Prediction of uniaxial compressive strength of rock samples using density weighted least squares twin support vector regression

Non-destructive test-based assessment of uniaxial compressive strength and elasticity modulus of intact carbonate rocks using stacking ensemble models

The uniaxial compressive strength (UCS) and elasticity modulus (E) of intact rock are two fundamental requirements in engineering applications. These parameters can be measured either directly from the uniaxial compressive strength test or indirectly by using soft computing predictive models. In the present research, the UCS and E of intact carbonate rocks have been predicted by introducing two stacking ensemble learning models from non-destructive simple laboratory test results. For this purpose, dry unit weight, porosity, P-wave velocity, Brinell surface harnesses, UCS, and static E were measured for 70 carbonate rock samples. Then, two stacking ensemble learning models were developed for estimating the UCS and E of the rocks. The applied stacking ensemble learning method integrates the advantages of two base models in the first level, where base models are multi-layer perceptron (MLP) and random forest (RF) for predicting UCS, and support vector regressor (SVR) and extreme gradient boosting (XGBoost) for predicting E. Grid search integrating k-fold cross validation is applied to tune the parameters of both base models and meta-learner. The results demonstrate the generalization ability of the stacking ensemble method in the comparison of base models in the terms of common performance measures. The values of coefficient of determination (R2) obtained from the stacking ensemble are 0.909 and 0.831 for predicting UCS and E, respectively. Similarly, the stacking ensemble yielded Root Mean Squared Error (RMSE) values of 1.967 and 0.621 for the prediction of UCS and E, respectively. Accordingly, the proposed models have superiority in the comparison of SVR and MLP as single models and RF and XGBoost as two representative ensemble models. Furthermore, sensitivity analysis is carried out to investigate the impact of input parameters.

Source apportionment of heavy metals in PM2.5 samples and effects of heavy metals on hypertension among schoolchildren in Tianjin

The prevalence of hypertension in children has increased significantly in recent years in China. The aim of this study was to provide scientific support to control ambient heavy metals (HMs) pollution and prevent childhood hypertension. In this study, ambient HMs in PM2.5 were collected, and 1339 students from Tianjin were randomly selected. Positive matrix factorization (PMF) was used to identify and determine the sources of HMs pollution. The generalized linear model, Bayesian kernel machine regression (BKMR) and the quantile g-computation method were used to analyze the relationships between exposure to HMs and the risk of childhood hypertension. The results showed that HMs in PM2.5 mainly came from four sources: soil dust, coal combustion, incineration of municipal waste and the metallurgical industry. The positive relationships between As, Se and Pb exposures and childhood hypertension risk were found. Coal combustion and incineration of municipal waste were important sources of HMs in the occurrence of childhood hypertension. Based on these accomplishments, this study could provide guidelines for the government and individuals to alleviate the damaging effects of HMs in PM2.5. The government must implement policies to control prime sources of HMs pollution.

A novel hybrid random forest linear model approach for forecasting groundwater fluoride contamination

Groundwater quality in the Datong basin is threatened by high fluoride contamination. Laboratory analysis is a standard method for estimating groundwater quality parameters, which is expensive and time-consuming. Therefore, this paper proposes a hybrid random forest linear model (HRFLM) as a novel approach for estimating groundwater fluoride contamination. Light gradient boosting (LightGBM), random forest (RF), and extreme gradient boosting (Xgboost) were also employed in comparison with HRFLM for predicting fluoride contamination in groundwater. 202 groundwater samples were collected to draw up the performance capability of several models in forecasting subsurface water fluoride contamination. The performance of the models was assessed utilizing the receiver operating characteristic (ROC) area under the curve (AUC) and the confusion matrix (CM). The CM results reveal that with nine predictor variables, the hybrid HRFLM achieved an accuracy of 95%, outperforming the Xgboost, LightGBM, and RF models, which attained 88%, 88%, and 85%, respectively. Likewise, the AUC results of the hybrid HRFLM show high performance with an AUC of 0.98 compared to Xgboost, LightGBM, and RF, which achieved an AUC of 0.95, 0.90, and 0.88, respectively. The study demonstrates that the HRFLM can be applied as an advanced approach for groundwater fluoride contamination prediction in the Datong basin and could be adopted in various areas facing a similar challenge.

Least squares support vector regression for complex censored data

Least squares support vector regression (LS-SVR) is a robust machine learning algorithm for small sample data. Its solution is derived from solving a set of linear equations, making the calculation process straightforward. In order to overcome the difficulties of the regression estimations when the responses are subject to interval censoring or left truncation and right censoring, two LS-SVR methods are proposed. For interval-censored data, one can easily estimate the regression functions by combining the imputation techniques and LS-SVR for right-censored data. For left-truncated and right-censored data, a weight is used to reduce the effects of truncation and censoring on the LS-SVR procedure. Simulation results show that the proposed methods can reduce regression error and yield high accuracy and stability.

Assessment of Machine Learning Models for the Prediction of Rate-Dependent Compressive Strength of Rocks

The prediction of rate-dependent compressive strength of rocks in dynamic compression experiments is still a notable challenge. Four machine learning models were introduced and employed on a dataset of 164 experiments to achieve an accurate prediction of the rate-dependent compressive strength of rocks. Then, the relative importance of the seven input features was analyzed. The results showed that compared with the extreme learning machine (ELM), random forest (RF), and the original support vector regression (SVR) models, the correlation coefficient R2 of prediction results with the hybrid model that combines the particle swarm optimization (PSO) algorithm and SVR was highest in both the training set and the test set, both exceeding 0.98. The PSO-SVR model obtained a higher prediction accuracy and a smaller prediction error than the other three models in terms of evaluation metrics, which showed the possibility of the model as a rate-dependent compressive strength prediction tool. Additionally, besides the static compressive strength, the stress rate is the most important influence factor on the rate-dependent compressive strength of the rock among the listed input parameters. Moreover, the strain rate has a positive effect on the rock strength.

Prediction of Uniaxial Compression Strength of Limestone Based on the Point Load Strength and SVM Model

Uniaxial compression strength (UCS) is a fundamental parameter to carry out geotechnical engineering design and construction. It is simple and efficient to predict UCS using point load strength (PLS) at engineering sites. However, the high dispersion of rock strength limits the accuracy of traditional fitting prediction methods. In order to improve the UCS prediction accuracy, 30 sets of regular cylindrical specimen tests between PLS and UCS are conducted on limestone mines. The correlation relationship between PLS and UCS is found by using four basic fitting functions. Then, a prediction model is established by using SVM algorithm. Multiple training test data are used to achieve high-precision prediction of UCS and the results show it is less different from the actual values. Especially, the R2 coefficient reached 0.98. The SVM model prediction performance is significantly better than the traditional fitting function. The constructed SVM model in this study can accurately predict the UCS using the PLS obtained in the field, which has a great significance to the rock stability judgment in the actual construction environment.