Linking synthesis and structure descriptors from a large collection of synthetic records of zeolite materials

How to accelerate the inorganic materials synthesis: from computational guidelines to data-driven method?

The development of novel functional materials has attracted widespread attention to meet the constantly growing demand for addressing the major global challenges facing humanity, among which experimental synthesis emerges as one of the crucial challenges. Understanding the synthesis processes and predicting the outcomes of synthesis experiments are essential for increasing the success rate of experiments. With the advancements in computational power and the emergence of machine learning (ML) techniques, computational guidelines and data-driven methods have significantly contributed to accelerating and optimizing material synthesis. Herein, a review of the latest progress on the computation-guided and ML-assisted inorganic material synthesis is presented. First, common synthesis methods for inorganic materials are introduced, followed by a discussion of physical models based on thermodynamics and kinetics, which are relevant to the synthesis feasibility of inorganic materials. Second, data acquisition, commonly utilized material descriptors, and ML techniques in ML-assisted inorganic material synthesis are discussed. Third, applications of ML techniques in inorganic material synthesis are presented, which are classified according to different material data sources. Finally, we highlight the crucial challenges and promising opportunities for ML-assisted inorganic materials synthesis. This review aims to provide critical scientific guidance for future advancements in ML-assisted inorganic materials synthesis.

Integrating Enzymes with Reticular Frameworks To Govern Biocatalysis

Integrating enzymes with reticular frameworks offers promising avenues for access to functionally tailorable biocatalysis. This Minireview explores recent advances in enzyme-reticular framework hybrid biocomposites, focusing on the utilization of porous reticular frameworks, including metal-organic frameworks, covalent-organic frameworks, and hydrogen-bonded organic frameworks, to regulate the reactivity of an enzyme encapsulated inside mainly by pore infiltration and in situ encapsulation strategies. We highlight how pore engineering and host-guest interfacial interactions within reticular frameworks create tailored microenvironments that substantially impact the mass transfer and enzyme conformation, leading to biocatalytic rate enhancement, or imparting enzymes with non-native biocatalytic functions, including substrate selectivity and new activity. Additionally, the feasibility of leveraging the photothermal effect of a framework to optimize the local reaction temperature and photoelectric effect to elicit diverse photoenzyme-coupled reactions is also summarized in detail, which can expand the functional repertoire of biocatalytic transformations under light irradiation. This Minireview underscores the potential of reticular frameworks as tunable and reliable platforms to govern biocatalysis, offering pathways for engineering sustainable, efficient, and selective biocatalytic reactors in pharmaceutical, environmental, and energy-related applications.

Interpretable Machine Learning Model for Predicting Postpartum Depression: Retrospective Study

Background

Postpartum depression (PPD) is a prevalent mental health issue with significant impacts on mothers and families. Exploring reliable predictors is crucial for the early and accurate prediction of PPD, which remains challenging.

Objective

This study aimed to comprehensively collect variables from multiple aspects, develop and validate machine learning models to achieve precise prediction of PPD, and interpret the model to reveal clinical implications.

Methods

This study recruited pregnant women who delivered at the West China Second University Hospital, Sichuan University. Various variables were collected from electronic medical record data and screened using least absolute shrinkage and selection operator penalty regression. Participants were divided into training (1358/2055, 66.1%) and validation (697/2055, 33.9%) sets by random sampling. Machine learning-based predictive models were developed in the training cohort. Models were validated in the validation cohort with receiver operating curve and decision curve analysis. Multiple model interpretation methods were implemented to explain the optimal model.

Results

We recruited 2055 participants in this study. The extreme gradient boosting model was the optimal predictive model with the area under the receiver operating curve of 0.849. Shapley Additive Explanation indicated that the most influential predictors of PPD were antepartum depression, lower fetal weight, elevated thyroid-stimulating hormone, declined thyroid peroxidase antibodies, elevated serum ferritin, and older age.

Conclusions

This study developed and validated a machine learning-based predictive model for PPD. Several significant risk factors and how they impact the prediction of PPD were revealed. These findings provide new insights into the early screening of individuals with high risk for PPD, emphasizing the need for comprehensive screening approaches that include both physiological and psychological factors.

Analyzing dissemination, quality, and reliability of Chinese brain tumor-related short videos on TikTok and Bilibili: a cross-sectional study

Background

As the Internet becomes an increasingly vital source of medical information, the quality and reliability of brain tumor-related short videos on platforms such as TikTok and Bilibili have not been adequately evaluated. Therefore, this study aims to assess these aspects and explore the factors influencing the dissemination of such videos.

Methods

A cross-sectional analysis was conducted on the top 100 brain tumor-related short videos from TikTok and Bilibili. The videos were evaluated using the Global Quality Score and the DISCERN reliability instrument. An eXtreme Gradient Boosting algorithm was utilized to predict dissemination outcomes. The videos were also categorized by content type and uploader.

