← 研踪 PaperTrailarXiv:2611.18043 · v1
Enrichment-Oriented Virtual Screening of Perovskite Solar Cells through Reinforcement Learning
首次提交 2026-11-13 19:13
版本更新 2026-11-13 19:13
雷达观测 2026-11-16 11:42
摘要
Experimental optimization of perovskite solar cells is constrained by combinatorial diversity in absorber compositions, device layers, and processing, which makes virtual screening attractive for prioritizing recipes before fabrication. We develop a surrogate-guided reinforcement-learning framework that casts recipe generation as virtual screening, enriching candidate shortlists near high-performing experimental neighbors. A frozen Tabular Prior-data Fitted Network (TabPFN) guides recipe generation, while a reference pool of 890 measured devices enables neighborhood-based assessment. Five-fold evaluation on 1,846 devices shows top-ten selection raises mean power conversion efficiency (PCE) from 19.68\% to 23.74\%. Three learned policies are compared with six baselines under 3,000 surrogate evaluations per run. In top-100 shortlists, Proximal policy optimization (PPO) and recurrent PPO (RPPO) achieve neighborhood-supported hit rates of 23\% and 24\% (7.9- and 8.3-fold Pure Random's 2.9\%), versus 10\% (3.4-fold) for the baselines with the highest supported hit rate (L-SHADE and Ax BO, tied) at . Gains coexist with weak-support fractions. Of 9,000 recipes, 65.4\% match a composition family at similarity 0.80, falling to 11.7\% at 0.90. Results support enrichment-oriented prioritization but not experimental performance, seed robustness, or matched-budget advantage.
作者备注:55 pages, 9 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-13 19:13 · 最新观测版本
Enrichment-Oriented Virtual Screening of Perovskite Solar Cells through Reinforcement Learning
Experimental optimization of perovskite solar cells is constrained by combinatorial diversity in absorber compositions, device layers, and processing, which makes virtual screening attractive for prioritizing recipes before fabrication. We develop a surrogate-guided reinforcement-learning framework that casts recipe generation as virtual screening, enriching candidate shortlists near high-performing experimental neighbors. A frozen Tabular Prior-data Fitted Network (TabPFN) guides recipe generation, while a reference pool of 890 measured devices enables neighborhood-based assessment. Five-fold evaluation on 1,846 devices shows top-ten selection raises mean power conversion efficiency (PCE) from 19.68\% to 23.74\%. Three learned policies are compared with six baselines under 3,000 surrogate evaluations per run. In top-100 shortlists, Proximal policy optimization (PPO) and recurrent PPO (RPPO) achieve neighborhood-supported hit rates of 23\% and 24\% (7.9- and 8.3-fold Pure Random's 2.9\%), versus 10\% (3.4-fold) for the baselines with the highest supported hit rate (L-SHADE and Ax BO, tied) at . Gains coexist with weak-support fractions. Of 9,000 recipes, 65.4\% match a composition family at similarity 0.80, falling to 11.7\% at 0.90. Results support enrichment-oriented prioritization but not experimental performance, seed robustness, or matched-budget advantage.
查看此版本解读 →查看此版本原文 ↗