Human–AI collaboration for modeling heat conduction in nanostructures

Materials informatics, which combines data science and artificial intelligence (AI), has garnered significant attention owing to its ability to accelerate material development. However, human involvement is often limited to the initiation and oversight of machine learning processes and rarely includes roles that capitalize on human intuition or domain expertise. In this study, taking the problem of heat conduction in a two-dimensional nanostructure as a case study, an integrated human-AI collaboration framework is designed and used to construct a model to predict the thermal conductivity. This approach is used to determine the parameters that govern phonon transmission over frequencies and incidence angles. The self-learning entropic population annealing technique, which combines entropic sampling with a surrogate machine learning model, generates a global dataset that can be interpreted by a human. This allows humans to develop parameters with physical interpretations, which can guide nanostructural design for specific properties.