Results

TikTok videos scored relatively higher on both the Global Quality Score (median 2, interquartile range [2, 3] on TikTok vs. median 2, interquartile range [1, 2] on Bilibili, p = 1.51E-04) and the DISCERN reliability instrument (median 15, interquartile range [13, 18.25] on TikTok vs. 13.5, interquartile range [11, 16] on Bilibili, p = 1.66E-04). Subgroup analysis revealed that videos uploaded by professional individuals and institutions had higher quality and reliability compared to those uploaded by non-professional entities. Videos focusing on disease knowledge exhibited the highest quality and reliability compared to other content types. The number of followers emerged as the most important variable in our dissemination prediction model.

Conclusion

The overall quality and reliability of brain tumor-related short videos on TikTok and Bilibili were unsatisfactory and did not significantly influence video dissemination. Future research should expand the scope to better understand the factors driving the dissemination of medical-themed videos.

Advances and challenges in designing active site environments in zeolites for Brønsted acid catalysis

Zeolites contain proton active sites in diverse void environments that stabilize the reactive intermediates and transition states formed in converting hydrocarbons and oxygenates to chemicals and energy carriers. The catalytic diversity that exists among active sites in voids of varying sizes and shapes, even within a given zeolite topology, has motivated research efforts to position and quantify active sites within distinct voids (synthesis-structure) and to link active site environment to catalytic behavior (structure-reactivity). This Feature Article describes advances and challenges in controlling the position of framework Al centers and associated protons within distinct voids during zeolite synthesis or post-synthetic modification, in identifying and quantifying distinct active site environments using characterization techniques, and in determining the influence of active site environments on catalysis. During zeolite synthesis, organic structure directing agents (SDAs) influence Al substitution at distinct lattice positions via intermolecular interactions (e.g., electrostatics, hydrogen bonding) that depend on the size, structure, and charge distribution of organic SDAs and their mobility when confined within zeolitic voids. Complementary post-synthetic strategies to alter intrapore active site distributions include the selective removal of protons by differently-sized titrants or unreactive organic residues and the selective exchange of framework heteroatoms of different reactivities, but remain limited to certain zeolite frameworks. The ability to identify and quantify active sites within distinct intrapore environments depends on the resolution with which a given characterization technique can distinguish Al T-site positions or proton environments in a given zeolite framework. For proton sites in external unconfined environments, various (post-)synthetic strategies exist to control their amounts, with quantitative methods to distinguish them from internal sites that largely depend on using stoichiometric or catalytic probes that only interact with external sites. Protons in different environments influence reactivity by preferentially stabilizing larger transition states over smaller precursor states and influence selectivity by preferentially stabilizing or destabilizing competing transition states of varying sizes that share a common precursor state. We highlight opportunities to address challenges encountered in the design of active site environments in zeolites by closely integrating precise (post-)synthetic methods, validated characterization techniques, well-defined kinetic probes, and properly calibrated theoretical models. Further advances in understanding the molecular details that underlie synthesis-structure-reactivity relationships for active site environments in zeolite catalysis can accelerate the predictive design of tailored zeolites for desired catalytic transformations.

Self-Driving Laboratories for Chemistry and Materials Science

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

Predicting the binding configuration and release potential of heavy metals on iron (oxyhydr)oxides: A machine learning study on EXAFS

Heavy metals raise a global concern and can be easily retained by ubiquitous iron (oxyhydr)oxides in natural and engineered systems. The complex interaction between iron (oxyhydr)oxides and heavy metals results in various mineral-metal binding configurations, such as outer-sphere complexes and edge-sharing inner-sphere complexes, which determine the accumulation and release of heavy metals in the environment. However, traditional experimental approaches are time-consuming and inadequate to elucidate the complex binding relationships and configurations between iron (oxyhydr)oxides and heavy metals. Herein, a workflow that integrates the binding configuration data of 11 heavy metals on 7 iron (oxyhydr)oxides and then trains machine learning models to predict unknown binding configurations was proposed. The well-trained multi-grained cascade forest models exhibited high accuracy (> 90%) and predictive performance (R2 ∼ 0.75). The underlying effects of mineral properties, metal ion species, and environmental conditions on mineral-metal binding configurations were fully interpreted with data mining. Moreover, the metal release rate was further successfully predicted based on mineral-metal binding configurations. This work provides a method to accurately and quickly predict the binding configuration of heavy metals on iron (oxyhydr)oxides, which would provide guidance for estimating the potential release behavior of heavy metals and remediating heavy metal pollution in natural and engineered environments.

