This paper presents a novel application of machine learning models to clarify the intricate behaviors of expansive soils, focusing on the impact of sand content, saturation level, and dry density. Departing from conventional methods, this research utilizes a data-centric approach, employing a suite of sophisticated machine learning models to predict soil properties with remarkable precision. The inclusion of a 30% sand mixture is identified as a critical threshold for optimizing soil strength and stiffness, a finding that underscores the transformative potential of sand amendment in soil engineering. In a significant advancement, the study benchmarks the predictive power of several models including extreme gradient boosting (XGBoost), gradient boosting regression (GBR), random forest regression (RFR), decision tree regression (DTR), support vector regression (SVR), symbolic regression (SR), and artificial neural networks (ANNs and proposed ANN-GMDH). Symbolic regression equations have been developed to predict the elasticity modulus and unconfined compressive strength of the investigated expansive soil. Despite the complex behaviors of expansive soil, the trained models allow for optimally predicting the values of unconfined compressive parameters. As a result, this paper provides for the first time a reliable and simply applicable approach for estimating the unconfined compressive parameters of expansive soils. The proposed ANN-GMDH model emerges as the pre-eminent model, demonstrating exceptional accuracy with the best metrics. These results not only highlight the ANN’s superior performance but also mark this study as a groundbreaking endeavor in the application of machine learning to soil behavior prediction, setting a new benchmark in the field.

This study aims to evaluate the utilization of technology known as Digital Twin for fault detection in buildings. The strategy consisted of studying existing applications, difficulties, and possibilities that come with it. The Digital Twin technology is one of the most intriguing newly discovered technologies rapidly evolving; however, some problems still need to be addressed. First, using Digital Twins to detect building faults to prevent future failures and cutting overall costs by improving building maintenance is still ambiguous. Second, how Digital Twin technology may be applied to discover inefficiencies inside the building to optimize energy usage is not well defined. To address these issues, we reviewed 326 documents related to Digital Twin, BIM, and fault detection in civil engineering. Then out of the 326 documents, we reviewed 115 documents related to Digital Twin for fault detection in detail. This study used a qualitative assessment to uncover Digital Twin technology’s full fault detection capabilities. Our research concludes that Digital Twins need more development in areas such as scanner hardware and software, detection and prediction algorithms, modeling, and twinning programs before they will be convincing enough for fault detection and prediction. In addition, more building owners, architects, and engineers need substantial financial incentives to invest in condition monitoring before many of the strategies discussed in the reviewed papers will be used in the construction industry. For future investigation, more research needs to be devoted to exploring how machine learning may be integrated with other Digital Twin components to develop new fault detection methods.