Employing Machine Learning to investigate properties of molecules and periodic systems
Title: Employing Machine Learning to investigate properties of molecules and periodic systems
SNIC Project: SNIC 2019/32-3
Project Type: SNIC Small Storage
Principal Investigator: Rodrigo Pereira de Carvalho <rodrigo.carvalho@physics.uu.se>
Affiliation: Uppsala universitet
Duration: 2019-11-01 – 2020-11-01
Classification: 10304 10403


Nowadays, it is a common sense on science that the interplay of Artificial Intelligence (more specifically by means of machine learning techniques) and first principles calculations can lead us to a breakthrough on materials design. Recent works has been employing machine learning to show the possibility to discover new materials [1], calculate physical properties without the high computational cost of prior techniques [2] and even to by-pass the solution of Quantum Mechanic equations [3]. For molecular systems, we can produce a high-accurate fingerprints to serve as inputs for machine learning, but for periodic systems (solids, surfaces, etc) we face some difficulties, besides new approachs has been developed [2,4]. However, the development of high quality data to be used in ML methods is imperative and it must be carefully checked before use in final projects. The specific goals for this project are: (I) Apply the machine learning machinery to molecular systems to improve and by-pass ab initio calculations. (ii) Development of high quality datasets for molecular and bulk systems using DFT calculations to be used in our ML code. (iii) Design a workflow interplayed with a state-of-the-art ML/Deep Learning code to design novel materials for energy storage/Lithium-Ion Batteries. 1. Balachandran, Prasanna V., et al. Physical Review Materials 2.4 (2018) 2. Faber, Felix, et al. International Journal of Quantum Chemistry 115.16 (2015) 3. Brockherde, Felix, et al. Nature communications 8.1 (2017) 4. Huo, Haoyan, and Matthias Rupp. "Unified representation for machine learning of molecules and crystals." preprint (2017).