Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: AI4Science, Mila, :, Hernandez-Garcia, Alex, Duval, Alexandre, Volokhova, Alexandra, Bengio, Yoshua, Sharma, Divya, Carrier, Pierre Luc, Benabed, Yasmine, Koziarski, Michał, Schmidt, Victor, Rignanese, Gian-Marco, De Breuck, Pierre-Paul, Clancy, Paulette
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.04925
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915832439767040
author AI4Science, Mila
:
Hernandez-Garcia, Alex
Duval, Alexandre
Volokhova, Alexandra
Bengio, Yoshua
Sharma, Divya
Carrier, Pierre Luc
Benabed, Yasmine
Koziarski, Michał
Schmidt, Victor
Rignanese, Gian-Marco
De Breuck, Pierre-Paul
Clancy, Paulette
author_facet AI4Science, Mila
:
Hernandez-Garcia, Alex
Duval, Alexandre
Volokhova, Alexandra
Bengio, Yoshua
Sharma, Divya
Carrier, Pierre Luc
Benabed, Yasmine
Koziarski, Michał
Schmidt, Victor
Rignanese, Gian-Marco
De Breuck, Pierre-Paul
Clancy, Paulette
contents The discovery of novel solid-state materials, such as electrocatalysts, super-ionic conductors, or photovoltaic materials, plays a critical role in addressing various global challenges. It has, for instance, the potential to significantly improve the efficiency of renewable energy production and storage, thereby making substantial contributions to climate crisis mitigation strategies. In this paper, we introduce Crystal-GFN, a generative model of crystal structures possessing desirable properties and constraints. Operating as a multi-environment, continuous-discrete GFlowNet, it sequentially samples structural attributes of crystalline materials, namely space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physicochemical and geometric hard constraints. We demonstrate the capabilities of Crystal-GFN to efficiently discover diverse and valid crystals with various properties: low predicted formation energy (median -3.2 eV/atom), band gap close to a target value and high density. Overall, Crystal-GFN is a crystal generation method that addresses several existing challenges in the literature and opens promising paths for accelerating materials discovery with machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2310_04925
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Crystal-GFN: sampling crystals with desirable properties and constraints
AI4Science, Mila
:
Hernandez-Garcia, Alex
Duval, Alexandre
Volokhova, Alexandra
Bengio, Yoshua
Sharma, Divya
Carrier, Pierre Luc
Benabed, Yasmine
Koziarski, Michał
Schmidt, Victor
Rignanese, Gian-Marco
De Breuck, Pierre-Paul
Clancy, Paulette
Machine Learning
The discovery of novel solid-state materials, such as electrocatalysts, super-ionic conductors, or photovoltaic materials, plays a critical role in addressing various global challenges. It has, for instance, the potential to significantly improve the efficiency of renewable energy production and storage, thereby making substantial contributions to climate crisis mitigation strategies. In this paper, we introduce Crystal-GFN, a generative model of crystal structures possessing desirable properties and constraints. Operating as a multi-environment, continuous-discrete GFlowNet, it sequentially samples structural attributes of crystalline materials, namely space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physicochemical and geometric hard constraints. We demonstrate the capabilities of Crystal-GFN to efficiently discover diverse and valid crystals with various properties: low predicted formation energy (median -3.2 eV/atom), band gap close to a target value and high density. Overall, Crystal-GFN is a crystal generation method that addresses several existing challenges in the literature and opens promising paths for accelerating materials discovery with machine learning.
title Crystal-GFN: sampling crystals with desirable properties and constraints
topic Machine Learning
url https://arxiv.org/abs/2310.04925