Search

Materials design often relies on human-generated hypotheses, a process inherently limited by cognitive constraints such as knowledge gaps and limited ability to integrate and extract knowledge implications, particularly when multidisciplinary expertise is required. This work demonstrates that large language models (LLMs), coupled with prompt engineering, can effectively generate non-trivial materials hypotheses by integrating scientific principles from diverse sources without explicit design guidance by human experts. These include design ideas for high-entropy alloys with superior cryogenic properties and halide solid electrolytes with enhanced ionic conductivity and formability. These design ideas have been experimentally validated in high-impact publications in 2023 not available in the LLM training data, demonstrating the LLM's ability to generate highly valuable and realizable innovative ideas not established in the literature. Our approach primarily leverages materials system charts encoding processing-structure-property relationships, enabling more effective data integration by condensing key information from numerous papers, and evaluation and categorization of numerous hypotheses for human cognition, both through the LLM. This LLM-driven approach opens the door to new avenues of artificial intelligence-driven materials discovery by accelerating design, democratizing innovation, and expanding capabilities beyond the designer's direct knowledge.

We demonstrate the ability of large language models (LLMs) to perform material and molecular property regression tasks, a significant deviation from the conventional LLM use case. We benchmark the Large Language Model Meta AI (LLaMA) 3 on several molecular properties in the QM9 dataset and 24 materials properties. Only composition-based input strings are used as the model input and we fine tune on only the generative loss. We broadly find that LLaMA 3, when fine-tuned using the SMILES representation of molecules, provides useful regression results which can rival standard materials property prediction models like random forest or fully connected neural networks on the QM9 dataset. Not surprisingly, LLaMA 3 errors are 5-10x higher than those of the state-of-the-art models that were trained using far more granular representation of molecules (e.g., atom types and their coordinates) for the same task. Interestingly, LLaMA 3 provides improved predictions compared to GPT-3.5 and GPT-4o. This work highlights the versatility of LLMs, suggesting that LLM-like generative models can potentially transcend their traditional applications to tackle complex physical phenomena, thus paving the way for future research and applications in chemistry, materials science and other scientific domains.

Oxygen ion conductors are crucial for enhancing the efficiency of various clean energy technologies, including fuel cells, batteries, electrolyzers, membranes, sensors, and more. In this study, LaBi2O4Cl is identified as an ultra-fast oxygen conductor from the MBi2O4X (M=rare-earth element, X=halogen element) family, discovered by a structure-similarity analysis of >60k oxygen-containing compounds. Ab initio studies reveal that LaBi2O4Cl has an ultra-low migration barrier of 0.1 eV for oxygen vacancy, significantly lower than 0.6-0.8 eV for interstitial oxygen. Frenkel pairs are the dominant defects in intrinsic LaBi2O4Cl, facilitating notable oxygen diffusion primarily through vacancies at higher temperatures. LaBi2O4Cl with extrinsic oxygen vacancies (2.8%) exhibits a conductivity of 0.3 S/cm at 25{\deg}C, maintains a 0.1 eV diffusion barrier up to 1100{\deg}C, and transitions from extrinsic to mixed extrinsic and intrinsic behavior as the Frenkel pair concentration increases at higher temperatures. Experimental results on synthesized LaBi2O4Cl and Sr-doped LaBi2O4Cl demonstrate comparable or higher oxygen conductivity than YSZ and LSGM below 400 {\deg}C, with lower activation energies. Further experimental optimization of LaBi2O4Cl, including aliovalent doping and microstructure refinement, could significantly enhance its performance and efficiency, facilitating fast oxygen conduction approaching room temperature.

