Crystal materials design via physics-guided evolutionary multi-objective optimization with knowledge transfer

Abstract

The design of new crystal materials holds significant scientific value for societal advancement. Recent advancements in machine learning-based approaches have demonstrated considerable promise in the realm of crystal material design. However, their effectiveness relies heavily on the availability of high-quality and extensive training datasets, which are often challenging to collect in practice. To this end, we propose a novel physics-informed evolutionary transfer optimization framework that can design new crystal materials without necessitating extensive data. Specifically, we introduce a physics-informed encoding for materials, enabling the use of multi-objective evolutionary optimization to simultaneously optimize multiple physical objectives that are critical to the effective design of crystal materials, including the validity, properties, and energy of crystal materials. Additionally, to mitigate the slow optimization speed of evolutionary computation, we propose a physics-informed evolutionary transfer optimization technique to enhance the design speed of optimized materials. We conducted comprehensive experiments to analyze the designed crystals from the perspectives of validity, density functional theory (DFT) validation, formation energy, and energy above hull. The experimental results validate the immense potential of the proposed physics-informed multi-objective evolutionary optimization framework in crystal material design.