Thermoelectric Material Performance () Predictions with Machine Learning.

Research efforts using the tools in machine- and deep learning models have begun to show success in predicting target properties such as thermoelectric (TE) properties, including the figure of merit (). These models were trained on various data sources that used experimental, crystallographic, and density functional theory (DFT) data. We developed an interpretable model on a huge experimental data set of ∼160,000 data points to predict the performance of thermoelectric materials.

Machine learning descriptors in materials chemistry used in multiple experimentally validated studies: Oliynyk elemental property dataset.

Materials informatics employs data-driven approaches for analysis and discovery of materials. Features also referred to as descriptors are essential in generating reliable and accurate machine-learning models. While general data can be obtained through public and commercial sources, features must be tailored to specific applications.

Machine-learning prediction of thermal expansion coefficient for perovskite oxides with experimental validation.

Perovskite oxides have been of high-interest and relatively well studied over the last 20 years due to their various applications, specifically for solid oxide fuel cells (SOFCs) and solid oxide electrolysis cells (SOECs). One of the key properties for a perovskite to perform well as a component in SOFCs, SOECs, and other high-temperature applications is its thermal expansion coefficient (TEC). The use of machine learning (ML) to predict material properties has greatly increased over the years and has proven to be a very useful tool for materials screening.

Interpretable Machine Learning in Solid-State Chemistry, with Applications to Perovskites, Spinels, and Rare-Earth Intermetallics: Finding Descriptors Using Decision Trees.

Machine-learning methods have exciting potential to aid materials discovery, but their wider adoption can be hindered by the opaqueness of many models. Even if these models are accurate, the inability to understand the basis for the predictions breeds skepticism. Thus, it is imperative to develop machine-learning models that are explainable and interpretable so that researchers can judge for themselves if the predictions are consistent with their own scientific understanding and chemical insight.

Ternary Rare-Earth-Metal Nickel Indides RENiIn (RE = Gd, Tb, Dy) with YbCuMg-Type Structure.

The ternary rare-earth-metal nickel indides RENiIn (RE = Gd, Tb, Dy) were prepared by arc-melting mixtures of the elements followed by annealing at 870 K. They adopt the YbCuMg-type structure (space group 6/, Pearson symbol 68, = 2), as determined by laboratory and synchrotron powder diffraction methods for RE = Gd ( = 9.6435(10) Å, = 22.

Finding the Next Superhard Material through Ensemble Learning.

An ensemble machine-learning method is demonstrated to be capable of finding superhard materials by directly predicting the load-dependent Vickers hardness based only on the chemical composition. A total of 1062 experimentally measured load-dependent Vickers hardness data are extracted from the literature and used to train a supervised machine-learning algorithm utilizing boosting, achieving excellent accuracy (R  = 0.97).

Significant Variability in the Photocatalytic Activity of Natural Titanium-Containing Minerals: Implications for Understanding and Predicting Atmospheric Mineral Dust Photochemistry.

The billions of tons of mineral dust released into the atmosphere each year provide an important surface for reaction with gas-phase pollutants. These reactions, which are often enhanced in the presence of light, can change both the gas-phase composition of the atmosphere and the composition and properties of the dust itself. Because dust contains titanium-rich grains, studies of dust photochemistry have largely employed commercial titanium dioxide as a proxy for its photochemically active fraction; to date, however, the validity of this model system has not been empirically determined.

Tailorable Indirect to Direct Band-Gap Double Perovskites with Bright White-Light Emission: Decoding Chemical Structure Using Solid-State NMR.

Efficient white-light-emitting single-material sources are ideal for sustainable lighting applications. Though layered hybrid lead-halide perovskite materials have demonstrated attractive broad-band white-light emission properties, they pose a serious long-term environmental and health risk as they contain lead (Pb) and are readily soluble in water. Recently, lead-free halide double perovskite (HDP) materials with a generic formula A(I)B'(III)B″(I)X (where A and B are cations and X is a halide ion) have demonstrated white-light emission with improved photoluminescence quantum yields (PLQYs).

Dehydrocoupling - an alternative approach to functionalizing germanium nanoparticle surfaces.

