Insights into Thermal Conductivity of Pnictogen Chalcogenides: Machine Learning Stereochemically Active Lone Pairs and Hybridization

Stereochemically active lone pairs (SCALPs) are pivotal in influencing the lattice thermal conductivity (κ_L), representing a critical aspect in formulating strategies for achieving high thermoelectric performance. Despite the transformative potential of the material genome paradigm for screening materials with tailored properties, accurately describing SCALPs in terms of performance indicators remains a challenge. In this machine learning (ML) study, we introduce specialized chemical bonding descriptors that capture the empirical hidden influence of SCALP and chemical bonding hierarchies in pnictogen chalcogenide materials. The ML model, trained with screened data sets from the Open Quantum Materials Database, the Materials Project, and experimental reports, achieved a significant reduction in test error scores by using chemical bonding descriptors over conventional features in predicting κ_L values for pnictogen chalcogenides. We predict five materials, MnTl₂As₂S₅, Ba₂As₂Se₅, Bi₁₄Te₁₃S₈, AgCu₂PbBiS₄, and Tl₂SnAs₂S₆, exhibiting ultralow κ_L values of ≤0.40 W m^–1 K^–1 at room temperature. Additionally, we specified the precise ranges for ionicity, hybridization, number mismatch, and polarizability required for ultralow κ_L for 245 newly predicted materials. Our data-driven approach not only identifies promising candidates with ultralow κ_L but also reveals new avenues for the design of pnictogen-based thermoelectric materials, emphasizing the crucial influence of lone pairs and hybridization.