Prediction of compressive strength of geopolymer concrete by using ANN and GPR

Machine learning techniques are the future of the research and development industries. There are various techniques available based on mathematical models. It can predict the future by the usage of past data sets. Geopolymer concrete is the future of construction industries due to its fresh, mechanical and durable properties, and it is also an option for sustainable development. In this investigation, the compressive strength of geopolymer concrete by using artificial neural network and Gaussian process regression models of machine-learning techniques has been predicted. In which, the models for predicting the compressive strength of GPC by using past destructive data sets have been developed. After developing the models, both predicted compressive strength results and analysis of the accuracy of models like RMSE (root mean square error), R 2, MSE (mean square error), and MAE (mean absolute error) have been compared. After the investigation, it is concluded that the average error in the ANN model is 7.2% and minimum error is 0.006% and the maximum error observed is 34% in the data. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.