High‐Throughput Screening of Electrocatalysts for Nitrogen Reduction Reactions Accelerated by Interpretable Intrinsic Descriptor

Abstract

Developing easily accessible descriptors is crucial but challenging to rationally design single‐atom catalysts (SACs). This paper describes a simple and interpretable activity descriptor, which is easily obtained from the atomic databases. The defined descriptor proves to accelerate high‐throughput screening of more than 700 graphene‐based SACs without computations, universal for 3–5d transition metals and C/N/P/B/O‐based coordination environments. Meanwhile, the analytical formula of this descriptor reveals the structure–activity relationship at the molecular orbital level. Using electrochemical nitrogen reduction as an example, this descriptor's guidance role has been experimentally validated by 13 previous reports as well as our synthesized 4 SACs. Orderly combining machine learning with physical insights, this work provides a new generalized strategy for low‐cost high‐throughput screening while comprehensive understanding the structure‐mechanism‐activity relationship.

Activity and Selectivity Roadmap for C–N Electro-Coupling on MXenes

“…The formula for general descriptors E ad‑CO and E ad‑N were identified using the SISSO method, a ML method with an exceptional performance on huge-dimensional space. SISSO has been utilized to predict surface adsorption energy across a wide range of materials, including single metal atoms, metal alloys, and oxides. − Its excellent predictive accuracy underscores its suitability in our study. DFT database was used as the training data.…”

Machine Learning Design of Single-Atom Catalysts for Nitrogen Fixation

“…30,31 Furthermore, by combining the data sets obtained from high-throughput computation with ML techniques, it is possible to bypass the laborious calculation process, precisely identify the promising structures, and significantly reduce the resources required for high-precision calculations. 32,33 The design and implementation of the high-performance reaction system are thus guided. Herein, we propose a systematic and efficient strategy for the rational design of TM SACs for NRR, as illustrated in Figure 1.…”

“…To accelerate the discovery and optimization of efficient catalysts, high-throughput computation has been combined with machine learning (ML) techniques. , High-throughput computation employs computational models and algorithms to rapidly evaluate numerous potential catalyst compositions, structures, and catalytic performances; this significantly reduces the time and cost required for traditional trial-and-error experiments. , Simultaneously, ML algorithms analyze and learn from extensive computational results and experimental data. , By uncovering hidden patterns and trends within the data, these algorithms identify crucial features that impact the catalyst’s performance. , Furthermore, by combining the data sets obtained from high-throughput computation with ML techniques, it is possible to bypass the laborious calculation process, precisely identify the promising structures, and significantly reduce the resources required for high-precision calculations. , The design and implementation of the high-performance reaction system are thus guided.…”

Optimizing Electrocatalytic Nitrogen Reduction via Interfacial Electric Field Modulation: Elevating d‐Band Center in WS2‐WO3 for Enhanced Intermediate Adsorption

“…[1][2][3] However, the conventional Haber-Bosch process, which dominates industrial ammonia synthesis, requires high temperature and pressure, resulting in a significant environmental impact. [4][5][6] To address this issue, electrocatalytic nitrogen reduction reaction (ENRR) is being considered as an alternative approach to produce NH 3 under mild conditions, which is more sustainable and environmentally friendly. [7][8][9] However, the sluggish reaction kinetics significantly limit the activity and selectivity of ENRR.…”

“…Ammonia (NH 3 ) is an indispensable chemical in agriculture, chemical industry, refrigeration, hydrogen energy and healthcare [1–3] . However, the conventional Haber‐Bosch process, which dominates industrial ammonia synthesis, requires high temperature and pressure, resulting in a significant environmental impact [4–6] . To address this issue, electrocatalytic nitrogen reduction reaction (ENRR) is being considered as an alternative approach to produce NH 3 under mild conditions, which is more sustainable and environmentally friendly [7–9] .…”