Potential energy surface prediction of Alumina polymorphs using graph neural network

Sanyal, Subrata; Sagotra, Arun K.; Kumar, Narendra; Rathi, Sharad; Krishna, M. Bala; Somayajula, Nagesh; Palanisamy, Duraivelan; Ratnakar, Ram R.; Sanyal, Sankar P.; Talukdar, Partha; Waghmare, Umesh V.; Balachandran, Janakiraman

doi:10.48550/arxiv.2301.12059

Cited by 1 publication

(1 citation statement)

References 23 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, incorporating long-range interactions in GCNN models is challenging due to the computational cost to run DFT calculations on crystal structures large enough to accurately capture them. Recent work described in [42] has developed GCNN models for transferable potential energy surface prediction of alumina polymorphs across different lattice sizes and crystal structures and by fixing the chemical composition of the material. This work sheds light on promising transferability property of GCNN models, and encourages further research to assess the transferability of GCNN predictions for other classes of materials, such as solid solution alloys, and to extend the transferability study by spanning several chemical compositions of the material.…”

Section: Introductionmentioning

confidence: 99%

Transferring predictions of formation energy across lattices of increasing size*

Lupo Pasini,

Karabin,

Eisenbach

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

In this study, we show the transferability of graph convolutional neural network (GCNN) predictions of the formation energy of the nickel-platinum (NiPt) solid solution alloy across atomic structures of increasing sizes. The original dataset was generated with the Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) using the second nearest-neighbor modified embedded-atom method (2NN MEAM) empirical interatomic potential. Geometry optimization was performed on the initially randomly generated face centered cubic (FCC) crystal structures and the formation energy has been calculated at each step of the geometry optimization, with configurations spanning the whole compositional range. Using data from various steps of the geometry optimization, we first trained our open-source, scalable implementation of GCNN called HydraGNN on a lattice of 256 atoms, which accounts well for the short-range interactions. Using this data, we predicted the formation energy for lattices of 864 atoms and 2,048 atoms, which resulted in lower-than-expected accuracy due to the long-range interactions present in these larger lattices. We accounted for the long-range interactions by including a small amount of training data representative for those two larger sizes, whereupon the predictions of HydraGNN scaled linearly with the size of the lattice. Therefore, our strategy ensured scalability while reducing significantly the computational cost of training on larger lattice sizes.

show abstract

Section: Introductionmentioning

confidence: 99%