Discovery of germanium-based hybrid perovskites with high photovoltaic performance with machine-learning.
Source check: Source checked. Not independent scientific confirmation.
Finding: XGBoost screened a large theoretical candidate set, and learned structure-property models narrowed the shortlist for first-principles evaluation. Four lead-free germanium-based candidates had calculated band gaps in a photovoltaic-relevant range; these are computational predictions, not synthesized materials or measured device performance.
Technology: XGBoost screens candidate compositions; learned structure-property models prioritize a shortlist for density-functional-theory evaluation.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Machine-learning screening enabled prioritization and computational characterization of specific candidate perovskites.
- Test and result
- Four candidate compositions had HSE+SOC-calculated indirect band gaps of approximately 1.17–1.75 eV after screening about 180,000 theoretical candidates.
- Limitation / still unknown
- Evidence is computational, with disagreement across learned models and DFT settings; no synthesis or photovoltaic-device performance was reported.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13690253/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary source full-text Methods and Results; version date and reported validation scope checked..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.