Nanotechnology's impact on semiconductor industry advancement, particularly through the engineering of nanostructures like nanowires, opens new possibilities for material functionality due to the tunable physical properties of nanostructures compared to bulk materials. This paper presents a comprehensive study on group IV semiconductors and their binaries across four polytypes: 2H, 3C, 4H, and 6H, focusing on their optoelectronic application potential. Deep understanding of these polytypes is particularly relevant for nanowire-based technologies. Through first principles modeling, we examine the structural and electronic properties of these materials, emphasizing their band structure, stability, and the feasibility for light-emitting applications. We use a generalized Ising model to discuss materials stability and tendency for polytypism. We also determine relative band edge positions and employ a six $k\cdot p$ model for a detailed understanding of the materials' electronic properties. Due to the comprehensive nature of this study, we provide insight on the chemical trends present in all of the studied properties. Our theoretical predictions align well with existing experimental data, suggesting new avenues for nanostructure-based device development. The discussion extends to the implications of these findings for the fabrication of optoelectronic devices with the studied IV-IV materials, highlighting the challenges and opportunities for future research in nanowire synthesis and their application.

In this work, we present a ready-to-use symmetry invariant expansion form of the eight-band k.p Hamiltonian for inorganic and organic metal halide perovskites (CsPbX$_3$ and MAPbX$_3$ with $X = \{$Cl, Br, I$\}$). We use the k.p model to calculate the electronic band structures for perovskite materials of cubic and pseudo-cubic phase. In order to find respective parameters, the band structures of considered materials were obtained within state-of-the-art density functional theory and used next as targets to adjust the k.p bands and determine the values of k.p parameters. The calculated band structures were used to obtain the material gain for bulk crystals (CsPbCl$_3$, CsPbBr$_3$, CsPbI$_3$, MAPbCl$_3$, MAPbBr$_3$ and MAPbI$_3$) which is compared with the material gain in well-established III-V semiconductors. It was found that for these perovskites a positive material gain appears at lower carrier density than for the reference materials (GaAs and InP). We demonstrate that from the point of view of the electronic band structure, the studied perovskites are very promising gain medium for lasers.

There has been a growing effort to replace manual extraction of data from research papers with automated data extraction based on natural language processing, language models, and recently, large language models (LLMs). Although these methods enable efficient extraction of data from large sets of research papers, they require a significant amount of up-front effort, expertise, and coding. In this work we propose the ChatExtract method that can fully automate very accurate data extraction with minimal initial effort and background, using an advanced conversational LLM. ChatExtract consists of a set of engineered prompts applied to a conversational LLM that both identify sentences with data, extract that data, and assure the data's correctness through a series of follow-up questions. These follow-up questions largely overcome known issues with LLMs providing factually inaccurate responses. ChatExtract can be applied with any conversational LLMs and yields very high quality data extraction. In tests on materials data we find precision and recall both close to 90% from the best conversational LLMs, like ChatGPT-4. We demonstrate that the exceptional performance is enabled by the information retention in a conversational model combined with purposeful redundancy and introducing uncertainty through follow-up prompts. These results suggest that approaches similar to ChatExtract, due to their simplicity, transferability, and accuracy are likely to become powerful tools for data extraction in the near future. Finally, databases for critical cooling rates of metallic glasses and yield strengths of high entropy alloys are developed using ChatExtract., Comment: 7 pages, 3 figures, 1 table

Accurate and comprehensive material databases extracted from research papers are crucial for materials science and engineering, but their development requires significant human effort. With large language models (LLMs) transforming the way humans interact with text, LLMs provide an opportunity to revolutionize data extraction. In this study, we demonstrate a simple and efficient method for extracting materials data from full-text research papers leveraging the capabilities of LLMs combined with human supervision. This approach is particularly suitable for mid-sized databases and requires minimal to no coding or prior knowledge about the extracted property. It offers high recall and nearly perfect precision in the resulting database. The method is easily adaptable to new and superior language models, ensuring continued utility. We show this by evaluating and comparing its performance on GPT-3 and GPT-3.5/4 (which underlie ChatGPT), as well as free alternatives such as BART and DeBERTaV3. We provide a detailed analysis of the method's performance in extracting sentences containing bulk modulus data, achieving up to 90% precision at 96% recall, depending on the amount of human effort involved. We further demonstrate the method's broader effectiveness by developing a database of critical cooling rates for metallic glasses over twice the size of previous human curated databases., Comment: 13 pages, 4 figures

The band gap engineering of group IV semiconductors has not been well explored theoretically and experimentally, except for SiGe. Recently, GeSn has attracted much attention due to the possibility of obtaining a direct band gap in this alloy, thereby making it suitable for light emitters. Other group IV alloys may also potentially exhibit material properties useful for device applications, expanding the space for band gap engineering in group IV. In this work the electronic band structure of all group IV semiconductor alloys is investigated. Twelve possible A:B alloys, where A is a semiconducting host (A = C, Si, and Ge) and B is an isovalent dopant (B = C, Si, Ge, Sn, and Pb), were studied in the dilute regime (0.8%) of the isovalent dopant in the entire Brillouin zone (BZ), and the chemical trends in the evolution of their electronic band structure were carefully analyzed. Density functional theory with state-of-the-art methods such as meta-GGA functionals and a spectral weight approach to band unfolding from large supercells was used to obtain dopant-related changes in the band structure, in particular the direct band gap at the {\Gamma} point and indirect band gaps at the L(X) points of the BZ. Analysis of contributions from geometry distortion and electronic interaction was also performed. Moreover, the obtained results are discussed in the context of obtaining a direct fundamental gap in Ge:B (B = C, Sn, and Pb) alloys, and intermediate band formation in C:B (B = Sn and Pb) and Ge:C. An increase in localization effects is also observed: a strong hole localization for alloys diluted with a dopant of a larger covalent radius and a strong electron localization for alloys with a dopant of smaller radius. Finally, it is shown that alloying Si and Ge with other elements from group IV is a promising way to enhance the functionality of group IV semiconductors.

Quantifying charge-state transition energy levels of impurities in semiconductors is critical to understanding and engineering their optoelectronic properties for applications ranging from solar photovoltaics to infrared lasers. While these transition levels can be measured and calculated accurately, such efforts are time-consuming and more rapid prediction methods would be beneficial. Here, we significantly reduce the time typically required to predict impurity transition levels using multi-fidelity datasets and a machine learning approach employing features based on elemental properties and impurity positions. We use transition levels obtained from low-fidelity (i.e., local-density approximation or generalized gradient approximation) density functional theory (DFT) calculations, corrected using a recently proposed modified band alignment scheme, which well-approximates transition levels from high-fidelity DFT (i.e., hybrid HSE06). The model fit to the large multi-fidelity database shows improved accuracy compared to the models trained on the more limited high-fidelity values. Crucially, in our approach, when using the multi-fidelity data, high-fidelity values are not required for model training, significantly reducing the computational cost required for training the model. Our machine learning model of transition levels has a root mean squared (mean absolute) error of 0.36 (0.27) eV vs high-fidelity hybrid functional values when averaged over 14 semiconductor systems from the II-VI and III-V families. As a guide for use on other systems, we assessed the model on simulated data to show the expected accuracy level as a function of bandgap for new materials of interest. Finally, we use the model to predict a complete space of impurity charge-state transition levels in all zinc blende III-V and II-VI systems.

