arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05372cond-mat.mtrl-sci
收藏

CatFlow:通过流匹配共生成层-吸附质系统

CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Minkyu Kim, Nayoung Kim, Honghui Kim, Sungsoo Ahn

AI总结:

本研究提出CatFlow框架,通过流匹配方法实现异质催化剂的从头设计和结构预测,提升了生成催化剂的结构保真度和吸附能分布的准确性。

摘要:

发现针对特定反应中间体定制的异质催化剂仍然是材料科学中的基本瓶颈。虽然传统试错方法和最近的生成模型已显示出前景,但它们难以捕捉表面几何形状与吸附质相互作用之间的内在耦合。为了解决这一限制,我们提出了CatFlow,一种基于流匹配的框架,用于异质催化剂的从头设计和结构预测。我们的模型基于原始单元格的因子化表示来操作层-吸附质复合物,通过将可学习变量的数量减少约9.2倍,同时显式编码层-吸附质界面的表面取向。在Open Catalyst 2020数据集上的实验表明,与自回归和顺序基线相比,CatFlow显著提高了生成催化剂的结构保真度。进一步的实验显示,生成的结构能够准确捕捉物理上合理界面的吸附能分布,并更接近热力学局部极小值。

英文摘要:

Discovering heterogeneous catalysts tailored for specific reaction intermediates remains a fundamental bottleneck in materials science. While traditional trial-and-error methods and recent generative models have shown promise, they struggle to capture the intrinsic coupling between surface geometry and adsorbate interactions. To address this limitation, we propose CatFlow, a flow matching-based framework for de novo design and structure prediction of heterogeneous catalysts. Our model operates on a primitive cell-based factorized representation of the slab-adsorbate complex, reducing the number of learnable variables by an average of 9.2x while explicitly encoding the surface orientation of the slab-adsorbate interface. Experiments on the Open Catalyst 2020 dataset demonstrate that CatFlow significantly improves the structural fidelity of generated catalysts compared to autoregressive and sequential baselines. Further experiments show that the generated structures accurately capture the adsorption energy distributions of physically plausible interfaces and lie closer to thermodynamic local minima.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