Guest Editors
Dr. Yaping Qi
Email: qi.yaping.a2@tohoku.ac.jp
Affiliation: Advanced Institute for Materials Research (WPI-AIMR), Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai 980-8577, Japan
Homepage:
Research Interests: AI and material analysis, material science, biotech, machine learning
Summary
The issue introduction includes the background and the importance of this research area.
The application of artificial intelligence (AI) in materials science has become a transformative approach for accelerating discovery, characterization, and optimization of functional materials. In particular, the concept of "materials data neighborhoods"—which emphasizes local atomic environments, interfacial interactions, and structural motifs—provides a powerful framework to capture complex structure–property relationships in data-rich domains. This is especially relevant to two-dimensional (2D) quantum materials and van der Waals heterostructures, where subtle variations in stacking, strain, or symmetry can significantly alter material behavior. As the volume of experimental and computational data continues to grow, there is an urgent need to develop robust AI methods that can interpret, learn from, and make physically grounded predictions based on this localized structural information.
The aim and scope of the Special Issue shall be highlighted.
This Special Issue aims to gather cutting-edge research that leverages AI and statistical learning for the interpretation and prediction of local material environments, with particular emphasis on low-dimensional, quantum, and data-intensive materials systems. The scope includes but is not limited to AI-guided Raman and spectroscopy analysis, local descriptor engineering, inverse materials design, and predictive modeling of functional properties. We seek interdisciplinary contributions at the interface of materials science, condensed matter physics, and computational intelligence, especially those that bridge AI models with physical interpretability and experimental validation.
Suggested themes shall be listed.
·AI-assisted spectroscopy (Raman, PL, ARPES) and microscopy interpretation
·Structure–property mapping based on local descriptors or data neighborhoods
·Deep learning models for ferroelectric and piezoelectric prediction in 2D materials
·Twist angle recognition and strain analysis in van der Waals heterostructures
·Generative and inverse design of low-dimensional quantum materials
·Explainable AI and uncertainty quantification in physical modeling
·Integration of AI with high-throughput synthesis and characterization pipelines
·AI-driven analysis of interfacial phenomena and phase transitions in quantum systems
Keywords
AI in materials science, data-driven discovery, materials data neighborhood, deep learning, 2d materials, structure-property relationships, spectroscopy analysis, generative models, van der waals materials, quantum materials
Login
Register
Submit a Paper
Propose a Special lssue