Predicting compressive strength of fly ash and sugarcane bagasse ash-based geopolymer concrete using statistical techniques

Cement production and other industrial activities are major contributors to environmental and health concerns, primarily due to the substantial amounts of carbon dioxide (CO₂) emitted into the atmosphere. The use of supplementary cementitious materials can reduce the quantity of cement required, thus lowering CO₂ emissions. One such material, sugarcane bagasse ash, improves the mechanical properties of concrete by promoting a denser mix, which is crucial for achieving higher strength. This study proposes three predictive models’ linear regression (LR), nonlinear regression (NLR), and artificial neural networks (ANN) to estimate the compressive strength of high-strength fly ash geopolymer concrete modified with sugarcane bagasse ash. These models present a practical and cost-effective method for predicting compressive strength, offering a more efficient alternative to traditional approaches that require extended testing. The study utilizes 54 experimental data points from geopolymer concrete mixtures containing sugarcane bagasse ash, collected through experimental work, to develop and assess the prediction models. The models are evaluated using various metrics, including the coefficient of determination (R²), root means squared error (RMSE), scatter plot analysis, and mean absolute error (MAE). Among the models tested, the ANN model proves to be the most effective, achieving R², RMSE, and MAE values of 0.905, 2.5004 MPa, and 1.9604, respectively.