Machine-learning-accelerated discovery of single-atom catalysts based on bidirectional activation mechanism

Abstract

Single-atom catalysts (SACs) have provided new impetus to the field of catalysis because of their high activity, high selectivity, and theoretically full utilization of active atoms. However, the ambiguous activation mechanism prevents a clear understanding of the structure-activity relationship and results in a great challenge of rational design of SACs. Herein, by combining density functional theory (DFT) calculations with machine learning (ML), we explore 126 SACs to analyze and develop the structure-activity relationship for the electrocatalytic nitrogen reduction reaction (NRR). We first propose a bidirectional activation mechanism with a new descriptor for catalytic activity, which provides new insights for the rational design of SACs. More importantly, we establish a ML model for predicting the catalytic performance of NRR, validated by both DFT calculations and experimental works. The successful ML prediction in this work helps with the accelerated design and discovery of new catalysts by computational screening with high practical significance. • A bidirectional activation mechanism is proposed for building catalytic theory • A new descriptor of N ie-d is applied for evalulating the catalytic activity for NRR • The developed ML model could predict the catalytic performance of SACs accurately Single-atom catalysts (SACs) have provided a new impetus to the field of catalysis. The key challenges in the development of SACs are to explore the structure-activity relationship and predict the catalytic performance of SACs. Our work addresses these challenges by examining a series of SACs supported on 2D materials via the combination of density functional theory (DFT) calculations and machine learning (ML). The proposed “bidirectional activation mechanism” not only explains some experimental results but also can be extended to other catalytic reactions, laying the foundations for constructing catalytic theory. Moreover, the developed ML model could predict the catalytic activity of SACs for the nitrogen reduction reaction with reliable accuracy, as validated by previous DFT and experimental work. This work provides new insights into catalysis theory and will accelerate the discovery of SACs, hugely influencing the real-world energy field. Singh and co-workers propose a bidirectional activation mechanism with a new descriptor of N ie-d for providing insights into catalysis on the basis of DFT calculations. Their developed ML model with high accuracy could accelerate the design of SACs for NRR.