PulseAugur
EN
LIVE 08:07:44

Machine learning predicts sustainable cement performance

Researchers have developed a machine learning model to predict the performance of alkali-activated slag (AAS) materials, a more sustainable alternative to traditional cement. By analyzing a large dataset of over 3100 compressive strength records and 24 attributes including precursor chemistry and curing conditions, the model achieved improved predictive accuracy. A key innovation is the integration of 'average metal oxide dissociation energy' (AMODE) as a reactivity descriptor, which offers a more interpretable and effective representation than individual oxide compositions. This approach allows for the exploration of design spaces that balance strength, cost, and significantly lower CO2 emissions compared to ordinary Portland cement. AI

IMPACT Enables more sustainable material design by predicting performance and environmental impact.

RANK_REASON Academic paper detailing a new methodology for materials science. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Qiyao He, Zhanzhao Li, Kai Gong ·

    Reactivity-Informed Machine Learning for Performance Prediction and Design Space Exploration of Alkali-Activated Slag

    arXiv:2606.06765v1 Announce Type: cross Abstract: Establishing quantitative relationships among mix design, raw material properties, curing conditions, and performance remains a long-standing challenge in cementitious materials, particularly for alkali-activated materials with va…