликована online:	29 нояб. 2025 г.
Опубликована в печати:	1 февр. 2026 г.

Нет идентификаторов

Пока нет цитирований