Application of Gradient Boosting Machine Learning Algorithms to Predict Uniaxial Compressive Strength of Soft Sedimentary Rocks at Thar Coalfield

The uniaxial compressive strength (UCS) of rock is one of the essential data in engineering planning and design. Correctly testing UCS of rock to ensure its accuracy and authenticity is a prerequisite for assuring the design of any rock engineering project. UCS of rock has a broad range of applications in mining, geotechnical, petroleum, geomechanics, and other fields of engineering. The application of the gradient boosting machine learning algorithms has been rarely used, especially for UCS prediction, and has performed well, based on the relevant literature of the study. In this study, four gradient boosting machine learning algorithms, namely, gradient boosted regression (GBR), Catboost, light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost), were developed to predict the UCS in MPa of soft sedimentary rocks of the Block-IX at Thar Coalfield, Pakistan, using four input variables such as wet density (ρw) in g/cm3; moisture in %; dry density (ρd) in g/cm3; and Brazilian tensile strength (BTS) in MPa. Then, 106-point dataset was allocated identically for each algorithm into 70% for the training phase and 30% for the testing phase. According to the results, the XGBoost algorithm outperformed the GBR, Catboost, and LightGBM with coefficient of correlation (R2) = 0.99, mean absolute error (MAE) = 0.00062, mean square error (MSE) = 0.0000006, and root mean square error (RMSE) = 0.00079 in the training phase and R2 = 0.99, MAE = 0.00054, MSE = 0.0000005, and RMSE = 0.00069 in the testing phase. The sensitivity analysis showed that BTS and ρw are positively correlated, and the moisture and ρd are negatively correlated with the UCS. Therefore, in this study, the XGBoost algorithm was shown to be the most accurate algorithm among all the investigated four algorithms for UCS prediction of soft sedimentary rocks of the Block-IX at Thar Coalfield, Pakistan.

Evaluation of Mercury in Environmental Samples by a Supramolecular Solvent–Based Dispersive Liquid–Liquid Microextraction Method Before Analysis by a Cold Vapor Generation Technique

Supramolecular solvent–based dispersive liquid–liquid microextraction was used as a preconcentration method for the determination of trace levels of Hg. This simple method accurately measured oxidized HgII content inclaystone and sandstone samples obtained from the Thar Coalfield in Pakistan. Cold vapor atomic absorption spectrometry was used as the detection technique because it is reliable and accurate. The HgII in acidic media forms a complexwith dithizone (DTz) in the presence of supramolecular solvent (tetrahydrofuran and 1-undecanol), forming reverse micelles. Formation of the Hg-DTz complex was achieved to increase the interactions with the supramolecular solvent phase at pH 2.5 under the optimized experimental conditions. After additionof the supramolecular solvent to the aqueous solution, the micelles were uniformly mixed using a vortex mixer. The cloudy solution was centrifuged, and the Hg-DTz complex was extracted into the supramolecular solvent phase. Under optimized experimental conditions, the LOD and enrichment factor were foundto be 5.61 ng/L and 77.8, respectively. Accuracy of the developed method was checked with Certified Reference Materials. The developed method was successfully applied for the determination of HgII in claystone and sandstone samples from the Block VII and Block VIII areas of the Thar Coalfield on the basis of depth.