HydroBERT-MTL: deep semantic representation of incomplete tabular data for hydrogen uptake prediction
Journal of Materials Chemistry A · 2026
DOI: 10.1039/d6ta07972e ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Materials Chemistry A, 2026. Verfasst von Rui Luo und 7 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: Natural Science Foundation of Guangxi Zhuang Autonomous Region, Guangxi University of Science and Technology.
Abstract (Originalsprache)
HydroBERT-MTL integrates SciBERT-based semantic encoding with mask-aware numerical learning to deliver accurate and robust hydrogen-uptake prediction from literature-derived porous-carbon datasets with missing structural descriptors.
Förderung
- Natural Science Foundation of Guangxi Zhuang Autonomous Region
- Guangxi University of Science and Technology
Zitieren
APA
Luo, R., Zhang, Z., Xu, G., Li, H., Lin, X., Liu, R., Liu, J., & Dong, X. (2026). HydroBERT-MTL: deep semantic representation of incomplete tabular data for hydrogen uptake prediction. Journal of Materials Chemistry A. https://doi.org/10.1039/d6ta07972e
Vancouver
Luo R, Zhang Z, Xu G, Li H, Lin X, Liu R, et al. HydroBERT-MTL: deep semantic representation of incomplete tabular data for hydrogen uptake prediction. Journal of Materials Chemistry A. 2026. doi:10.1039/d6ta07972e
BibTeX
@article{Luo2026,
author = {Luo, Rui and Zhang, Ziliang and Xu, Guoxiao and Li, Hongli and Lin, Xiangbo and Liu, Rulong and Liu, Jinghua and Dong, Xinwei},
title = {HydroBERT-MTL: deep semantic representation of incomplete tabular data for hydrogen uptake prediction},
journal = {Journal of Materials Chemistry A},
year = {2026},
doi = {10.1039/d6ta07972e}
}
EUVIMED