In the quest for sustainable construction materials, researchers have long been exploring alternatives to conventional concrete, which is notorious for its high carbon footprint. Enter geopolymer concrete (GPC), a promising eco-friendly substitute that has been gaining traction in the industry. However, its variable compressive strength has posed a significant challenge, hindering its widespread adoption. A recent study published in *Media Komunikasi Teknik Sipil* (translated as *Civil Engineering Communication Media*) introduces an innovative solution that could revolutionize the way we predict and utilize GPC’s strength.
Led by Riqi Radian Khasani from the Department of Civil Engineering at Universitas Diponegoro in Indonesia, the research presents the optimized least squares moment balanced machine with feature selection (OLSMBM-FS), an advanced artificial intelligence-based model designed to accurately predict GPC compressive strength. This model combines several cutting-edge techniques, including backpropagation neural networks (BPNN) for weight assignment, least squares support vector machines (LSSVM) for hyperplane optimization, and the optical microscope algorithm (OMA) for hyperparameter tuning.
The study employs a systematic dataset, implementing normalization and feature selection techniques to enhance the accuracy and efficiency of the model training process. The OLSMBM-FS model was validated using 10-fold cross-validation and demonstrated superior performance compared to other machine learning models. It achieved impressive results, including the lowest root mean square error (RMSE) of 4.279, mean absolute error (MAE) of 2.291, and mean absolute percentage error (MAPE) of 6.59%, alongside the highest correlation coefficient (R) of 0.901 and coefficient of determination (R²) of 0.813.
“Our model offers a reliable and efficient tool for predicting the compressive strength of geopolymer concrete,” said Khasani. “This can significantly support the broader application of GPC in sustainable construction practices, ultimately reducing the carbon footprint of the construction industry.”
The implications of this research are far-reaching, particularly for the energy sector. As the world shifts towards renewable energy sources, the demand for sustainable construction materials is on the rise. GPC, with its reduced carbon emissions and enhanced mechanical properties, is poised to play a crucial role in this transition. The OLSMBM-FS model can help engineers and construction professionals make informed decisions about material composition, ensuring optimal strength and durability for various applications.
Moreover, the study highlights the potential of machine learning and artificial intelligence in advancing sustainable construction practices. By leveraging these technologies, researchers can develop more accurate predictive models, ultimately driving innovation and efficiency in the industry.
As the construction sector continues to evolve, the integration of advanced technologies like the OLSMBM-FS model will be instrumental in shaping a more sustainable and resilient future. The research published in *Media Komunikasi Teknik Sipil* not only contributes to the scientific community but also provides practical solutions for industry professionals seeking to adopt greener construction materials.
In the words of Khasani, “This is just the beginning. We are excited about the potential of our model and the positive impact it can have on the construction industry and the environment.”