Our research objectives involve the development of theoretical methods to address existing limitations in quantum chemistry and to offer theoretical insights into macroscopic systems through the application of machine learning at ab initio level. 

​

 We develope a highly-scalable universal sparse Gaussian process regression (SGPR) machine learning potential for all known compounds. The ultimate objective is to refine the SGPR methods for direct simulations of macroscopic systems by incorporating various factors at the ab initio level, such as light-electron interactions, oxidation/reduction, charging/discharging, absorption/emission, and external voltage.

​

This groundbreaking methodology can be applied to various fields such as physics, chemistry, biology, and energy materials, enabling the study of large-scale phenomena that were previously hard to access.