In the quest for sustainable construction materials, a groundbreaking study led by Talip Cakmak from the Department of Civil Engineering at Recep Tayyip Erdogan University in Türkiye is making waves. The research, published in the journal *Developments in the Built Environment* (translated as *Advances in the Built Environment*), focuses on integrating obsidian and silica fume in geopolymer mortars, offering a greener alternative to traditional cement. The study not only highlights the potential of these materials but also introduces a sophisticated machine learning framework to predict their compressive strength accurately.
Cakmak and his team have developed a robust machine learning framework to predict the compressive strength of geopolymer mortars containing obsidian (OB) and silica fume (SF). This is a significant step forward, as accurately assessing the behavior of these materials under various curing conditions has been a persistent challenge. “The integration of obsidian and silica fume in geopolymer mortars presents a sustainable alternative to conventional binders,” Cakmak explains. “Our study aims to bridge the gap in predicting the compressive strength of these materials using advanced machine learning techniques.”
The research involved testing five popular machine learning techniques—Gaussian Process Regression, Extremely Randomized Trees, Extreme Gradient Boosting, Bagging, and Decision Tree—both individually and in combination through a hybrid meta-model. The combined model outperformed the standalone models, achieving an impressive R2 value of 0.979. This high level of accuracy is a testament to the potential of ensemble machine learning methods in enhancing the precision and reliability of strength predictions for geopolymer mortars.
The study also examined the principal factors influencing the compressive strength, such as the proportions of obsidian and silica fume, curing temperature, and curing duration. Feature Importance and Permutation Feature Importance analyses, along with ANOVA, confirmed the relevance of these factors. K-fold cross-validation further verified the robustness of the model, demonstrating the substantial improvements that ensemble ML methods can bring to the field.
The implications of this research are far-reaching, particularly for the energy sector. As the construction industry seeks to reduce its carbon footprint, the development of sustainable materials like geopolymer mortars becomes increasingly important. “This research not only advances the design of sustainable construction materials but also contributes to reducing carbon emissions in the building industry,” Cakmak notes. The ability to predict the compressive strength of these materials with high accuracy can lead to more efficient and cost-effective construction practices, ultimately benefiting the energy sector and beyond.
As the construction industry continues to evolve, the integration of advanced technologies like machine learning with sustainable materials will play a crucial role in shaping the future of the field. Cakmak’s research is a significant step in this direction, offering valuable insights and paving the way for further innovations. With the publication of this study in *Developments in the Built Environment*, the potential of geopolymer mortars and machine learning techniques is brought into sharper focus, promising a more sustainable and efficient future for construction.