Debye Temperature
Debye temperature model supports formulas with up to 3 elements
an ensemble of 15 GNN models
Cite this model:
Si-Da Xue and Qi-Jun Hong, Materials Properties Prediction (MAPP): Empowering the Prediction of Material Properties Solely Based on Chemical Formulas, Materials, 2024. Download.
This model is currently deployed on Microsoft Azure and the Research Computing facilities at ASU. Due to network limit, computation may take up to 10 seconds.
Metrics
R2 training score: 0.97
R2 testing score: 0.91
Root mean square error, training: 26 Kelvin
Root mean square error, testing: 60 Kelvin
What is new
Version 1: ensemble of 15 deep learning models.
About this model

