Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates
This paper benchmarks 15 machine learning surrogate models on a large Phonix database to predict lattice thermal conductivity, revealing that while MLIP-embedded models excel in interpolation, deep neural networks like ALiEGNN offer superior robustness for out-of-distribution extrapolation, thereby enabling efficient high-throughput screening of thermoelectric materials at a fraction of the computational cost of first-principles simulations.
Zeyu Wang, Shuya Yamazaki, Martin Hoffmann Petersen, Masato Ohnishi, Tomiya Yamamoto, Wei Nong, Jianghai Wang, Ruiming Zhu, Masatoshi Hanai, Michimasa Morita, Toyotaro Suzumura, Zekun Ren, Junichiro S (…)2026-05-13🔬 cond-mat.mtrl-sci