Prompt Engineering Accelerates the Data‐Driven Discovery of Photocatalysts via an LLM‐Based Model Ensemble Strategy
Advanced Science · 2026-04 · 13 (24)
DOI: 10.1002/advs.202524215 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 16.02.2026. Verfasst von Dianyuan Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: Frontiers Science Centre for Flexible Electronics (FSCFE), MIIT Key Laboratory of Flexible Electronics (KLoFE), Shaanxi Key Laboratory of Flexible El…. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: key research program of Ningbo, National Foreign Expert Project.
Abstract (Originalsprache)
The overwhelming volume of unstructured scientific literature presents a fundamental bottleneck to materials discovery, where critical data on synthesis and properties remain locked in text. Here, a closed‐loop framework that integrates automated knowledge extraction with interpretable machine learning and targeted experimental validation is presented. This approach is centered on a novel data extraction pipeline, which combines a prompt‐engineered large language model with a model ensemble strategy, systematically optimized to interpret complex materials science narratives. When deployed to construct a database for defect‐engineered carbon nitride photocatalysts, the system achieved 90% accuracy and recall for key parameters. Analysis of the high‐fidelity dataset enabled reliable machine learning models to identify specific surface area (170 m 2 g −1 ) and bandgap (≈2.31 eV) as dominant performance parameters. Crucially, SHapley Additive exPlanations analysis elucidated a non‐monotonic relationship for bandgap, identifying an optimal range of 2.2–2.4 eV and quantifying the fundamental trade‐off between light absorption and charge recombination. These data‐driven insights guided the synthesis of representative materials, with experimental hydrogen evolution rates deviating by less than 5% from predictions. This work establishes a scalable and transferable paradigm, transforming fragmented literature into actionable intelligence and offering a powerful strategy for accelerating the development of functional materials.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Frontiers Science Centre for Flexible Electronics (FSCFE), MIIT Key Laboratory of Flexible Electronics (KLoFE), Shaanxi Key Laboratory of Flexible Electronics, Xi'an Key Laboratory of Flexible Electronics, Xi'an Key Lab…
- School of Economics and Management, Xi'an University of Posts and Telecommunications, Xi'an, Shaanxi, China.
- Key laboratory of Flexible Electronics of Zhejiang Province, Ningbo Institute of Northwestern Polytechnical University, Ningbo, China.
ORCID-Profile: Yuezhou Zhang
Förderung
- key research program of Ningbo
- National Foreign Expert Project
Zitieren
APA
Li, D., Sun, X., Sun, S., Wang, R., Zhang, M., Xiao, M., Wang, Y., & Zhang, Y. (2026). Prompt Engineering Accelerates the Data‐Driven Discovery of Photocatalysts via an LLM‐Based Model Ensemble Strategy. Advanced Science, 13(24). https://doi.org/10.1002/advs.202524215
Vancouver
Li D, Sun X, Sun S, Wang R, Zhang M, Xiao M, et al. Prompt Engineering Accelerates the Data‐Driven Discovery of Photocatalysts via an LLM‐Based Model Ensemble Strategy. Advanced Science. 2026;13(24). doi:10.1002/advs.202524215
BibTeX
@article{Li2026,
author = {Li, Dianyuan and Sun, Xichen and Sun, Shaohua and Wang, Runzhou and Zhang, Miaomiao and Xiao, Meng and Wang, Yue and Zhang, Yuezhou},
title = {Prompt Engineering Accelerates the Data‐Driven Discovery of Photocatalysts via an LLM‐Based Model Ensemble Strategy},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {24},
doi = {10.1002/advs.202524215}
}
EUVIMED