Predicting tensorial molecular properties with equivariant machine learning models

Embedding molecular symmetries into machine-learning models is key for efficient learning of chemico-physical scalar properties, but little evidence on how to extend the same strategy tensorial quantities exists. Here we formulate a scalable equivariant model based local atomic environment descriptors. We apply it series molecules and show that accurate predictions can be achieved comprehensive list dielectric magnetic properties different ranks. These results are promising platform scope machine in materials modelling.