GuaPbI3 shows ultralow thermal conductivity of 0.088 W m^{-1} K^{-1} via lone-pair-induced lattice softness identified by ML-guided design and confirmed by synthesis, measurements, and DFT.
hub
Title resolution pending
5 Pith papers cite this work, alongside 1,003 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1,003
external citations · Crossref
hub tools
representative citing papers
A CNN predicts blurred EDS elemental maps from 4D-STEM diffraction data, with strong correlations for O and Te, but weak generalization evidence beyond one sample.
Supervised pretraining with surrogate class labels improves material property prediction on six Materials Project properties over self-supervised baselines, by 2 to 6.67 percent MAE.
On the Materials Project Battery Explorer dataset, CrabNet predicts gravimetric and volumetric capacity and average voltage from composition more accurately than MODNet or Magpie-random-forest.
A neural network potential trained on DFT data reproduces pair distribution functions for amorphous and amorphous porous palladium at system sizes far beyond ab initio limits.
citing papers explorer
-
Lone-Pair-Induced Lattice Softness Enables Ultralow Thermal Conductivity in Hybrid Organic-Inorganic Perovskite GuaPbI$_3$
GuaPbI3 shows ultralow thermal conductivity of 0.088 W m^{-1} K^{-1} via lone-pair-induced lattice softness identified by ML-guided design and confirmed by synthesis, measurements, and DFT.
-
Prediction of EDS Maps from 4DSTEM Diffraction Patterns Using Convolutional Neural Networks
A CNN predicts blurred EDS elemental maps from 4D-STEM diffraction data, with strong correlations for O and Te, but weak generalization evidence beyond one sample.
-
Supervised Pretraining for Material Property Prediction
Supervised pretraining with surrogate class labels improves material property prediction on six Materials Project properties over self-supervised baselines, by 2 to 6.67 percent MAE.
-
Machine Learning for Electrode Materials: Property Prediction via Composition
On the Materials Project Battery Explorer dataset, CrabNet predicts gravimetric and volumetric capacity and average voltage from composition more accurately than MODNet or Magpie-random-forest.
-
Harnessing Artificial Intelligence for Modeling Amorphous and Amorphous Porous Palladium: A Deep Neural Network Approach
A neural network potential trained on DFT data reproduces pair distribution functions for amorphous and amorphous porous palladium at system sizes far beyond ab initio limits.