Supervised learning algorithms are a recent trend for the prediction of mechanical properties of concrete. This paper presents AdaBoost, random forest (RF), and decision tree (DT) models for predicting the compressive strength of concrete at high temperature, based on the experimental data of 207 tests. The cement content, water, fine and coarse aggregates, silica fume, nano silica, fly ash, super plasticizer, and temperature were used as inputs for the models’ development. The performance of the AdaBoost, RF, and DT models are assessed using statistical indices, including the coefficient of determination (R²), root mean squared error-observations standard deviation ratio (RSR), mean absolute percentage error, and relative root mean square error. The applications of the above-mentioned approach for predicting the compressive strength of concrete at high temperature are compared with each other, and also to the artificial neural network and adaptive neuro-fuzzy inference system models described in the literature, to demonstrate the suitability of using the supervised learning methods for modeling to predict the compressive strength at high temperature. The results indicated a strong correlation between experimental and predicted values, with R² above 0.9 and RSR lower than 0.5 during the learning and testing phases for the AdaBoost model. Moreover, the cement content in the mix was revealed as the most sensitive parameter by sensitivity analysis.

Rockburst is a complex phenomenon of dynamic instability in the underground excavation of rock. Owing to the complex and unclear rockburst mechanism, it is difficult to accurately predict and reasonably assess the rockburst potential. With the increasing availability of case histories from rock engineering and the advancement of data science, the data mining algorithms provide a good way to predict complex phenomena, like rockburst potential. This paper investigates the potential of J48 and random tree algorithms to predict the rockburst classification ranks using 165 cases, with four parameters, namely maximum tangential stress of surrounding rock, uniaxial compressive strength, uniaxial tensile strength, and strain energy storage index. A comparison of developed models’ performances reveals that the random tree gives more reliable predictions than J48 and other empirical models (Russenes criterion, rock brittleness coefficient criterion, and artificial neural networks). Similar comparisons with convolutional neural network resulted at par performance in modeling the rockburst hazard data.

Many factors impact earthquake-induced liquefaction, and there are complex interactions between them. Therefore, rationally identifying the key factors and clarifying their direct and indirect effects on liquefaction help to reduce the complexity of the predictive model and improve its predictive performance. This information can also help researchers understand the liquefaction phenomenon more clearly. In this paper, based on a shear wave velocity (V_s) database, 12 key factors are quantitatively identified using a correlation analysis and the maximum information coefficient (MIC) method. Subsequently, the regression method combined with the MIC method is used to construct a multiple causal path model without any assumptions based on the key factors for clarifying their direct and mediation effects on liquefaction. The results show that earthquake parameters produce more important influences on the occurrence of liquefaction than soil properties and site conditions, whereas deposit type, soil type, and deposit age produce relatively small impacts on liquefaction. In the multiple causal path model, the influence path of each factor on liquefaction becomes very clear. Among the key factors, in addition to the duration of the earthquake and V_s, other factors possess multiple mediation paths that affect liquefaction; the thickness of the critical layer and thickness of the unsaturated zone between the groundwater table and capping layer are two indirect-only mediators, and the fines content and thickness of the impermeable capping layer induce suppressive effects on liquefaction. In addition, the constructed causal model can provide a logistic regression model and a structure of the Bayesian network for predicting liquefaction. Five-fold cross-validation is used to compare and verify their predictive performances.