Improved prediction of clay soil expansion using machine learning algorithms and meta-heuristic dichotomous ensemble classifiers

Soil swelling-related disaster is considered as one of the most devastating geo-hazards in modern history.Hence,proper determination of a soil’s ability to expand is very vital for achieving a secure and safe ground for infrastructures.Accordingly,this study has provided a novel and intelligent approach that enables an improved estimation of swelling by using kernelised machines(Bayesian linear regression(BLR)&bayes point machine(BPM)support vector machine(SVM)and deep-support vector machine(D-SVM));(multiple linear regressor(REG),logistic regressor(LR)and artificial neural network(ANN)),tree-based algorithms such as decision forest(RDF)&boosted trees(BDT).Also,and for the first time,meta-heuristic classifiers incorporating the techniques of voting(VE)and stacking(SE)were utilised.Different independent scenarios of explanatory features’combination that influence soil behaviour in swelling were investigated.Preliminary results indicated BLR as possessing the highest amount of deviation from the predictor variable(the actual swell-strain).REG and BLR performed slightly better than ANN while the meta-heuristic learners(VE and SE)produced the best overall performance(greatest R2 value of 0.94 and RMSE of 0.06%exhibited by VE).CEC,plasticity index and moisture content were the features considered to have the highest level of importance.Kernelized binary classifiers(SVM,D-SVM and BPM)gave better accuracy(average accuracy and recall rate of 0.93 and 0.60)compared to ANN,LR and RDF.Sensitivity-driven diagnostic test indicated that the meta-heuristic models’best performance occurred when ML training was conducted using k-fold validation technique.Finally,it is recommended that the concepts developed herein be deployed during the preliminary phases of a geotechnical or geological site characterisation by using the best performing meta-heuristic models via their background coding resource.

Behavior and characteristics of compacted expansive unsaturated bentonite-sand mixture

Limited studies dealt with the expansive unsaturated soils in the case of large-scale model close to the field conditions and therefore, there is much more room for improvement. In this study, expansive （bentonite–sand （B–S） mixture） and non-expansive （kaolin） soils were tested in different water contents and dry unit weights chosen from the compaction curve to examine the effect of water content change on soil properties （swelling pressure, expansion indices, shear strength （soil cohesion） and soil suction） for the small soil samples. Large-scale model was also used to show the effect of water content change on different relations （swelling and suction with elapsed time）. The study reveals that the initial soil conditions （water content and dry unit weight） affect the soil cohesion, suction and swelling, where all these parameters slightly decrease with the increase in soil water content especially on the wet side of optimum water content. The settlement of each soil at failure increases with the increase in soil degrees of saturation since the matric suction reduces the soil ability to deform. The settlement observed in B–S mixture is higher than that in kaolin due to the effect of higher swelling observed in B–S mixture and the huge amount of water absorbed which transformed the soil to highly compressible soil. The matric suction seems to decrease with elapsed time from top to bottom of tensiometers due to the effect of water flowing from top of the specimen. The tensiometer reading at first of the saturation process is lower than that at later period of saturation （for soil sample B–S3, the tensiometer #1 took 3 d to drop from 93 kPa to 80 kPa at early stage, while the same tensiometer took 2 d to drop from 60 kPa to 20 kPa）.