EUVIMEDEUVIMED entdecken
Crossref

Physics‐Aware Hybrid Equivariant Graph Neural Networks for Robust Design of Inorganic Perovskite Photodetector

Shiyang Lei, Baoyi An, Guoqiang Peng, Xiangzheng Chen, Hao Jia, Zhiwen Jin

Advanced Optical Materials · 2026-05 · 14 (18)

DOI: 10.1002/adom.202502871 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Optical Materials, online erschienen am 24.04.2026. Verfasst von Shiyang Lei und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Gansu Province, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inorganic ABX 3 perovskites have exceptional optoelectronic properties, yet efficiently navigating their vast chemical space for high‐performance photodetectors remains challenged by the trade‐off between computational fidelity and screening efficiency. To overcome this bottleneck, we develop a hierarchical physics‐aware graph neural network (PAGNN) framework featuring a novel Dynamic RBF Modulation mechanism. Our model achieves deep coupling of chemical priors with geometric equivariance. Crucially, we implement a three‐stage curriculum learning strategy to bridge the fidelity gap between standard PBE and high‐precision mBJ functionals. For photodetector and optoelectronic applications, we predict band gaps and formation energies as well as hull energies, achieving mean absolute errors of 0.11 eV and 0.06 eV/atom, respectively. Validation Structure‐Unseen Split protocol demonstrates the model's superior structural inference capability. Applying our model to screen promising ABX 3 candidates and guide the continuous compositional engineering of solid solutions, we recover known high‐performance perovskites and identify novel compounds for optoelectronic integration. Ultimately, this work establishes a generalizable, data‐efficient, and interpretable paradigm for accelerated materials discovery.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Gansu Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Lei, S., An, B., Peng, G., Chen, X., Jia, H., & Jin, Z. (2026). Physics‐Aware Hybrid Equivariant Graph Neural Networks for Robust Design of Inorganic Perovskite Photodetector. Advanced Optical Materials, 14(18). https://doi.org/10.1002/adom.202502871

Vancouver

Lei S, An B, Peng G, Chen X, Jia H, Jin Z. Physics‐Aware Hybrid Equivariant Graph Neural Networks for Robust Design of Inorganic Perovskite Photodetector. Advanced Optical Materials. 2026;14(18). doi:10.1002/adom.202502871

BibTeX
@article{Lei2026,
  author = {Lei, Shiyang and An, Baoyi and Peng, Guoqiang and Chen, Xiangzheng and Jia, Hao and Jin, Zhiwen},
  title = {Physics‐Aware Hybrid Equivariant Graph Neural Networks for Robust Design of Inorganic Perovskite Photodetector},
  journal = {Advanced Optical Materials},
  year = {2026},
  volume = {14},
  number = {18},
  doi = {10.1002/adom.202502871}
}
Kostenlos starten →