Opinion Mining by Convolutional Neural Networks for Maximizing Discoverability of Nanomaterials

The scientific literature contains valuable information that can be used for future applications, but manual analysis presents challenges due to its size and disciplinary boundaries. The prevailing solution involves natural language processing (NLP) techniques such as information retrieval. Nonetheless, existing automated systems primarily provide either statistically based shallow information or deep information without traceability, thereby falling short of delivering high-quality and reliable insights. To address this, we propose an innovative approach of leveraging sentiment information embedded within the literature to track the opinions toward materials. In this study, we integrated material knowledge into text representation and constructed opinion data sets to hierarchically train deep learning models, named as Scientific Sentiment Network (SSNet). SSNet can effectively extract knowledge from the energy material literature and accurately categorize expert opinions into challenges and opportunities (94% and 92% accuracy, respectively). By incorporating sentiment features determined by SSNet, we can predict the ranking of emerging thermoelectric materials with a 70% correlation to experimental outcomes. Furthermore, our model achieves a commendable 68% accuracy in predicting suitable nanomaterials for atomic layer deposition (ALD) over time. These promising results offer a practical framework to extract and synthesize knowledge from the scientific literature, thereby accelerating research in the field of nanomaterials.

The Current Understanding of Mechanistic Pathways in Zeolite Crystallization

Zeolite catalysts and adsorbents have been an integral part of many commercial processes and are projected to play a significant role in emerging technologies to address the changing energy and environmental landscapes. The ability to rationally design zeolites with tailored properties relies on a fundamental understanding of crystallization pathways to strategically manipulate processes of nucleation and growth. The complexity of zeolite growth media engenders a diversity of crystallization mechanisms that can manifest at different synthesis stages. In this review, we discuss the current understanding of classical and nonclassical pathways associated with the formation of (alumino)silicate zeolites. We begin with a brief overview of zeolite history and seminal advancements, followed by a comprehensive discussion of different classes of zeolite precursors with respect to their methods of assembly and physicochemical properties. The following two sections provide detailed discussions of nucleation and growth pathways wherein we emphasize general trends and highlight specific observations for select zeolite framework types. We then close with conclusions and future outlook to summarize key hypotheses, current knowledge gaps, and potential opportunities to guide zeolite synthesis toward a more exact science.

ZeoSyn: A Comprehensive Zeolite Synthesis Dataset Enabling Machine-Learning Rationalization of Hydrothermal Parameters

Zeolites, nanoporous aluminosilicates with well-defined porous structures, are versatile materials with applications in catalysis, gas separation, and ion exchange. Hydrothermal synthesis is widely used for zeolite production, offering control over composition, crystallinity, and pore size. However, the intricate interplay of synthesis parameters necessitates a comprehensive understanding of synthesis-structure relationships to optimize the synthesis process. Hitherto, public zeolite synthesis databases only contain a subset of parameters and are small in scale, comprising up to a few thousand synthesis routes. We present ZeoSyn, a dataset of 23,961 zeolite hydrothermal synthesis routes, encompassing 233 zeolite topologies and 921 organic structure-directing agents (OSDAs). Each synthesis route comprises comprehensive synthesis parameters: 1) gel composition, 2) reaction conditions, 3) OSDAs, and 4) zeolite products. Using ZeoSyn, we develop a machine learning classifier to predict the resultant zeolite given a synthesis route with >70% accuracy. We employ SHapley Additive exPlanations (SHAP) to uncover key synthesis parameters for >200 zeolite frameworks. We introduce an aggregation approach to extend SHAP to all building units. We demonstrate applications of this approach to phase-selective and intergrowth synthesis. This comprehensive analysis illuminates the synthesis parameters pivotal in driving zeolite crystallization, offering the potential to guide the synthesis of desired zeolites. The dataset is available at https://github.com/eltonpan/zeosyn_dataset.

Spherical Binderless 4A/5A Zeolite Assemblies: Synthesis, Characterization, and Adsorbent Applications

Zeolite microspheres have been successfully applied in commercial-scale separators such as oxygen concentrators. However, further enhancement of their applications is hampered by the post-synthetic shaping process that formulates the zeolite powder into packing-sized spherical bodies with various binders leading to active site blockage and suboptimal performance. Herein, binderless zeolite microspheres with a tunable broad size range from 2 µm to 500 µm have been developed with high crystallinity, sphericity over 92%, monodispersity with a coefficient of variation (CV) less than 5%, and hierarchical pore architecture. Combining precursor impregnation and steam-assisted crystallization (SAC), mesoporous silica microspheres with a wide size range could be successfully transformed into zeolite. For preserved size and spherical morphology, a judicious selection of the synthesis conditions is crucial to ensure a pure phase, high crystallinity, and hierarchical architecture. For the sub-2-µm zeolite microsphere, low-temperature prolonged aging was important so as to suppress external zeolization that led to a large, single macroporous crystal. For the large 500 µm sphere, ultrasound pretreatment and vacuum impregnation were crucial and facilitated spatially uniform gel matrix dispersion and homogenous crystallization. The obtained zeolite 5A microspheres exhibited excellent air separation performance, while the 4A microspheres displayed ammonium removal capabilities. This work provides a general strategy to overcome the existing limitations in fabricating binder-free technical bodies of zeolites for various applications.

