There is a growing demand for the use of machine learning (ML) to derive fast-to-evaluate surrogate models of materials properties. In recent years, a broad array of materials property databases have emerged as part of a digital transformation of materials science. However, recent technological advances in ML are not fully exploited because of the insufficient volume and diversity of materials data. An ML framework called “transfer learning” has considerable potential to overcome the problem of limited amounts of materials data. Transfer learning relies on the concept that various property types, such as physical, chemical, electronic, thermodynamic, and mechanical properties, are physically interrelated. For a given target property to be predicted from a limited supply of training data, models of related proxy properties are pretrained using sufficient data; these models capture common features relevant to the target task. Repurposing of such machine-acquired features on the target task yields outstanding prediction performance even with exceedingly small data sets, as if highly experienced human experts can make rational inferences even for considerably less experienced tasks. In this study, to facilitate widespread use of transfer learning, we develop a pretrained model library called XenonPy.MDL. In this first release, the library comprises more than 140 000 pretrained models for various properties of small molecules, polymers, and inorganic crystalline materials. Along with these pretrained models, we describe some outstanding successes of transfer learning in different scenarios such as building models with only dozens of materials data, increasing the ability of extrapolative prediction through a strategic model transfer, and so on. Remarkably, transfer learning has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science; for example, our analysis has revealed underlying bridges between small molecules and polymers and between organic and inorganic chemistry.

Automated materials design with machine learning is increasingly common in recent years. Theoretically, it is characterized as black-box optimization in the space of candidate materials. Since the difficulty of this problem grows exponentially in the number of variables, designing complex materials is often beyond the ability of classical algorithms. We show how quantum annealing can be incorporated into automated materials discovery and conduct a proof-of-principle study on designing complex thermofunctional metamaterials. Our algorithm consists of three parts: regression for a target property by factorization machine, selection of candidate metamaterial based on the regression results, and simulation of the metamaterial property. To accelerate the selection part, we rely on the D-Wave 2000Q quantum annealer. Our method is used to design complex structures of wavelength selective radiators showing much better concordance with the thermal atmospheric transparency window in comparison to existing human-designed alternatives.

The pledge of achieving carbon peak before 2030 and carbon neutrality before 2060 is a strategic decision that responds to the inherent needs of China’s sustainable and high-quality development, and is an important driving force for promoting China’s ecological civilization constructions. As the consumption of fossil fuel energy is responsible for more than 90% of China’s greenhouse gases emissions, policies focusing on energy transition are vital for China accomplishing the goal of carbon neutrality. Considering the fact that China’s energy structure is dominated by fossil fuels, especially coal, it is urgent to accelerate the low-carbon transition of the energy system in a relatively short time, and dramatically increase the proportion of clean energy in the future energy supply. Although China has made notable progress in the clean energy transition in the past, its path to carbon neutrality still faces many significant challenges. During the process of energy transformation, advanced technologies and greater investment will play essential parts in this extensive and profound systemic reform for China’s economy and society. In the meantime, these changes will create immense economic opportunities and geopolitical advantages.

We demonstrate optimization of thermal conductance across nanostructures by developing a method combining atomistic Green’s function and Bayesian optimization. With an aim to minimize and maximize the interfacial thermal conductance (ITC) across Si-Si and Si-Ge interfaces by means of the $\mathrm{Si}/\mathrm{Ge}$ composite interfacial structure, the method identifies the optimal structures from calculations of only a few percent of the entire candidates (over 60 000 structures). The obtained optimal interfacial structures are nonintuitive and impacting: the minimum ITC structure is an aperiodic superlattice that realizes 50% reduction from the best periodic superlattice. The physical mechanism of the minimum ITC can be understood in terms of the crossover of the two effects on phonon transport: as the layer thickness in the superlattice increases, the impact of Fabry-Pérot interference increases, and the rate of reflection at the layer interfaces decreases. An aperiodic superlattice with spatial variation in the layer thickness has a degree of freedom to realize optimal balance between the above two competing mechanisms. Furthermore, the spatial variation enables weakening the impact of constructive phonon interference relative to that of destructive interference. The present work shows the effectiveness and advantage of material informatics in designing nanostructures to control heat conduction, which can be extended to other nanostructures and properties.

We computationally designed an ultranarrow-band wavelength-selective thermal radiator via a materials informatics method alternating between Bayesian optimization and thermal electromagnetic field calculation. For a given target infrared wavelength, the optimal structure was efficiently identified from over 8 billion candidates of multilayers consisting of multiple components (Si, Ge, and SiO₂). The resulting optimized structure is an aperiodic multilayered metamaterial exhibiting high and sharp emissivity with a Q-factor of 273. The designed metamaterials were then fabricated, and reasonable experimental realization of the optimal performance was achieved with a Q-factor of 188, which is significantly higher than those of structures empirically designed and fabricated in the past. This is the first demonstration of the experimental realization of metamaterials designed by Bayesian optimization. The results facilitate the machine-learning-based design of metamaterials and advance our understanding of the narrow-band thermal emission mechanism of aperiodic multilayered metamaterials.

Efficient multifunctional materials informatics enables the design of optimal graphene thermoelectrics.