Compressive strength estimation of eco-friendly geopolymer concrete: Application of hybrid machine learning techniques

Geopolymer concrete (𝐺𝑃𝐶) has emerged as a feasible choice for construction materials as a result of the environmental issues associated with the production of cement. The findings of this study contribute to the development of machine learning methods for estimating the properties of eco-friendly concrete to help reduce 𝐶𝑂2 emissions in the construction industry. The compressive strength (𝑓𝑐) of 𝐺𝑃𝐶 is predicted using artificial intelligence approaches in the present study when ground granulated blast-furnace slag (𝐺𝐺𝐵𝑆) is substituted with natural zeolite (𝑁𝑍), silica fume (𝑆𝐹), and varying 𝑁𝑎𝑂𝐻 concentrations. For this purpose, two machine learning methods multi-layer perceptron (𝑀𝐿𝑃) and radial basis function (𝑅𝐵𝐹) were considered and hybridized with arithmetic optimization algorithm (𝐴𝑂𝐴), and grey wolf optimization algorithm (𝐺𝑊𝑂). According to the results, all methods performed very well in predicting the 𝑓𝑐 of 𝐺𝑃𝐶. The proposed 𝐴𝑂𝐴 − 𝑀𝐿𝑃 might be identified as the outperformed framework, although other methodologies (𝐴𝑂𝐴 − 𝑅𝐵𝐹, 𝐺𝑊𝑂 − 𝑅𝐵𝐹, and 𝐺𝑊𝑂 − 𝑀𝐿𝑃) were also reliable in the 𝑓𝑐 of 𝐺𝑃𝐶 forecasting process.