Prediction of heavy-section ductile iron fracture toughness based on machine learning

The preparation process and composition design of heavy-section ductile iron are the key factors affecting its fracture toughness. These factors are challenging to address due to the long casting cycle, high cost and complex influencing factors of this type of iron. In this paper, 18 cubic physical simulation test blocks with 400 mm wall thickness were prepared by adjusting the C, Si and Mn contents in heavy-section ductile iron using a homemade physical simulation casting system. Four locations with different cooling rates were selected for each specimen, and 72 specimens with different compositions and cooling times of the heavy-section ductile iron were prepared. Six machine learning-based heavy-section ductile iron fracture toughness predictive models were constructed based on measured data with the C content, Si content, Mn content and cooling rate as input data and the fracture toughness as the output data. The experimental results showed that the constructed bagging model has high accuracy in predicting the fracture toughness of heavy-section ductile iron, with a coefficient of coefficient (R2) of 0.9990 and a root mean square error (RMSE) of 0.2373.

Machine learning-assisted crystal engineering of a zeolite

It is shown that Machine Learning (ML) algorithms can usefully capture the effect of crystallization composition and conditions (inputs) on key microstructural characteristics (outputs) of faujasite type zeolites (structure types FAU, EMT, and their intergrowths), which are widely used zeolite catalysts and adsorbents. The utility of ML (in particular, Geometric Harmonics) toward learning input-output relationships of interest is demonstrated, and a comparison with Neural Networks and Gaussian Process Regression, as alternative approaches, is provided. Through ML, synthesis conditions were identified to enhance the Si/Al ratio of high purity FAU zeolite to the hitherto highest level (i.e., Si/Al = 3.5) achieved via direct (not seeded), and organic structure-directing-agent-free synthesis from sodium aluminosilicate sols. The analysis of the ML algorithms' results offers the insight that reduced Na₂O content is key to formulating FAU materials with high Si/Al ratio. An acid catalyst prepared by partial ion exchange of the high-Si/Al-ratio FAU (Si/Al = 3.5) exhibits improved proton reactivity (as well as specific activity, per unit mass of catalyst) in propane cracking and dehydrogenation compared to the catalyst prepared from the previously reported highest Si/Al ratio (Si/Al = 2.8).

Machine Learning in the Development of Adsorbents for Clean Energy Application and Greenhouse Gas Capture

Addressing climate change challenges by reducing greenhouse gas levels requires innovative adsorbent materials for clean energy applications. Recent progress in machine learning has stimulated technological breakthroughs in the discovery, design, and deployment of materials with potential for high-performance and low-cost clean energy applications. This review summarizes basic machine learning methods-data collection, featurization, model generation, and model evaluation-and reviews their use in the development of robust adsorbent materials. Key case studies are provided where these methods are used to accelerate adsorbent materials design and discovery, optimize synthesis conditions, and understand complex feature-property relationships. The review provides a concise resource for researchers wishing to use machine learning methods to rapidly develop effective adsorbent materials with a positive impact on the environment.

The positive energy of netizens: development and application of fine-grained sentiment lexicon and emotional intensity model

The outbreak of COVID-19 has led to a global health crisis and caused huge emotional swings. However, the positive emotional expressions, like self-confidence, optimism, and praise, that appear in Chinese social networks are rarely explored by researchers. This study aims to analyze the characteristics of netizens' positive energy expressions and the impact of node events on public emotional expression during the COVID-19 pandemic. First, a total of 6,525,249 Chinese texts posted by Sina Weibo users were randomly selected through textual data cleaning and word segmentation for corpus construction. A fine-grained sentiment lexicon that contained POSITIVE ENERGY was built using Word2Vec technology; this lexicon was later used to conduct sentiment category analysis on original posts. Next, through manual labeling and multi-classification machine learning model construction, four mainstream machine learning algorithms were selected to train the emotional intensity model. Finally, the lexicon and optimized emotional intensity model were used to analyze the emotional expressions of Chinese netizens. The results show that POSITIVE ENERGY expression accounted for 40.97% during the COVID-19 pandemic. Over the course of time, POSITIVE ENERGY emotions were displayed at the highest levels and SURPRISES the lowest. The analysis results of the node events showed after the outbreak was confirmed officially, the expressions of POSITIVE ENERGY and FEAR increased simultaneously. After the initial victory in pandemic prevention and control, the expression of POSITIVE ENERGY and SAD reached a peak, while the increase of SAD was the most prominent. The fine-grained sentiment lexicon, which includes a POSITIVE ENERGY category, demonstrated reliable algorithm performance and can be used for sentiment classification of Chinese Internet context. We also found many POSITIVE ENERGY expressions in Chinese online social platforms which are proven to be significantly affected by nod events of different nature.

