Machine Learning-Enabled Real-Time Prediction of Drying Shrinkage in Fly Ash-Modified Cementitious Materials

Chi-tathon Kupwiwat, Lapyote Prasittisopin · 2026

Read Machine Learning-Enabled Real-Time Prediction of Drying Shrinkage in Fly Ash-Modified Cementitious Materials by Chi-tathon Kupwiwat, Lapyote Prasittisopin (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-13280831.txt.

Description

Chi-tathon Kupwiwat and Lapyote Prasittisopin published a 2026 study using machine learning to predict drying shrinkage in concrete containing fly ash, hour by hour rather than test by test. Shrinkage as concrete dries drives cracking and long-term durability problems, and conventional checks sample it too sparsely to catch its course. The authors assembled 79,008 hourly observations across sixteen mix designs and several curing regimes, then trained ensemble and neural models on inputs.

Random forest, extra trees, nearest-neighbor, and neural network models all predicted shrinkage with accuracy near an R-squared of 0.99 on held-out data. Explanation analysis showed time variables dominating, separating capillary moisture loss from slow pore-level drying. Fly ash content exerted a smaller but consistent effect via the cement's microstructure. The authors propose continuous prediction as a replacement for periodic testing, enabling real-time quality control for lower-carbon concrete that substitutes fly ash for cement.

Catalog record

CREATORChi-tathon Kupwiwat, Lapyote Prasittisopin
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE56 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13280831

Browse the full library · About the Tower of Babel