Equivariant Parameter Sharing for Porous Crystalline Materials
This work addresses the need for efficient high-throughput screening in materials science, though it is incremental as it builds on existing crystal property prediction methods.
The paper tackled the problem of predicting properties of porous crystalline materials by developing a model that incorporates unit cell symmetries and explicitly models porous structures, resulting in better performance than existing methods and more efficient modeling.
Efficiently predicting properties of porous crystalline materials has great potential to accelerate the high throughput screening process for developing new materials, as simulations carried out using first principles model are often computationally expensive. To effectively make use of Deep Learning methods to model these materials, we need to utilize the symmetries present in the crystals, which are defined by their space group. Existing methods for crystal property prediction either have symmetry constraints that are too restrictive or only incorporate symmetries between unit cells. In addition, these models do not explicitly model the porous structure of the crystal. In this paper, we develop a model which incorporates the symmetries of the unit cell of a crystal in its architecture and explicitly models the porous structure. We evaluate our model by predicting the heat of adsorption of CO$_2$ for different configurations of the mordenite zeolite. Our results confirm that our method performs better than existing methods for crystal property prediction and that the inclusion of pores results in a more efficient model.