Platform-conditioned machine learning and descriptor-group auditing for precursor additive discovery in perovskite solar cells
- 24 September 2026
- journal article
- Published by Royal Society of Chemistry (RSC) in Journal of Materials Chemistry A
- Vol. 14 (57) , 39462-39475
Abstract
Platform-conditioned machine learning enables auditable, in-domain prioritization of precursor additives from heterogeneous literature data. The selected additive 4-TBA improves perovskite solar-cell efficiency and reduces hysteresis.Keywords
Funding Information
- China University of Geosciences
This publication has 53 references indexed in Scilit:
- Data‐Driven Molecular Encoding for Efficient Screening of Organic Additives in Perovskite Solar CellsAdvanced Functional Materials, 2025
- Interfacial Coupling Induced Discrete Orientation of Epitaxial Graphene on High‐Index Cu SubstratesAdvanced Functional Materials, 2024
- Discovery of Lead‐Free Perovskites for High‐Performance Solar Cells via Machine Learning: Ultrabroadband Absorption, Low Radiative Combination, and Enhanced Thermal ConductivitiesAdvanced Science, 2021
- Predictions and Strategies Learned from Machine Learning to Develop High‐Performing Perovskite Solar CellsAdvanced Energy Materials, 2019
- Thermodynamic Stability Landscape of Halide Double Perovskites via High‐Throughput Computing and Machine LearningAdvanced Functional Materials, 2019
- Record Efficiency Stable Flexible Perovskite Solar Cell Using Effective Additive Assistant StrategyAdvanced Materials, 2018
- Humidity‐Induced Degradation via Grain Boundaries of HC(NH2)2PbI3 Planar Perovskite Solar CellsAdvanced Functional Materials, 2018
- Planar‐Structure Perovskite Solar Cells with Efficiency beyond 21%Advanced Materials, 2017
- Thin Insulating Tunneling Contacts for Efficient and Water‐Resistant Perovskite Solar CellsAdvanced Materials, 2016
- Unique Properties of Halide Perovskites as Possible Origins of the Superior Solar Cell PerformanceAdvanced Materials, 2014