The major criteria that control pile foundation design is pile bearing capacity (P_u). The load bearing capacity of piles is affected by the various characteristics of soils and the involvement of multiple parameters related to both soil and foundation. In this study, a new model for predicting bearing capacity is developed using an extreme gradient boosting (XGBoost) algorithm. A total of 200 driven piles static load test-based case histories were used to construct and verify the model. The developed XGBoost model results were compared to a number of commonly used algorithms—Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM) using various performance measure metrics such as coefficient of determination, mean absolute error, root mean square error, mean absolute relative error, Nash–Sutcliffe model efficiency coefficient and relative strength ratio. Furthermore, sensitivity analysis was performed to determine the effect of input parameters on P_u. The results show that all of the developed models were capable of making accurate predictions however the XGBoost algorithm surpasses others, followed by AdaBoost, RF, DT, and SVM. The sensitivity analysis result shows that the SPT blow count along the pile shaft has the greatest effect on the P_u.

Seismic soil liquefaction is considered as one of the most complex geotechnical earthquake engineering problems owing to the uncertainty and complexity involved in soil parameters, seismic parameters, and site condition factors. Each one of these parameters contains a variety of factors that trigger liquefaction and have varying degrees of importance. However, estimating accurate and reliable liquefaction-induced hazards requires identification and benchmarking of the most influential factors that control soil liquefaction. Seismic soil liquefaction factors were identified by Systematic Literature Review (SLR) approach and analyzed through Interpretive Structural Modeling (ISM) and the Cross-Impact Matrix Multiplication Applied to Classification (MICMAC) methodologies. The ISM model presented the relationships between fifteen seismic soil liquefaction factors and their benchmarking position from higher to lower-level significant factors in hierarchy. MICMAC is used to examine the strength of the relationship between seismic soil liquefaction significant factors based on their driving and dependence power. This research characterizes the identification and benchmarking of the seismic soil liquefaction factors and their relationships. The results show that the factors—duration of earthquake, peak ground acceleration, drainage condition, and standard penetration test (SPT) blow counts—influence seismic soil liquefaction directly and soil type is the governing factor that forms the base of the ISM hierarchy and consequently triggers seismic soil liquefaction. The results provide a more accurate way of selecting significant factors for establishment of seismic soil liquefaction potential and liquefaction-induced hazards risk assessment models.

The present research employs new boosting-based ensemble machine learning models i.e., gradient boosting (GB) and adaptive boosting (AdaBoost) to predict the unconfined compressive strength (UCS) of geopolymer stabilized clayey soil. The GB and AdaBoost models were developed and validated using 270 clayey soil samples stabilized with geopolymer, with ground-granulated blast-furnace slag and fly ash as source materials and sodium hydroxide solution as alkali activator. The database was randomly divided into training (80%) and testing (20%) sets for model development and validation. Several performance metrics, including coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE), and mean squared error (MSE), were utilized to assess the accuracy and reliability of the developed models. The statistical results of this research showed that the GB and AdaBoost are reliable models based on the obtained values of R² (= 0.980, 0.975), MAE (= 0.585, 0.655), RMSE (= 0.969, 1.088), and MSE (= 0.940, 1.185) for the testing dataset, respectively compared to the widely used artificial neural network, random forest, extreme gradient boosting, multivariable regression, and multi-gen genetic programming based models. Furthermore, the sensitivity analysis result shows that ground-granulated blast-furnace slag content was the key parameter affecting the UCS.

Concrete is the most widely used material in construction. It has the characteristics of strong plasticity, good economy, high safety, and good durability. As a kind of structural material, concrete must have sufficient strength to resist various loads. At the same time, due to the brittleness of concrete, compressive strength is the most important mechanical property of concrete. To solve the disadvantages of the low efficiency of the traditional concrete compressive strength prediction methods, this study proposes a firefly algorithm (FA) and random forest (RF) hybrid machine-learning method to predict the compressive strength of concrete. First, a database is built based on the data of published articles. The dataset in the database contains eight input variables (cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age) and one output variable (concrete compressive strength). Then, the correlation of the eight input variables was analyzed, and the results showed that there was no high correlation between the input variables; thus, they could be used as input variables to predict the compressive strength of concrete. Next, this study used the FA algorithm to optimize the hyperparameters of RF to obtain better hyperparameters. Finally, we verified that the FA and RF hybrid machine-learning model proposed in this study can predict the compressive strength of concrete with high accuracy by analyzing the R values and RSME values of the training set and test set and comparing the predicted value and actual value of the training set and test machine.

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.

The effectiveness of the use of waste fly ash (FA) and cement (OPC) in the stabilization of subgrade soils and the reasons likely to influence the degree of stabilization were investigated. Incorporating waste fly ash (FA) and cement (OPC) as additives leads to significant environmental and economic contributions to soil stabilization. This study involves laboratory tests to obtain the Atterberg limit, free swell index (FSI), the unconfined compressive strength (UCS), the California bearing ratio (CBR), and the scanning electron microscope (SEM). The test results for the subgrade soil illustrate that the Atterberg limit, plasticity index, and free swell index are decreasing with the addition of different proportions of fly ash and cement, i.e., 0%, 5%, 10%, 15%, and 20% and 0%, 2%, 4%, 6%, and 8%, respectively. The CBR value of untreated soil is 2.91%, while the best CBR value of fly ash and cement mixture treated soil is 10.12% (20% FA+8% OPC), which increases 71.34% from the initial value. The UCS of untreated soil is 86.88 kPa and treated soil with fly ash and cement attains a maximum value of 167.75 kPa (20% FA+8% OPC), i.e., increases by 48.20% from the initial value. The tests result show that the stability of a subgrade soil can be improved by adding fly ash and cement. While effectiveness and usability of waste FA and cement are cost-effective and environmentally friendly alternatives to expansive soil for pavement and any other foundation work in the future.