Optimal machine learning feature selection for assessing the mechanical properties of a zeolite framework

In this study, 45 and 249 critical features were discovered among 896 zeolite descriptors generated by the matminer package for estimating the shear and bulk moduli of zeolites, respectively. A database containing the mechanical properties of 873 zeolite structures, calculated using density functional theory, was used to train the machine learning regression model. The results of using these critical features with the LightGBM algorithm were rigorously compared with those from other regressors as well as with different sets of features. The comparison results indicate that the surrogate model with critical features increases the prediction accuracy of the bulk and shear moduli of zeolites by 17.3% and 10.6%, respectively, and reduces the prediction uncertainty by one-third of that achieved using previously available features. The suggested features originating from several physical and chemical groups highlight the unveiled relationships between the features and mechanical properties of zeolites. The robustness of the constructed model with 356 features was confirmed by applying a set of different training-test set ratios. We believe that the suggested critical features of zeolites can help to understand the mechanical behavior of a half million unlabeled hypothetical zeolite structures and accelerate the discovery of novel zeolites with unprecedented mechanical properties.

Data-driven efficient synthetic exploration of anionic lanthanide-based metal-organic frameworks

The synthesis of lanthanide metal-organic frameworks with terephthalate (Ln-BDC-MOFs) was investigated using a data-driven approach. Visually mapping the previously reported synthetic conditions suggested the existence of unexplored search spaces for novel Ln-BDC-MOFs. By focusing on the unexplored chemical reaction space, we successfully synthesized a series of new anionic Ln-BDC-MOFs, KGF-15, which demonstrated potential as luminescent sensors for Cu²⁺ ions. This synthetic exploration approach can significantly reduce the experimental effort required to discover new materials.

Synthesis of Zeolites from Fine-Grained Perlite and Their Application as Sorbents

The hydrothermal alteration of perlite into zeolites was studied using a two-step approach. Firstly, perlite powder was transformed into Na-P1 (GIS) or hydro(xy)sodalite (SOD) zeolites at 100 °C and 24 h using 2 or 5 M NaOH solutions. Secondly, the Si:Al molar ratio of the reacted Si-rich solution was adjusted to 1 by Na-aluminate addition to produce zeolite A (LTA) at 65 or 95 °C and 6 or 24 h at an efficiency of 90 ± 9% for Al and 93 ± 6% for Si conversion. The performance of these zeolites for metal ion removal and water softening applications was assessed by sorption experiments using an artificial waste solution containing 4 mmol/L of metal ions (Me²⁺: Ca²⁺, Mg²⁺, Ba²⁺ and Zn²⁺) and local tap water (2.1 mmol/L Ca²⁺ and 0.6 mmol/L Mg²⁺) at 25 °C. The removal capacity of the LTA-zeolite ranged from 2.69 to 2.86 mmol/g for Me²⁺ (=240–275 mg/g), which is similar to commercial zeolite A (2.73 mmol/g) and GIS-zeolite (2.69 mmol/g), and significantly higher compared to the perlite powder (0.56 mmol/g) and SOD-zeolite (0.88 mmol/g). The best-performing LTA-zeolite removed 99.8% Ca²⁺ and 93.4% Mg²⁺ from tap water. Our results demonstrate the applicability of the LTA-zeolites from perlite for water treatment and softening applications.

Machine Learning at the Interface of Polymer Science and Biology: How Far Can We Go?

This Perspective outlines recent progress and future directions for using machine learning (ML), a data-driven method, to address critical questions in the design, synthesis, processing, and characterization of biomacromolecules. The achievement of these tasks requires the navigation of vast and complex chemical and biological spaces, difficult to accomplish with reasonable speed. Using modern algorithms and supercomputers, quantum physics methods are able to examine systems containing a few hundred interacting species and determine the probability of finding them in a particular region of phase space, thereby anticipating their properties. Likewise, modern approaches in chemistry and biomolecular simulation, supported by high performance computing, have culminated in producing data sets of escalating size and intrinsically high complexity. Hence, using ML to extract relevant information from these fields is of paramount importance to advance our understanding of chemical and biomolecular systems. At the heart of ML approaches lie statistical algorithms, which by evaluating a portion of a given data set, identify, learn, and manipulate the underlying rules that govern the whole data set. The assembly of a quality model to represent the data followed by the predictions and elimination of error sources are the key steps in ML. In addition to a growing infrastructure of ML tools to address complex problems, an increasing number of aspects related to our understanding of the fundamental properties of biomacromolecules are exposed to ML. These fields, including those residing at the interface of polymer science and biology (i.e., structure determination, de novo design, folding, and dynamics), strive to adopt and take advantage of the transformative power offered by approaches in the ML domain, which clearly has the potential of accelerating research in the field of biomacromolecules.

