fig3

PINK: physical-informed machine learning for lattice thermal conductivity

Figure 3. The web page for our PINK app is divided into two panels. The left panel allows users to upload files, while the right panel displays the results. The output includes a DataFrame that lists various properties such as the number of atoms, density (g/cm-3), volume (Å3), atomic mass (amu), bulk modulus (GPa), shear modulus (GPa), transverse and longitudinal wave sound velocities (m/s), speed of sound (m/s), Poisson’s ratio (v), Grüneisen parameter (γ), acoustic Debye temperature (θa, K), and lattice thermal conductivity (W·m-1·K-1). For detailed instructions on using PINK, please refer to the PINK_tutorial.mp4. Additionally, the app supports custom functions for calculating bulk modulus (GPa), shear modulus (GPa), and Grüneisen parameter, with a separate tutorial available in PINK_Custom_Parameters_tutorial.mp4. PINK: Physical-informed kappa.

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/