Comprehensive dataset for performance evaluation of SCM-blended concrete

The application of supplementary cementitious materials (SCMs) as cement replacements has become an effective approach for reducing the carbon footprint of concrete structures. The effectiveness of this approach is primarily attributed to the pozzolanic properties of SCMs, which enhance concrete performance and reduce environmental impact. Meanwhile, machine learning (ML) has emerged as a powerful tool for predicting SCM-blended concrete properties, offering a more efficient and reliable alternative to traditional experimental approach. However, existing datasets of SCM-based concrete are often region-specific (i.e. datasets are limited to a specific region/country), limiting their applicability to diverse geographical and environmental conditions. To address this issue, a comprehensive dataset on SCM-based concrete incorporating fly ash (FA), silica fume (SF), and ground granulated blast furnace slag (GGBFS) has been compiled from 136 publications across 27 countries, focusing on both the mechanical properties and durability of concrete. This extensive dataset serves as a valuable resource for predicting concrete properties using ML models, facilitating the development of more sustainable and high-performance concrete mixtures.