Material Evolution with Nanotechnology, Nanoarchitectonics, and Materials Informatics: What will be the Next Paradigm Shift in Nanoporous Materials?

Materials science and chemistry have played a central and significant role in advancing society. With the shift toward sustainable living, it is anticipated that the development of functional materials will continue to be vital for sustaining life on our planet. In the recent decades, rapid progress has been made in materials science and chemistry owing to the advances in experimental, analytical, and computational methods, thereby producing several novel and useful materials. However, most problems in material development are highly complex. Here, the best strategy for the development of functional materials via the implementation of three key concepts is discussed: nanotechnology as a game changer, nanoarchitectonics as an integrator, and materials informatics as a super-accelerator. Discussions from conceptual viewpoints and example recent developments, chiefly focused on nanoporous materials, are presented. It is anticipated that coupling these three strategies together will open advanced routes for the swift design and exploratory search of functional materials truly useful for solving real-world problems. These novel strategies will result in the evolution of nanoporous functional materials.

Controlling Nucleation Pathways in Zeolite Crystallization: Seeding Conceptual Methodologies for Advanced Materials Design

A core objective of synthesizing zeolites for widespread applications is to produce materials with properties and corresponding performances that exceed conventional counterparts. This places an impetus on elucidating and controlling processes of crystallization where one of the most critical design criteria is the ability to prepare zeolite crystals with ultrasmall dimensions to mitigate the deleterious effects of mass transport limitations. At the most fundamental level, this requires a comprehensive understanding of nucleation to address this ubiquitous materials gap. This Perspective highlights recent methodologies to alter zeolite nucleation by using seed-assisted protocols and the exploitation of interzeolite transformations to design advanced materials. Introduction of crystalline seeds in complex growth media used to synthesize zeolites can have wide-ranging effects on the physicochemical properties of the final product. Here we discuss the diverse pathways of zeolite nucleation, recent breakthroughs in seed-assisted syntheses of nanosized and hierarchical materials, and shortcomings for developing generalized guidelines to predict synthesis outcomes. We offer a critical analysis of state-of-the-art approaches to tailor zeolite crystallization wherein we conceptualize whether parallels between network theory and zeolite synthesis can be instrumental for translating key findings of individual discoveries across a broader set of zeolite crystal structures and/or synthesis conditions.

Failure-Experiment-Supported Optimization of Poorly Reproducible Synthetic Conditions for Novel Lanthanide Metal-Organic Frameworks with Two-Dimensional Secondary Building Units*

Novel metal-organic frameworks containing lanthanide double-layer-based secondary building units (KGF-3) were synthesized by using machine learning (ML). Isolating pure KGF-3 was challenging, and the synthesis was not reproducible because impurity phases were frequently obtained under the same synthetic conditions. Thus, dominant factors for the synthesis of KGF-3 were identified, and its synthetic conditions were optimized by using two ML techniques. Cluster analysis was used to classify the obtained powder X-ray diffractometry patterns of the products and thus automatically determine whether the experiments were successful. Decision-tree analysis was used to visualize the experimental results, after extracting factors that mainly affected the synthetic reproducibility. Water-adsorption isotherms revealed that KGF-3 possesses unique hydrophilic pores. Impedance measurements demonstrated good proton conductivities (σ=5.2×10^-4  S cm^-1 for KGF-3(Y)) at a high temperature (363 K) and relative humidity of 95 % RH.

Machine-Learning-Assisted Selective Synthesis of a Semiconductive Silver Thiolate Coordination Polymer with Segregated Paths for Holes and Electrons

Coordination polymers (CPs) with infinite metal-sulfur bond networks have unique electrical conductivities and optical properties. However, the development of new (-M-S-)_n -structured CPs is hindered by difficulties with their crystallization. Herein, we describe the use of machine learning to optimize the synthesis of trithiocyanuric acid (H₃ ttc)-based semiconductive CPs with infinite Ag-S bond networks, report three CP crystal structures, and reveal that isomer selectivity is mainly determined by proton concentration in the reaction medium. One of the CPs, [Ag₂ Httc]_n , features a 3D-extended infinite Ag-S bond network with 1D columns of stacked triazine rings, which, according to first-principle calculations, provide separate paths for holes and electrons. Time-resolved microwave conductivity experiments show that [Ag₂ Httc]_n is highly photoconductive (φΣμ_max =1.6×10^-4  cm²  V^-1  s^-1 ). Thus, our method promotes the discovery of novel CPs with selective topologies that are difficult to crystallize.