Surface functionalization is an essential aspect of nanoparticle design and preparation; it can impart stability, processability, functionality, as well as tailor optoelectronic properties that facilitate future applications. Herein we report a new approach toward modifying germanium nanoparticle (GeNP) surfaces and for the first time tether alkyl chains to the NP surfaces through Si-Ge bonds. This was achieved via heteronuclear dehydrocoupling reactions involving alkylsilanes and Ge-H moieties on the NP surfaces.

Alkaline Earth Metal-Organic Frameworks with Tailorable Ion Release: A Path for Supporting Biomineralization.

An innovative application of metal-organic frameworks (MOFs) is in biomedical materials. To treat bone demineralization, which is a hallmark of osteoporosis, biocompatible MOFs (bioMOFs) have been proposed in which various components, such as alkaline-earth cations and bisphosphonate molecules, can be delivered to maintain normal bone density. Multicomponent bioMOFs that release several components simultaneously at a controlled rate thus offer an attractive solution.

Solving the Coloring Problem in Half-Heusler Structures: Machine-Learning Predictions and Experimental Validation.

The site preferences within the structures of half-Heusler compounds have been evaluated through a machine-learning approach. A support-vector machine algorithm was applied to develop a model which was trained on 179 experimentally reported structures and 23 descriptors based solely on the chemical composition. The model gave excellent performance, with sensitivity of 93%, selectivity of 96%, and accuracy of 95%.

Enhancement in surface mobility and quantum transport of BiSbTeSe topological insulator by controlling the crystal growth conditions.

Despite numerous studies on three-dimensional topological insulators (3D TIs), the controlled growth of high quality (bulk-insulating and high mobility) TIs remains a challenging subject. This study investigates the role of growth methods on the synthesis of single crystal stoichiometric BiSbTeSe (BSTS). Three types of BSTS samples are prepared using three different methods, namely melting growth (MG), Bridgman growth (BG) and two-step melting-Bridgman growth (MBG).

Not Just Par for the Course: 73 Quaternary Germanides RE M XGe ( RE = La-Nd, Sm, Gd-Tm, Lu; M = Mn-Ni; X = Ag, Cd) and the Search for Intermetallics with Low Thermal Conductivity.

A total of 73 new quaternary rare-earth germanides RE M XGe ( RE = rare-earth metal; M = Mn-Ni; X = Ag, Cd) were prepared through reactions of the elements. The solid solution NdMnCd(GeSi ) was also prepared under the same conditions and found to be complete over the entire range. All of these compounds adopt the monoclinic HoNiInGe-type structure (space group C2/ m, a = 14.

Identifying an efficient, thermally robust inorganic phosphor host via machine learning.

Rare-earth substituted inorganic phosphors are critical for solid state lighting. New phosphors are traditionally identified through chemical intuition or trial and error synthesis, inhibiting the discovery of potential high-performance materials. Here, we merge a support vector machine regression model to predict a phosphor host crystal structure's Debye temperature, which is a proxy for photoluminescent quantum yield, with high-throughput density functional theory calculations to evaluate the band gap.

Polyanionic Gold-Tin Bonding and Crystal Structure Preference in REAuSn (RE = La, Ce, Pr, Nd).

During a systematic search of the RE-Au-Sn (RE = La, Ce, Pr, Nd) ternary phase space, a series of compounds with the general formula REAuSn have been identified. These phases can be synthesized by arc melting the elemental metals, followed by annealing. The crystal structures were solved using single-crystal X-ray diffraction, with the composition confirmed by energy-dispersive X-ray spectroscopy.

How To Optimize Materials and Devices via Design of Experiments and Machine Learning: Demonstration Using Organic Photovoltaics.

Most discoveries in materials science have been made empirically, typically through one-variable-at-a-time (Edisonian) experimentation. The characteristics of materials-based systems are, however, neither simple nor uncorrelated. In a device such as an organic photovoltaic, for example, the level of complexity is high due to the sheer number of components and processing conditions, and thus, changing one variable can have multiple unforeseen effects due to their interconnectivity.

Machine Learning Directed Search for Ultraincompressible, Superhard Materials.

In the pursuit of materials with exceptional mechanical properties, a machine-learning model is developed to direct the synthetic efforts toward compounds with high hardness by predicting the elastic moduli as a proxy. This approach screens 118 287 compounds compiled in crystal structure databases for the materials with the highest bulk and shear moduli determined by support vector machine regression. Following these models, a ternary rhenium tungsten carbide and a quaternary molybdenum tungsten borocarbide are selected and synthesized at ambient pressure.

