Autonomous Discovery of Multi‐Material Metamaterials With Programmable Multimodal Thermal Responses via Reinforcement Learning
Advanced Materials · 28.10.2026
DOI: 10.1002/adma.75546 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 28.10.2026. Verfasst von Chenxi Lu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Research Centre for Laser Extreme Manufacturing, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China. Die Arbeit nennt 60 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Postdoctoral Fellowship Program of CPSF.
Abstract (Originalsprache)
Inverse design deep learning models have significantly accelerated materials discovery through mapping complex structure‐property relationships. However, they remain constrained by prohibitive data demands and are limited to in‐distribution interpolation designs. Efficient out‐of‐distribution inverse design under sparse data constraints remains a critical bottleneck. Here we present an inverse design framework integrating Transformer encoder with reinforcement learning (RL) agent. By combining adaptable structural parameterization and hybrid iterative optimization, this framework efficiently navigates the complex, high‐dimensional multi‐material design landscape with extremely low data dependency (
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Centre for Laser Extreme Manufacturing, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China.
- Graduate School of Environmental Studies, Tohoku University, Sendai, Japan.
ORCID-Profile: Muhammad Aziz, Chao Wei
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Postdoctoral Fellowship Program of CPSF
- Zhejiang Provincial Natural Science Foundation
- Natural Science Foundation of Ningbo
- Natural Science Foundation of Zhejiang Province
- Natural Science Foundation of Ningbo Municipality
Zitieren
APA
Lu, C., Pan, K., Li, X., Qiu, Z., Chai, N., Gao, X., Aziz, M., Li, L., & Wei, C. (2026). Autonomous Discovery of Multi‐Material Metamaterials With Programmable Multimodal Thermal Responses via Reinforcement Learning. Advanced Materials. https://doi.org/10.1002/adma.75546
Vancouver
Lu C, Pan K, Li X, Qiu Z, Chai N, Gao X, et al. Autonomous Discovery of Multi‐Material Metamaterials With Programmable Multimodal Thermal Responses via Reinforcement Learning. Advanced Materials. 2026. doi:10.1002/adma.75546
BibTeX
@article{Lu2026,
author = {Lu, Chenxi and Pan, Kewen and Li, Xingran and Qiu, Zhaohui and Chai, Nianyao and Gao, Xuehao and Aziz, Muhammad and Li, Lin and Wei, Chao},
title = {Autonomous Discovery of Multi‐Material Metamaterials With Programmable Multimodal Thermal Responses via Reinforcement Learning},
journal = {Advanced Materials},
year = {2026},
doi = {10.1002/adma.75546}
}
EUVIMED