Accelerating 2D MXenes Catalyst Discovery for Hydrogen Evolution Reaction by Computer-Driven Workflow and Ensemble Learning Strategy
2D MXenes materials have the versatile chemical composition, tunable layer thickness, and facile functionalization nature advantages, which could be used as catalysts for hydrogen evolution reaction (HER). However, tuning the thermal stability and activation of in-plane activity remains a challenge. We apply high-throughput density functional theory (DFT) calculation, together with ensemble learning framework, to identify 2D MXenes ordered binary alloys (OBAs) activity trends and guide HER catalyst design. 2D MXenes of Mn+1XnO2 (n=1,2,3; X=C, N) and M2M’X2O2, M2M’2X3O2 with 3d, 4d and 5d electrons OBAs HER catalysts were enumerated screening, followed by catalytic activity, thermal stability, and conductivity computations. Our results indicate that 110 kinds experimentally unexplored 2D MXenes OBAs with thermostability and outstanding HER activity surpassing that of noble metal platinum were selected. Especially, titanium element is mainly contained in the ideal catalyst of 2D MXenes OBAs, which is consistent with the MXenes prepared by experiments. Further, we show that the AdaBoost ensemble learning model developed descriptors could accurately predict and uncover the essential geometric and chemical origin of HER activity, which is very consistent with the electronic insights. The advanced research strategy, which combines high-throughput computing with ensemble learning, shows robust ability for evaluating the activity trends and designing new complicated catalysts.