No more trial and error for zeolites

[Figure: see text].

A priori control of zeolite phase competition and intergrowth with high-throughput simulations

[Figure: see text].

Discovering Relationships between OSDAs and Zeolites through Data Mining and Generative Neural Networks

Organic structure directing agents (OSDAs) play a crucial role in the synthesis of micro- and mesoporous materials especially in the case of zeolites. Despite the wide use of OSDAs, their interaction with zeolite frameworks is poorly understood, with researchers relying on synthesis heuristics or computationally expensive techniques to predict whether an organic molecule can act as an OSDA for a certain zeolite. In this paper, we undertake a data-driven approach to unearth generalized OSDA-zeolite relationships using a comprehensive database comprising of 5,663 synthesis routes for porous materials. To generate this comprehensive database, we use natural language processing and text mining techniques to extract OSDAs, zeolite phases, and gel chemistry from the scientific literature published between 1966 and 2020. Through structural featurization of the OSDAs using weighted holistic invariant molecular (WHIM) descriptors, we relate OSDAs described in the literature to different types of cage-based, small-pore zeolites. Lastly, we adapt a generative neural network capable of suggesting new molecules as potential OSDAs for a given zeolite structure and gel chemistry. We apply this model to CHA and SFW zeolites generating several alternative OSDA candidates to those currently used in practice. These molecules are further vetted with molecular mechanics simulations to show the model generates physically meaningful predictions. Our model can automatically explore the OSDA space, reducing the amount of simulation or experimentation needed to find new OSDA candidates.

Accelerated Discovery of Zeolite Structures with Superior Mechanical Properties via Active Learning

A Bayesian active learning platform is developed for the accelerated discovery of mechanically superior zeolite structures from more than half a million hypothetical candidates. An initial database containing the mechanical properties of synthesizable zeolites is trained to develop the machine learning regression model. Then, a Bayesian optimization scheme is implemented to identify zeolites with potentially excellent mechanical properties. The newly accumulated database consists of 871 labeled structures, and the uncertainty of the predictive model is reduced by 40% and 58% for the bulk and shear moduli, respectively. The model convergence shows that no further improvement occurs after the 10th iteration of optimizations. The proposed platform is able to discover 23 new zeolite structures that have unprecedented shear moduli; in one case, the shear modulus (127.81 GPa) is 250% higher than the previous data set. The proposed platform accelerates the material discovery process while maximizing computational efficiency and enhancing the predictive accuracy.

Data science assisted investigation of catalytically active copper hydrate in zeolites for direct oxidation of methane to methanol using H2O2

Dozens of Cu zeolites with MOR, FAU, BEA, FER, CHA and MFI frameworks are tested for direct oxidation of CH₄ to CH₃OH using H₂O₂ as oxidant. To investigate the active structures of the Cu zeolites, 15 structural variables, which describe the features of the zeolite framework and reflect the composition, the surface area and the local structure of the Cu zeolite active site, are collected from the Database of Zeolite Structures of the International Zeolite Association (IZA). Also analytical studies based on inductively coupled plasma-optical emission spectrometry (ICP-OES), X-ray fluorescence (XRF), N₂ adsorption specific surface area measurement and X-ray absorption fine structure (XAFS) spectral measurement are performed. The relationships between catalytic activity and the structural variables are subsequently revealed by data science techniques, specifically, classification using unsupervised and supervised machine learning and data visualization using pairwise correlation. Based on the unveiled relationships and a detailed analysis of the XAFS spectra, the local structures of the Cu zeolites with high activity are proposed.

Structure–direction towards the new large pore zeolite NUD-3

A subtle structure–direction allows the crystallization of the ordered and fully connected zeolite NUD-3 instead of disordered or interrupted versions.

The Role of Machine Learning in the Understanding and Design of Materials

Developing algorithmic approaches for the rational design and discovery of materials can enable us to systematically find novel materials, which can have huge technological and social impact. However, such rational design requires a holistic perspective over the full multistage design process, which involves exploring immense materials spaces, their properties, and process design and engineering as well as a techno-economic assessment. The complexity of exploring all of these options using conventional scientific approaches seems intractable. Instead, novel tools from the field of machine learning can potentially solve some of our challenges on the way to rational materials design. Here we review some of the chief advancements of these methods and their applications in rational materials design, followed by a discussion on some of the main challenges and opportunities we currently face together with our perspective on the future of rational materials design and discovery.

