Catalyst Diffusion Transformer: Generative Inverse Design of Heterogeneous Catalysts
2026-07-27 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new computer model called CatDiT that can design catalysts—materials that speed up chemical reactions—by considering multiple desired features at once. Unlike previous models that focused on one property or small sets of materials, CatDiT can handle different catalyst types and predict how well they will work with different molecules. It learns simplified versions of catalyst structures to quickly generate new, valid candidate materials. When tested on making catalysts for nitrogen reduction, the model produced promising alloy candidates better than those commonly studied, showing it can help speed up the search for useful catalysts.
catalyst discoverygenerative modelsinverse designadsorbatebinding energyintermetallic alloysoxide surfaceslatent representationnitrogen reduction reaction (NRR)density functional theory (DFT)
Authors
Hayoung Doo, Dong Hyeon Mok, Seoin Back, Jonggeol Na
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.