CatDiT is presented, a unified framework for inverse catalyst design that generates valid and novel structures ranging from intermetallic alloys to oxide surfaces and establishes CatDiT as a practical and scalable approach for property-directed catalyst inverse design and targeted catalyst generation.
Abstract
The vast chemical design space and complex, interdependent design variables make catalyst discovery for targeted properties highly labor- and resource-intensive. Although generative models have emerged as a promising solution, existing approaches are generally limited to single-property conditioning or narrow chemical spaces. Here, we present Catalyst Diffusion Transformer (CatDiT), a unified framework for inverse catalyst design that generates valid and novel structures ranging from intermetallic alloys to oxide surfaces. By learning compressed latent representations, CatDiT enables efficient training and rapid sampling while supporting simultaneous conditioning on adsorbate type, binding energy, and catalyst class. The model provides reliable control of discrete properties and directional control of continuous properties, enriching candidate pools for reaction-specific catalyst discovery. As a representative application, multi-conditional generation for the nitrogen reduction reaction (NRR) yields 28 density functional theory (DFT)-relaxed alloy candidates that satisfy the target activity window and lie above the pure-metal *N-*H scaling line, corresponding to a ~1.5-fold enrichment over the source distribution. These results establish CatDiT as a practical and scalable approach for property-directed catalyst inverse design and targeted catalyst generation.
A mechanism-driven approach to alleviate data dependence and develop a multisource transfer learning (MS-TL) framework that leverages the knowledge embedded in abundant adsorption data sets while accurately capturing local structural dependence, enabling a deep fusion of multidimensional thermodynamic knowledge while preserving local structural information.
Wangqiang Lin, Huiyan Zhang, Jinxin Sun et al.· Journal of the American Chem...· 0 citations
A data-driven framework combining explainable machine learning (ML) with large-scale virtual library generation with large-scale virtual library generation is presented, establishing a practical route from experimental data to actionable catalyst designs.
Xuefeng Li, Haoke Qiu, Hanwen Pei et al.· Journal of Physical Chemistr...· 0 citations
Selective oxidation of methane to methanol under mild conditions remains a "holy grail" in chemical manufacturing, constrained not only by the inertness of the C-H bond but also by the difficulty of controlling highly reactive intermediates once methane is activated. Plasma activation provides a nonequilibrium reaction environment in which methyl radicals are generated independently of the catalytic surface, effectively bypassing surface-mediated C-H activation. However, this shifts the bottleneck to subsequent interfacial chemistry, where radical interception, product selectivity, and catalyst stability impose competing constraints. Here, we introduce a plasma-electrochemical reaction framework coupled with a generative catalyst discovery strategy to navigate this multiobjective landscape. By integrating graph-neural-network-accelerated evaluation with generative exploration across a multimetallic alloy space spanning ∼1029 possible configurations, the framework identifies transferable catalytic motifs rather than individual compositions. This process reveals an emergent catalytic architecture consisting of an Ag-rich matrix with isolated Pd/Pt sites, which provide localized reactivity for radical interception and C-O bond formation while maintaining weak oxygen affinity that suppresses overoxidation. Guided by this motif-level principle, we identify experimentally realizable Ag3Pd and Ag3Pt catalysts. In a hybrid plasma-electrocatalytic system, Ag3Pd achieves a methanol faradaic efficiency of up to 80.1% at ∼1.7 mA cm-2 with a productivity of 64.5 μmol·cm-2·h-1, outperforming previously reported plasma-assisted and electrochemical methane conversion systems. More broadly, this work demonstrates how generative algorithms can uncover emergent catalytic architectures across vast chemical spaces.
Chengyi Zhang, Qiang Song, Wanping Xu et al.· Journal of the American Chem...· 0 citations
It is shown that explainable artificial intelligence (XAI) provides a transformative approach by connecting model predictions to interpreting chemical descriptors, structural motifs, and reaction features, and it is reshaping data-driven catalysis from opaque prediction toward mechanism-informed catalyst design.
Zixuan Geng, Di Wu, Xu Zhao et al.· Academia Catalysis· 0 citations
Emerging opportunities in physics-informed machine learning, graph neural networks, generative artificial intelligence, active learning, and autonomous closed-loop DFT-ML-MKM workflows are discussed as promising directions for accelerating the discovery of next-generation electrocatalysts with enhanced activity, selectivity, and long-term stability.
Swetarekha Ram, Shalini Tomar, S. Bhattacharjee· Chemical Communications· 0 citations
Ru‐based solid‐solution alloys have emerged as attractive substitutes for Pt‐based electrocatalysts in the alkaline hydrogen evolution reaction (HER). However, the vast compositional space of these alloys hinders rapid catalyst discovery. Existing machine‐learning design strategies are largely based on idealized simulation data, limiting their experimental relevance and screening efficiency. Herein, we develop an interpretable machine‐learning framework informed by experiment to facilitate the rapid screening of Ru‐based HER electrocatalysts. Built on an experimental dataset, the framework integrates electronic descriptors, interpretability analysis, a Bayesian‐optimized surrogate model and uncertainty‐aware ranking to efficiently identify promising compositions. Interpretability analysis identifies V, Co, and Ru as the key elements governing catalytic performance, whereas the surrogate model maps HER activity across the ternary alloy space to define a confined high‐performance composition window. Guided by this framework, the optimized V
17
Co
31
Ru
52
catalyst exhibits an overpotential of 61.7 mV at a current density of 100 mA·cm
−2
in 1 M KOH, while maintaining stable operation for 260 h under the same current density. This work provides a rapid, interpretable and experimentally relevant strategy for discovering high‐performance alkaline HER electrocatalysts.
Jing Yang, Jun Yu, Jianming Cai et al.· Materials Genome Engineering...· 0 citations