Prompt Engineering Accelerates the Data‐Driven Discovery of Photocatalysts via an LLM‐Based Model Ensemble Strategy
Year: 2026
Type: article
Abstract: ABSTRACT 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.
Source: Advanced Science
Authors: Dianyuan Li, Xichen Sun, Shaohua Sun, Runzhou Wang, Miaomiao Zhang, Meng Xiao, Yue Wang, Yuezhou Zhang
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $6,730
OpenAlex ID: W7129042869