4 papers
Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors
Akihiro Fujii, Yoshitaka Ushiku, Koji Shimizu +2
Advanced crystal design can accelerate materials discovery across applications from photovoltaics to spintronics. Practical design must satisfy multiple properties and physical con…
A Straightforward Gradient-Based Approach for High-Tc Superconductor Design: Leveraging Domain Knowledge via Adaptive Constraints
Akihiro Fujii, Anh Khoa Augustin Lu, Koji Shimizu +1
Materials design aims to discover novel compounds with desired properties. However, prevailing strategies face critical trade-offs. Conventional element-substitution approaches rea…
Machine-learning potential for phonon transport in AlN with defects in multiple charge states
Ying Dou, Koji Shimizu, Jesús Carrete +2
Understanding phonon transport properties in defect-laden AlN is important for their device applications. Here, we construct a machine-learning potential to describe phonon transpo…
Representing Born effective charges with equivariant graph convolutional neural networks
Alex Kutana, Koji Shimizu, Satoshi Watanabe +1
Graph convolutional neural networks have been instrumental in machine learning of material properties. When representing tensorial properties, weights and descriptors of a physics-…