Machine-learning atomic simulation for heterogeneous catalysis | npj Computational Materials

Nature·Jan 7

✦ NabkaNews BriefAuto-summarized from multiple outlets · verify with the source

Researchers are utilizing machine learning to improve simulations and understanding of heterogeneous catalysis. This involves developing frameworks and potentials to enhance the accuracy and efficiency of computational calculations. Various studies and tools, such as AQCat25 and FALCON, are being explored to leverage machine learning in this field, with applications including the search for active sites and the analysis of surface structures.

Full coverage

AQCat25: unlocking spin-aware, high-fidelity machine learning potentials for heterogeneous catalysis

Nature·Apr 27

An end-to-end framework for reactivity in heterogeneous catalysis

Nature·Mar 19

Leveraging Machine Learning Potentials for In-Situ Searching of Active sites in Heterogeneous Catalysis

ACS Publications·Sep 11

Machine learning cuts complexity of computational calculations in catalysis

Chemistry World·Mar 24

Catalysis in the digital age: Unlocking the power of data with machine learning

Wiley Interdisciplinary Reviews·Sep 20

FALCON: fast active learning for machine learning potentials in atomistic and ab initio molecular dynamics simulations

Nature·Dec 12

Data-Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts

Wiley Online Library·Dec 12

Incongruent melting and phase diagram of SiC from machine learning molecular dynamics

Nature·Feb 16

View original report at Nature ↗

Fetching the latest headlines…