Machine learning based optimization of fly ash content for improving geopolymer concrete compressive strength
Mohammadreza Noori Sichani, Omid Mazahery Dehkordi, Morteza Khorshidi, Amirehsan Teimortashlu, Pourya Nejatipour · 2025
Read Machine learning based optimization of fly ash content for improving geopolymer concrete compressive strength by Mohammadreza Noori Sichani, Omid Mazahery Dehkordi, Morteza Khorshidi, Amirehsan Teimortashlu, Pourya Nejatipour (2025) 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-12749362.txt.
Description
Concrete made from fly ash and chemical activators, instead of cement, could cut construction's footprint if engineers can predict its strength. Mohammadreza Noori Sichani and co-authors train four machine learning models to forecast the compressive strength of this geopolymer concrete from its recipe. They tune each model with an automated search and hold back a quarter of the data for testing.
One model, TabPFN, predicts best, with the lowest errors and the steadiest behavior under uncertainty checks. The team then runs four nature-inspired search methods to design a stronger mix, and Harris Hawks Optimization wins with a mix reaching about 61.6 megapascals. Ingredient analysis shows the ash's alumina and silica shares matter most, followed by coarse aggregate.
Catalog record
| CREATOR | Mohammadreza Noori Sichani, Omid Mazahery Dehkordi, Morteza Khorshidi, Amirehsan Teimortashlu, Pourya Nejatipour |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 94 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |