A Machine Learning-Based Computational Architecture for Unlocking Water Dynamics in Saturated Calcium Silicate Hydrate
Chunlong Liu, Juntao Kang, Qimin Liu, Zechuan Yu · 2026
Read A Machine Learning-Based Computational Architecture for Unlocking Water Dynamics in Saturated Calcium Silicate Hydrate by Chunlong Liu, Juntao Kang, Qimin Liu, Zechuan Yu (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/PMC13302851.txt.
Description
Teaching a computer model how water moves in cement pores speeds durability work a thousandfold, Chunlong Liu and colleagues report in a 2026 study. Atom-level simulations first traced how pore water spreads through calcium silicate hydrate, the glue of concrete. A graph neural network then learned to link each atom's surroundings to that movement.
The model's guesses matched the slow simulations while running about a thousand times faster. It also handled rougher, many-particle pore shapes it had never seen. The authors sketch a future where these fast pore-level guesses feed bigger models of salt attack, guiding tougher concrete design.
Catalog record
| CREATOR | Chunlong Liu, Juntao Kang, Qimin Liu, Zechuan Yu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61794 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |