Isaiah A. Moses

The 2D Crystal Consortium Materials Innovation Platform (2DCC-MIP) is a NSF supported national user facility focused on advancing the synthesis of 2D materials, monolayers, surfaces, and interfaces. The need for the facility to organize and share data with users led to the development of an internal data management and analysis engine, the Lifetime Sample Tracking platform (LiST). This infrastructure allows the automated capture, curation, analysis, and dissemination of data ranging from experimental materials synthesis parameters and characterization to theoretical first-principles and ReaxFF molecular dynamics modeling [Nayir et al., 2D Mater. 10, 032002 (2023)]. The system currently hosts synthesis and property data (accessible via a REST API) on ∼20 000 samples produced by the 2DCC grown using a variety of techniques from bulk crystal growth to metal-organic chemical vapor deposition and molecular beam epitaxy, among others. Data used in publications can easily be grouped by the system into data packages that are given digital object identifiers for inclusion with each publication. The LiST platform is now being used by groups outside of the 2DCC as a solution for data curation in materials science. Data management tools, such as LiST, support the materials development process by allowing a closed loop iteration between synthesis, characterization, theory, and targeted materials design. This also enables machine learning research, artificial intelligence analysis, and the potential for autonomous synthesis in the future.

Subtle variations in local growth chemistry can fundamentally alter the morphology of layered chalcogenide thin films, yet the atomic-scale mechanisms underlying this sensitivity remain poorly understood. Here, we combine molecular beam epitaxy (MBE) experiments, reactive molecular dynamics simulations, and machine learning analysis to establish a chemistry–structure relationship for SnSe thin film growth on MgO. Experimentally, we show that modifying the Sn/Se flux ratio and deposition sequence promotes a transition between three-dimensional island formation and laterally coalesced smooth films, accompanied by pronounced changes in surface roughness. Reactive molecular dynamics simulations reveal that this transition originates from an intrinsic chemical asymmetry between Sn and Se that alters adatom surface diffusion and aggregation behavior during growth. Se-rich environments stabilize surface passivation and promote lateral growth, whereas Sn-rich conditions favor vertical aggregation through rapid Sn clustering. To assess morphology trends without imposing physical assumptions, we apply an unsupervised machine learning framework to images rendered from the simulation snapshots. The resulting low-dimensional representation of the surface morphologies captures morphology trends consistent with those observed experimentally and those in simulations, providing a complementary data-driven interpretation of the chemistry–morphology relationship. Because nanoscale roughness strongly influences carrier scattering, phonon transport, and domain stability in SnSe-based electronic and energy devices, these results provide a chemistry-guided framework for morphology control in layered chalcogenide thin films.

The growth and characterization of materials using empirical optimization typically requires a significant amount of expert time, experience, and resources. Several complementary characterization methods are routinely performed to determine the quality and properties of a grown sample. Machine learning (ML) can support the conventional approaches by using historical data to guide and provide speed and efficiency to the growth and characterization of materials. Specifically, ML can provide quantitative information from characterization data that is typically obtained from a different modality. In this study, the feasibility of projecting quantitative metrics from microscopy measurements, such as atomic force microscopy (AFM), using data obtained from spectroscopy measurements, like Raman spectroscopy is investigated. Generative models are also trained to generate the full and specific features of the Raman and photoluminescence spectra from each other and the AFM images of the thin‐film MoS ₂ . The results are promising and have provided a foundational guide for the use of ML for the cross‐modal characterization of materials for their accelerated, efficient, and cost‐effective discovery.

Autonomous synthesis platforms integrating machine learning with in situ diagnostics have the potential to revolutionize thin-film growth by enabling real-time process optimization and reducing the need for manual tuning. However, their application to molecular beam epitaxy (MBE) remains underdeveloped. Here, we present a machine learning-guided framework for MBE growth of GaSe films, leveraging reflection high-energy electron diffraction (RHEED) as an in situ diagnostic alongside ex situ characterization via X-ray diffraction and atomic force microscopy. Unsupervised learning on RHEED patterns reveals a well-defined boundary between high- and low-quality samples, capturing physically meaningful features. Mutual information analysis shows a strong correlation between RHEED embeddings and rocking curve full-width at half-maximum (fwhm), while the correlation with AFM root-mean-square (RMS) roughness is weak. Among key growth conditions, growth rate most strongly influences fwhm, whereas the Se/Ga flux ratio primarily affects RMS roughness and the RHEED embeddings. Supervised learning models trained to predict fwhm and RMS roughness demonstrate moderate accuracy, with significant improvement achieved by incorporating RHEED embeddings. Furthermore, anomaly detection via residual analysis in supervised learning aligns well with unsupervised classification from RHEED, reinforcing the reliability of the predictive models. This study establishes a data-driven framework for machine learning-assisted MBE, paving the way for real-time process control and accelerated optimization of thin-film synthesis.

Deep learning models based on atomic force microscopy enhance efficiency in inverse design and characterization of materials. However, the limited and imbalanced data of experimental materials that are typically available is a major challenge. Also important is the need to interpret trained models, which are normally complex enough to be uninterpretable by humans. Here, we present a systemic evaluation of transfer learning strategies to accommodate low-data scenarios in materials synthesis and a model latent feature analysis to draw connections to the human-interpretable characteristics of the samples. While we imagine this framework can be used in downstream analysis tasks such as quantitative characterization, we demonstrate the strategies on a multi-material classification task for which the ground truth labels are readily available. Our models show accurate predictions in five classes of transition metal dichalcogenides (TMDs) (MoS₂, WS₂, WSe₂, MoSe₂, and Mo-WSe₂) with up to 89% accuracy on held-out test samples. Analysis of the latent features reveals a correlation with physical characteristics such as grain density, Difference of Gaussian blob, and local variation. The transfer learning optimization modality and the exploration of the correlation between the latent and physical features provide important frameworks that can be applied to other classes of materials beyond TMDs to enhance the models’ performance and explainability which can accelerate the inverse design of materials for technological applications.

In this work, we present the optimized geometric stacking of several layered nanoporous organic nanocrystals (NONs) and the stacking effect on their electronic structure. Hexagonal layered structures, C₁₂H₆-h2D, B₆N₆H₆-h2D and C₆N₆-h2D are built from aromatic organic molecular units benzene, borazine and 1,3,5-triazine, respectively while oblique structures, C₁₀N₂H₄-o2D, C₈N₄H₂-o2D, C₁₀P₂H₄-o2D and C₁₀As₂H₄-o2D, are built from pyridine, 1,3-diazine, phosphinine and arsinine, respectively. Our density functional theory calculations show stacking energy profiles of NONs that are similar to graphene in both the stand-alone and bulk C₁₂H₆-h2D and B₆N₆H₆-h2D structures while the rest of the studied layered materials deviate from the perfect AB stacking. The number of layers as well as the stacking configuration significantly influence the electronic properties of these materials. Indirect to direct band gap crossovers from the bulk to monolayers are observed in all of the NONs except in C₆N₆-h2D which exhibits a direct band gap in both the monolayer, isolated few-layers, and bulk. Furthermore, it is observed that the electronic nature of C₁₀As₂H₄-o2D changes from a semiconducting character in the isolated monolayer to a metallic character in the bulk. The porous nature and the stability of these layered NONs combined with the electronic properties observed in this work point at them as valuable materials for potential applications in nanoelectronics and gas separation membranes, as well as deep ultraviolet optoelectronics and laser devices.