High Throughput Methods in the Synthesis, Characterization, and Optimization of Porous Materials

Porous materials are widely employed in a large range of applications, in particular, for storage, separation, and catalysis of fine chemicals. Synthesis, characterization, and pre- and post-synthetic computer simulations are mostly carried out in a piecemeal and ad hoc manner. Whilst high throughput approaches have been used for more than 30 years in the porous material fields, routine integration of experimental and computational processes is only now becoming more established. Herein, important developments are highlighted and emerging challenges for the community identified, including the need to work toward more integrated workflows.

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

By combining metal nodes with organic linkers we can potentially synthesize millions of possible metal-organic frameworks (MOFs). The fact that we have so many materials opens many exciting avenues but also create new challenges. We simply have too many materials to be processed using conventional, brute force, methods. In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations. The first part of the review gives an introduction to the principles of big-data science. We show how to select appropriate training sets, survey approaches that are used to represent these materials in feature space, and review different learning architectures, as well as evaluation and interpretation strategies. In the second part, we review how the different approaches of machine learning have been applied to porous materials. In particular, we discuss applications in the field of gas storage and separation, the stability of these materials, their electronic properties, and their synthesis. Given the increasing interest of the scientific community in machine learning, we expect this list to rapidly expand in the coming years.

Electrodeposition Fabrication of Chalcogenide Thin Films for Photovoltaic Applications

Electrodeposition, which features low cost, easy scale-up, good control in the composition and great flexible substrate compatibility, is a favorable technique for producing thin films. This paper reviews the use of the electrodeposition technique for the fabrication of several representative chalcogenides that have been widely used in photovoltaic devices. The review focuses on narrating the mechanisms for the formation of films and the key factors that affect the morphology, composition, crystal structure and electric and photovoltaic properties of the films. The review ends with a remark section addressing some of the key issues in the electrodeposition method towards creating high quality chalcogenide films.

Molecular level nucleation mechanisms of hierarchical MFI and MOR zeolite structures via non-stochastic pathways

Understanding the chemical mechanism of crystal nucleation at the molecular level is crucial for the design of architectural structures of valuable materials in the future. In this study, it has been revealed that amorphous silicate precursors, which play a role in the nucleation processes of zeolitic frameworks, can be regularly fragmented in mass spectroscopy due to the hydroxyl functional groups in their molecular structures. In this way, by using the mass spectra acquired from LDI-TOF MS, the systematic evolution stages of a common 1D precursor converting to the 3D unit cells of MFI and MOR zeolite structures observed in the same reaction medium were constructed through a nucleation mechanism at the molecular level for the first time. Here we show a novel nucleation pathway that does not occur via stochastic assembly of atoms or distinct building blocks by molecular recognition. Each of the proposed nucleation mechanisms of these different frameworks carrying structural similarities is from different combinations of sequential self-attaching intramolecular covalent couplings of identical origin precursors. The dynamic molecular structure capable of forming finite building units of target frameworks during the nucleation process of this precursor, which is the polymerized form of simple 6-membered siloxane chains, has been arranged around structure directing agents before a hydrothermal reaction.

Synthesis and Post-Synthesis Transformation of Germanosilicate Zeolites

Zeolites are one of the most important heterogeneous catalysts, with a high number of large-scale industrial applications. While the synthesis of new zeolites remain rather limited, introduction of germanium has substantially increased our ability to not only direct the synthesis of zeolites but also to convert them into new materials post-synthetically. The smaller Ge-O-Ge angles (vs. Si-O-Si) and lability of the Ge-O bonds in aqueous solutions account for this behaviour. This Minireview discusses critical aspects of germanosilicate synthesis and their post-synthesis transformations to porous materials.

Extracting an Empirical Intermetallic Hydride Design Principle from Limited Data via Interpretable Machine Learning

An open question in the metal hydride community is whether there are simple, physics-based design rules that dictate the thermodynamic properties of these materials across the variety of structures and chemistry they can exhibit. While black box machine learning-based algorithms can predict these properties with some success, they do not directly provide the basis on which these predictions are made, therefore complicating the a priori design of novel materials exhibiting a desired property value. In this work we demonstrate how feature importance, as identified by a gradient boosting tree regressor, uncovers the strong dependence of the metal hydride equilibrium H₂ pressure on a volume-based descriptor that can be computed from just the elemental composition of the intermetallic alloy. Elucidation of this simple structure-property relationship is valid across a range of compositions, metal substitutions, and structural classes exhibited by intermetallic hydrides. This permits rational targeting of novel intermetallics for high-pressure hydrogen storage (low-stability hydrides) by their descriptor values, and we predict a known intermetallic to form a low-stability hydride (as confirmed by density functional theory calculations) that has not yet been experimentally investigated.