Utilizing contemporary machine learning techniques for determining soilcrete properties

• Published in: Earth science informatics 2025, Vol.18 (1), p.176, Article 176
• Main Authors: Inqiad, Waleed Bin, Khan, Muhammad Saud, Mehmood, Zohaib, Khan, Naseer Muhammad, Bilal, Muhammad, Sazid, Mohammed, Alarifi, Saad S.
• Format: Article
• Language: English
• Subjects: Aggregates; Algorithms; Artificial intelligence; Carbon dioxide; Cement; Civil engineering; Concrete mixing; Construction costs; Construction industry; Construction materials; Density; Earth and Environmental Science; Earth science; Earth Sciences; Earth System Sciences; Emissions; Gene expression; Graphical user interface; Greenhouse gases; Industrial development; Informatics; Information Systems Applications (incl.Internet); Machine learning; Material properties; Mechanical properties; Metakaolin; Modulus of elasticity; Ontology; Permeability; Prediction models; Simulation and Modeling; Soil properties; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Strain analysis; User interface
• ISSN: 1865-0473; 1865-0481
• DOI: 10.1007/s12145-024-01520-2

Soilcrete is an innovative construction material made by combining naturally occurring earth materials with cement. It can be effectively used in areas where other construction materials are not readily available due to financial or environmental reasons since soilcrete is made from readily available natural clay. It can also help to cut down the greenhouse gas emissions from the construction industry by encouraging the use of resources that are locally available. Thus, it is imperative to reliably predict different properties of soilcrete since the accurate determination of these properties is crucial for the widespread use of soilcrete materials. However, the laboratory determination of these properties is subjected to significant time and resource constraints. As a result, this research was undertaken to provide empirical prediction models for the density, shrinkage, and strain of soilcrete mixes using two machine learning algorithms: Gene Expression Programming (GEP) and Extreme Gradient Boosting (XGB). The analysis revealed that XGB-based predictions correlated more with real-life values than GEP having training R 2 = 0.999 for both density and shrinkage prediction and R 2 = 0.944 for strain prediction. Moreover, several explanatory analyses including individual conditional expectation (ICE) analysis and shapely analysis were done on the XGB model which showed that water-to-binder ratio, metakaolin content, and modulus of elasticity are some of the most important variables for forecasting soilcrete materials properties. Furthermore, an interactive graphical user interface (GUI) has been developed for effective utilization in civil engineering industry to forecast these properties of soilcrete materials.