A backward-mapping framework with chemical-genome descriptors and ML reduces 13,088 compositions to seven DFT-validated lead-free double perovskite candidates with phase stability and functional electronic properties.
Instead of using machine learning only to rank compositions, the workflow starts from device-relevant targets and maps them back to chemically meaningful descriptor families
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Backward Mapping from Device Targets to Chemical Genomes for Interpretable Discovery of Phase-Stable Lead-Free Double Perovskites with DFT-Validated Design Rules
A backward-mapping framework with chemical-genome descriptors and ML reduces 13,088 compositions to seven DFT-validated lead-free double perovskite candidates with phase stability and functional electronic properties.