A density-functional-theory-based and machine-learning-accelerated hybrid method for intricate system catalysis

Abstract

Being progressively applied in the design of highly active catalysts for energy devices, machine learning (ML) technology has shown attractive ability of dramatically reducing the computational cost of the traditional density functional theory (DFT) method, showing a particular advantage for the simulation of intricate system catalysis. Starting with a basic description of the whole workflow of the novel DFT-based and ML-accelerated (DFT-ML) scheme, and the common algorithms useable for machine learning, we presented in this paper our work on the development and performance test of a DFT-based ML method for catalysis program (DMCP) to implement the DFT-ML scheme. DMCP is an efficient and user-friendly program with the flexibility to accommodate the needs of performing ML calculations based on the data generated by DFT calculations or from materials database. We also employed an example of transition metal phthalocyanine double-atom catalysts as electrocatalysts for carbon reduction reaction to exhibit the general workflow of the DFT-ML hybrid scheme and our DMCP program.