This paper provides an accurate theoretical defect energy database for pure and Bi-containing III-V (III-V:Bi) materials and investigates efficient methods for high-throughput defect calculations based on corrections of results obtained with local and semi-local functionals. Point defects as well as nearest-neighbor and second-nearest-neighbor pair defects were investigated in charge states ranging from -5 to 5. Ga-V:Bi systems (GaP:Bi, GaAs:Bi, and GaSb:Bi) were thoroughly investigated with significantly slower, higher fidelity hybrid Heyd-Scuseria-Ernzerhof (HSE) and significantly faster, lower fidelity local density approximation (LDA) calculations. In both approaches spurious electrostatic interactions were corrected with the Freysoldt correction. The results were verified against available experimental results and used to assess the accuracy of a previous band alignment correction. Here, a modified band alignment method is proposed in order to better predict the HSE values from the LDA ones. The proposed method allows prediction of defect energies with values that approximate those from the HSE functional at the computational cost of LDA (about 20x faster for the systems studied here). Tests of selected point defects in In-V:Bi materials resulted in corrected LDA values having a mean absolute error (MAE)=0.175 eV for defect levels vs. HSE. The method was further verified on an external database of defects and impurities in CdX (X=S, Se, Te) systems, yielding a MAE=0.194 eV. These tests demonstrate the correction to be sufficient for qualitative and semi-quantitative predictions, and may suggest transferability to many semiconductor systems without significant loss in accuracy. Properties of the remaining In-V:Bi defects and all Al-V:Bi defects were predicted with the use of the modified band alignment method.

MAST-SEY is an open-source Monte Carlo code capable of calculating secondary electron emission using input data generated entirely from first principle (density functional theory) calculations. It utilizes the complex dielectric function and Penn's theory for inelastic scattering processes, and relativistic Schr\"odinger theory by means of a partial-wave expansion method to govern elastic scattering. It allows the user to include explicitly calculated momentum dependence of the dielectric function, as well as to utilize first-principle density of states in secondary electron generation, which provides a more complete description of the underlying physics. In this paper we thoroughly describe the theoretical aspects of the modeling, as used in the code, and present sample results obtained for copper and aluminum.

The electronic band structure of Ga(PAsN) with a few percent of nitrogen is calculated in the whole composition of Ga(PAs) host using the state-of-the-art density functional methods including the modified Becke-Johnson functional to correctly reproduce the band gap, and band unfolding to reveal the character of the bands within the entire Brillouin zone. As expected, relatively small amounts of nitrogen introduced to Ga(PAs) lead to formation of an intermediate band below the conduction band which is consistent with the band anticrossing model, widely used to describe the electronic band structure of dilute nitrides. However, in this study calculations are performed in the whole Brillouin zone and reveal the significance of correct description of the band structure near the edges of Brillouin zone, especially for indirect band gap P-rich host alloy, which may not be properly captured with simpler models. The theoretical results are compared with experimental studies, confirming their reliability. The influence of nitrogen on the band structure is discussed in terms of application of Ga(PAsN) in optoelectronic devices such as intermediate band solar cells and light emitters. It is found that Ga(PAsN) with low N and As concentration has a band structure suitable for integration in Si tandem solar cells, since the lattice mismatch between Si and Ga(PAsN) is small in this case. Moreover, it is concluded that P-rich Ga(PAsN) alloys with low N concentration have a promising band structure for two colour emitters. Additionally, the effect of nitrogen incorporation on the carrier localization is studied and discussed.

Ge with a quasi-direct band gap can be realized by strain engineering, alloying with Sn, or ultrahigh n-type doping. In this work, we use all three approaches together to fabricate direct-band-gap Ge-Sn alloys. The heavily doped n-type Ge-Sn is realized with CMOS-compatible nonequilibrium material processing. P is used to form highly doped n-type Ge-Sn layers and to modify the lattice parameter of P-doped Ge-Sn alloys. The strain engineering in heavily-P-doped Ge-Sn films is confirmed by x-ray diffraction and micro Raman spectroscopy. The change of the band gap in P-doped Ge-Sn alloy as a function of P concentration is theoretically predicted by density functional theory and experimentally verified by near-infrared spectroscopic ellipsometry. According to the shift of the absorption edge, it is shown that for an electron concentration greater than 1x10^20 cm-3 the band-gap renormalization is partially compensated by the Burstein-Moss effect. These results indicate that Ge-based materials have high potential for use in near-infrared optoelectronic devices, fully compatible with CMOS technology., Comment: 20 pages, 6 figures