A partially quantum‑informed crystal graph network for direct adsorption energy prediction in catalysis
Ericsson Tetteh Chenebuah, Michel Nganbe, Linhao Liu, Alain Beaudelaire Tchagang · 2026
Read A partially quantum‑informed crystal graph network for direct adsorption energy prediction in catalysis by Ericsson Tetteh Chenebuah, Michel Nganbe, Linhao Liu, Alain Beaudelaire Tchagang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13572492.txt.
Description
Ericsson Tetteh Chenebuah, with three colleagues, presents a 2026 model that predicts how strongly molecules stick to catalyst surfaces. That sticking energy guides catalyst design for fuel cells and clean energy, yet quantum calculations are slow and lab trials cost much. The model aims for quantum-like accuracy at a fraction of the effort.
The network, Q-CatNet, builds on a crystal graph method that maps atoms and bonds. New inputs add charge-based edge cues plus global signals from electron states and X-ray patterns. It predicts the sticking energy directly, with no need to split the total energy into parts. On a curated data set, it beat an image-based method by 46 percent and topped several graph rivals by 8 to 38 percent. The authors pitch it as a faster screen for new catalysts.
Catalog record
| CREATOR | Ericsson Tetteh Chenebuah, Michel Nganbe, Linhao Liu, Alain Beaudelaire Tchagang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 115573 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |