Zeolite Adsorption Isotherms Predicted by Pore Channel and Local Environmental Descriptors: Feature Learning on DFT Binding Strength

Abstract

Fast prediction of adsorption isotherms is of great importance in the structural characterization and property prediction of zeolites prior to the synthesis of the target zeolite. Here, we employ the feature learning (FL) method to simulate the adsorption isotherms through density functional theory data generation of binding strength of nitrogen molecule adsorption in zeolites. Three features, that is, the size of adsorption cavities, the geometry of the pore apertures, and the local geometric distortion, are identified to control the binding strength, qualitatively in terms of a polynomial generative model. The local distortion of the Si–O–Si linkage is correlated with the electrostatic polarization of the nitrogen molecule upon adsorption in the zeolite cage. The electrostatic polarization from local zeolite environment can be further adjusted by the Si/Al ratios and thus can enhance the binding strength even twice as the silicalite zeolites when Si/Al = 47. The predicted adsorption isotherms of MFI and MWW zeolites from the feature-learned binding energies are in qualitative agreement with the experimental Brunauer–Emmett–Teller detection data. For 200,429 zeolites, including 248 known zeolites reported in the International Zeolite Association (IZA), the predicted adsorption isotherms are classified into three groups, among which the zeolites with the medium-sized three-dimensional channel architectures are favorable for nitrogen adsorption. The proposed FL scheme is a practical tool to give a quick prediction of adsorption isotherms and high-throughput screening of porous materials for adsorption-related applications.

Nitrogen reduction reaction energy and pathways in metal-zeolites: deep learning and explainable machine learning with local acidity and hydrogen bonding features

“…[49][50][51][52] It has been demonstrated by our group that R DLS is one of the three important features in predicting nitrogen adsorption strength in 200 429 kinds of siliceous zeolites. 29 Here, we found that R DLS gets larger to about 0.067-0.194 in metal-zeolites than that (0.005) in siliceous zeolites due to the signicant perturbation of the zeolite framework upon coordination with metal atoms. Among all the studied systems, the introduction of Pb atoms leads to the least distortion of the zeolite framework with R DLS ¼ 0.067, due to the weak coordination strength between Pb and O atoms with distances of about 2.35-2.86 Å.…”

“…The theoretical data of metal-zeolites contained 4428 geometry-related data, 5412 electronic-structure-related data, and 1968 reaction-related data for 492 structures with 27 metal elements, as shown in Table S2 †. As the first step of nitrogen activation, the nitrogen adsorption in various zeolites along with three features, 29 including effective adsorption space ( V eff ), pore largest diameter (PLD), and Si–O–Si refinement distance least squares ( R DLS ), is also collected in the ZA dataset.…”

“…due to their large surface area, tunable active sites, remarkable stability, and low production cost of molecular sieves. [23][24][25][26][27][28] Specically, zeolites with mediumsized 3D channel architectures were favorable for N 2 adsorption, 29 which is the rst step in the NRR (Fig. 1).…”

“…Some explainable machine learning (ML) models have been used to predict the mechanical and adsorption properties of zeolites via geometrical features such as the local distortion (R DLS ), Si-O bond length, and Si-O-Si bond angle. 29,33 The CO 2 / N 2 selectivity in porous carbons has been predicted by using deep learning via their textural features (micropore volume, mesopore volume, and BET surface area) and adsorption isotherms. 34,35 Introducing more mesopores in porous carbons could decrease the adsorption of N 2 and benet CO 2 capture, showing the importance of hierarchical pore structures in gas separation.…”

Regression Machine Learning Models Used to Predict DFT-Computed NMR Parameters of Zeolites

“…The three-dimensional zeolite structure is composed by tetrahedron units with Si atoms in the centre and four oxygen atoms at the vertices, which can organise in a variety of porous frameworks, with pores of sizes varying between 2 and 10 nm [27,28]. ML methods coupled to DFT computations have already emerged for predicting mechanical properties [29], nitrogen adsorption [30], molar volumes, and cohesive energies [31] in zeolites. The success rate of these ML applications to zeolites vary according to the predicted properties and the proposed ML approach [32].…”