Jul 2026· Journal of Physical Chemistry Letters· Vol 17, pp. 8444-8450· 0 citations· 27 references
Medicine
TL;DR
A data-driven framework that integrates state-of-the-art synthesis parameters with solution physical properties derived from molecular simulations to predict zeolite crystallization outcomes is developed, showing that framework selection is encoded not only in chemical composition but also in emergent solution properties.
Abstract
Zeolites are essential crystalline materials for catalysis and molecular separations, yet their targeted synthesis remains challenging because framework selection is governed by coupled solution chemistry, organic structure-directing agents, solvent environments, and crystallization conditions. Here we develop a data-driven framework that integrates state-of-the-art synthesis parameters with solution physical properties derived from molecular simulations to predict zeolite crystallization outcomes. Across 366 literature syntheses, the model achieves 96.4% accuracy in classifying 20 zeolite frameworks and 87.7% accuracy in distinguishing four structural aperture classes, outperforming composition-only baselines. Model interpretation reveals that solution density and dielectric constant provide independent information, with opposite effects on the formation of small- and large-aperture zeolites. These findings show that framework selection is encoded not only in chemical composition but also in emergent solution properties, offering a physically informed strategy for predictive zeolite synthesis.
Zeolites are microporous crystalline materials with diverse frameworks, widely used in industrial applications such as petroleum refining and molecular separation. Unlike most zeolites, EMT can be synthesized under mild conditions (at low temperatures and without the use of organic structure-directing agents), making it attractive for cost-effective and environmentally sustainable production. However, the specific synthesis conditions that selectively produce EMT rather than similar frameworks like FAU are not yet well established. In this work, we develop machine learning (ML) models to guide the discovery of synthesis conditions for EMT zeolites. Our dataset comprises 174 experimental synthesis attempts, recording reaction time, temperature, silica and alumina sources, Si/Al stoichiometric ratio, and other synthesis parameters. We apply both classical ML methods and pretrained foundation models to predict zeolite framework outcomes from these synthesis parameters. Feature importance analysis identifies critical parameters for EMT formation, validating known synthesis principles. Leveraging the ML models, we explore the synthesis space and identify six promising new conditions for EMT formation. Experimental validation confirms EMT crystallization in five cases, including two with Si/Al stoichiometric ratios outside the training dataset's range. Evaluation on independent literature-reported synthesis conditions further demonstrates the generalizability of the model. This work demonstrates a data-driven approach to accelerating zeolite synthesis, closing the loop between ML prediction and experimental validation.
Emmanuel A. Olanrewaju, Santosh Adhikari, Zhiyin Niu et al.· PHYSICAL REVIEW MATERIALS· 0 citations
It is shown that explainable artificial intelligence (XAI) provides a transformative approach by connecting model predictions to interpreting chemical descriptors, structural motifs, and reaction features, and it is reshaping data-driven catalysis from opaque prediction toward mechanism-informed catalyst design.
Zixuan Geng, Di Wu, Xu Zhao et al.· Academia Catalysis· 0 citations
A mechanism-driven approach to alleviate data dependence and develop a multisource transfer learning (MS-TL) framework that leverages the knowledge embedded in abundant adsorption data sets while accurately capturing local structural dependence, enabling a deep fusion of multidimensional thermodynamic knowledge while preserving local structural information.
Wangqiang Lin, Huiyan Zhang, Jinxin Sun et al.· Journal of the American Chem...· 0 citations
CatDiT is presented, a unified framework for inverse catalyst design that generates valid and novel structures ranging from intermetallic alloys to oxide surfaces and establishes CatDiT as a practical and scalable approach for property-directed catalyst inverse design and targeted catalyst generation.
Hayoung Doo, Dong Hyeon Mok, S. Back et al.· 0 citations
Despite extensive investigation of metal-organic framework (MOF) derived materials over the last 20 years, no systematic approach to predict the structural properties of the derived metal oxides is available. We present an integrated machine learning (ML) approach leveraging Smooth Overlap of Atomic Positions (SOAP) and multiple ML models, including Kernel Ridge Regression (KRR), to predict thermally derived zirconium dioxide (ZrO2) polymorph from diverse Zr-based precursors. By a systematic experimental dataset of calcination parameters, we train the ML model to quantitatively forecast material properties and the weight fraction of crystalline phases of the resulting ZrO2. Experimental validation of model predictions confirms that the chemical composition of precursors and calcination parameters have a profound influence on the crystallinity of MOF-derived ZrO2 polymorph. Our findings demonstrate the utility of small-data-driven predictive ML modeling and transfer learning for guiding the synthesis of advanced oxide materials providing a blueprint for accelerated discovery of MOF-derived nanomaterials.
David Gryc, I. Kouroudis, Pritam Banerjee et al.· npj Computational Materials· 0 citations
Epoxy polymers are widely used due to their multifunctional properties, however their complex 3D molecular structure, multi-component nature, and lack of curated datasets have limited the application of machine learning (ML) for these materials.Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an Informed Regression-based Knowledge Distillation (R-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, flexural strength, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 37 hardeners). The best-performing single-task regression model per target property serves as teacher model capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. Comparative analysis demonstrates superior or comparable prediction accuracy over multi-task NN baseline model and conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.
B. Sindu, J. Hamaekers· Scientific Reports· 0 citations