Decoding α‐MoC1− x Nanoparticle Formation in Continuous Flow via Machine Learning
Bin Pan, Allison P Forsberg, Ricki Chairil, Majed S Madani, Susan E Habas, Frederick G Baddour, Richard L Brutchey, Noah Malmstadt · 2026
Read Decoding α‐MoC1− x Nanoparticle Formation in Continuous Flow via Machine Learning by Bin Pan, Allison P Forsberg, Ricki Chairil, Majed S Madani, Susan E Habas, Frederick G Baddour, Richard L Brutchey, Noah Malmstadt (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/pmc-13392712.txt.
Description
Pan and co-authors describe, in 2026, a continuous-flow method for making molybdenum carbide nanoparticles, catalysts that mimic costly noble metals. Precursors flow through a reactor while instruments record spectra in real time, but the overlapping signals are hard to untangle by ordinary math. The team trained several machine learning models to convert those spectra into moment-by-moment amounts of precursor, intermediate material, and the end product.
A multilayer perceptron, a type of neural network, performed best, matching X-ray scattering checks with a mean error of only 9 percent across the validation runs. Its concentration profiles revealed a two-step pathway: the precursor first becomes an amorphous, disordered intermediate, and that material then crystallizes inside the particles. The first step limits the speed of the reaction. The authors present the setup as a step toward self-driving reactors that monitor and steer their production.
Catalog record
| CREATOR | Bin Pan, Allison P Forsberg, Ricki Chairil, Majed S Madani, Susan E Habas, Frederick G Baddour, Richard L Brutchey, Noah Malmstadt |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |