Search for: All records

Data-driven approaches to materials exploration and discovery are building momentum due to emerging advances in machine learning. However, parsimonious representations of crystals for navigating the vast materials search space remain limited. To address this limitation, we introduce a materials discovery framework that utilizes natural language embeddings from language models as representations of compositional and structural features. The contextual knowledge encoded in these language representations conveys information about material properties and structures, enabling both similarity analysis to recall relevant candidates based on a query material and multi-task learning to share information across related properties. Applying this framework to thermoelectrics, we demonstrate diversified recommendations of prototype crystal structures and identify under-studied material spaces. Validation through first-principles calculations and experiments confirms the potential of the recommended materials as high-performance thermoelectrics. Language-based frameworks offer versatile and adaptable embedding structures for effective materials exploration and discovery, applicable across diverse material systems.

 

Computation-guided selection of dopants enables the transformation of Hg₂GeTe₄from intrinsic to degenerate carrier concentrations and the thermoelectric performance is assessed experimentally.

 

Successful dopability in AgInTe₂requires careful navigation of the compensating intrinsic defects to maximize dopant solubility and efficiency.

 

Germanium telluride is a high performing thermoelectric material that additionally serves as a base for alloys such as GeTe–AgSbTe 2 and GeTe–PbTe. Such performance motivates exploration of other GeTe alloys in order understand the impact of site substitution on electron and phonon transport. In this work, we consider the root causes of the high thermoelectric performance material Ge 1− x Mn x Te. Along this alloy line, the crystal structure, electronic band structure, and electron and phonon scattering all depend heavily on the Mn content. Structural analysis of special quasirandom alloy structures indicate the thermodynamic stability of the rock salt phase over the rhombohedral phase with increased Mn incorporation. Effective band structure calculations indicate band convergence, the emergence of new valence band maxima, and strong smearing at the band edge with increased Mn content in both phases. High temperature measurements on bulk polycrystalline samples show a reduction in hole mobility and a dramatic increase in effective mass with respect to increasing Mn content. In contrast, synthesis as a function of tellurium chemical potential does not significantly impact electronic properties. Thermal conductivity shows a minimum near the rhombohedral to cubic phase transition, while the Mn Ge point defect scattering is weak as indicated by the low K L dependence on the Ge–Mn fraction (Fig. 10). From this work, alloys near this phase transition show optimal performance due to low thermal conductivity, moderate effective mass, and low scattering rates compared to Mn-rich compositions.