An unsupervised disentangling autoencoder learns a latent dimension in optical absorption spectra that correlates with photovoltaic efficiency, reflects the direct-to-indirect gap transition, and accelerates simulated materials discovery.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning disentangled latent representations facilitates discovery and design of functional materials
An unsupervised disentangling autoencoder learns a latent dimension in optical absorption spectra that correlates with photovoltaic efficiency, reflects the direct-to-indirect gap transition, and accelerates simulated materials discovery.