Searching for Missing Binary Equiatomic Phases: Complex Crystal Chemistry in the Hf-In System.

There remain 21 systems (out of over 3500 possible combinations of the elements) in which the existence of the simple binary equiatomic phases AB has not been established experimentally. Among these, the presumed binary phase HfIn is predicted to adopt the tetragonal CuAu-type structure (space group P4/ mmm) by a recently developed machine-learning model and by structure optimization through global energy minimization. To test this prediction, the Hf-In system was investigated experimentally by reacting the elements in a 1:1 stoichiometry at 1070 K.

Discovery of Intermetallic Compounds from Traditional to Machine-Learning Approaches.

Intermetallic compounds are bestowed by diverse compositions, complex structures, and useful properties for many materials applications. How metallic elements react to form these compounds and what structures they adopt remain challenging questions that defy predictability. Traditional approaches offer some rational strategies to prepare specific classes of intermetallics, such as targeting members within a modular homologous series, manipulating building blocks to assemble new structures, and filling interstitial sites to create stuffed variants.

Disentangling Structural Confusion through Machine Learning: Structure Prediction and Polymorphism of Equiatomic Ternary Phases ABC.

A method to predict the crystal structure of equiatomic ternary compositions based only on the constituent elements was developed using cluster resolution feature selection (CR-FS) and support vector machine (SVM) classification. The supervised machine-learning model was first trained with 1037 individual compounds that adopt the most populated ternary 1:1:1 structure types (TiNiSi-, ZrNiAl-, PbFCl-, LiGaGe-, YPtAs-, UGeTe-, and LaPtSi-type) and then validated using an additional 519 compounds. The CR-FS algorithm improves class discrimination and indicates that 113 variables including size, electronegativity, number of valence electrons, and position on the periodic table (group number) influence the structure preference.

Gd12Co5.3Bi and Gd12Co5Bi, Crystalline Doppelgänger with Low Thermal Conductivities.

Attempts to prepare Gd12Co5Bi, a member of the rare-earth (RE) intermetallics RE12Co5Bi, which were identified by a machine-learning recommendation engine as potential candidates for thermoelectric materials, led instead to formation of the new compound Gd12Co5.3Bi with a very similar composition. Phase equilibria near the Gd-rich corner of the Gd-Co-Bi phase diagram were elucidated by both lab-based and variable-temperature synchrotron powder X-ray diffraction, suggesting that Gd12Co5.

Many metals make the cut: quaternary rare-earth germanides RE4M2InGe4 (M = Fe, Co, Ni, Ru, Rh, Ir) and RE4RhInGe4 derived from excision of slabs in RE2InGe2.

The formation of quaternary rare-earth (RE) germanides containing transition metals (M's) from groups 6 to 10 was investigated through arc-melting and annealing reactions at 800 °C; about 50 new compounds were obtained. These include several new series of quaternary germanides RE4M2InGe4 (M = Fe, Co, Ru, Rh, Ir), previously known only for M = Mn and Ni; additional members of RE4Ni2InGe4 extended to other RE substituents; and a different but closely related series RE4RhInGe4. Detailed crystal structures were determined by single-crystal X-ray diffraction studies for 20 compounds.

Quaternary germanides RE4Mn2InGe4 (RE = La-Nd, Sm, Gd-Tm, Lu).

The quaternary germanides RE4Mn2InGe4 (RE = La-Nd, Sm, Gd-Tm, Lu) have been prepared by arc-melting reactions of the elements and annealing at 800 °C and represent the second example of the RE4M2InGe4 series previously known only for M = Ni. Single-crystal X-ray diffraction studies conducted on the earlier RE members of RE4Mn2InGe4 confirmed that they adopt the monoclinic Ho4Ni2InGe4-type structure [space group C2/m, a = 16.646(2)-15.

Phase equilibria in the Mo-Fe-P system at 800 °C and structure of ternary phosphide (Mo(1-x)Fe(x))3P (0.10 ≤ x ≤ 0.15).

Construction of the isothermal section in the metal-rich portion (<67 atom % P) of the Mo-Fe-P phase diagram at 800 °C has led to the identification of two new ternary phases: (Mo(1-x)Fe(x))(2)P (x = 0.30-0.82) and (Mo(1-x)Fe(x))(3)P (x = 0.