Prediction of specific gravity of Afghan coal based on conventional coal properties by stepwise regression and random forest

Abstract

Coal can be considered as the main fuel for electricity generation in Afghanistan. However, there is a quite limited data available about the overall quality, distribution, and character of coals in Afghanistan. Specific gravity (S.G) of coal as a key factor can be used for the estimation of potential tonnage production and be a fundamental parameter for the selection of coal washery process method. However, there is no investigation which comprehensively explores relationships between S.G and coal properties. In this investigation, the potential of S.G prediction based on conventional properties for Afghan coal samples was explored by stepwise regression and random forest. Pearson correlation (r) and variable importance measurement (VIM) of random forest (RF) were applied to select the most effective variables among conventional parameters for the S.G prediction. Results of VIM indicated that ash and carbon content of coal samples had the highest importance for the S.G prediction.Stepwise regression and RF models were developed based on these two coal variables. Testing the generated models indicated that S.G of Afghan coals can quite accurately predict by these models (R 2 > 0.90). Modeling outcomes showed that the highest S.G (S.G > 2) for Afghan coal occurred when ash was higher than 40% and carbon was lower than 30%.

Analysis of the Relationship between the Low-Temperature Properties and Distillation Profiles of HEFA-Processed Bio-Jet Fuel

“…In this study, Pearson correlation and linear regression were used to analyze the relationship between the low-temperature properties and SIMDIS distillation profile (IBP, 10~95% recovered and final boiling point (FBP)) of the blended bio-jet fuel. Pearson correlation (r) was used to explore the linear inter-correlations between the low-temperature properties and each recovered temperature of the SIMDIS distillation profile [35][36][37].…”

Prediction of CO 2 mole fraction via CO 2 CPU process using different machine learning algorithms

“…In its capacity RF is resistant to outliers because it is an ensemble method generates a fair approximation of the generalization fault makes over tting decrease, is exible, deals with lacking information, and doesn't contain any statistical assumptions [42,43]. The RF algorithm is based on a decision tree (DT) [44] which uses a haphazard methodology for sampling to create trees [45]. Since, drawing the training samples makes use of replacement, in a tree some samples might appear repeatedly.…”

“…Each feature's Shapley value, which re ects how that feature affects the output produced, is calculated by averaging the marginal contributions of all feature permutations [53]. The SHAP explanation algorithm can be formulated as follows [45,54]…”

A CGLS-based method for solving magnetic moments of hybrid-model magnetic targets

“…The key to solving the inverse problem lies in how to deal with the ill-posed equations and the problem of data perturbation [13]. The classical method of solving the inversion problem is the generalized inverse solution [14], stepwise regression method [15] and Levenberg-Marquardt algorithm [12], NSGA-II algorithm [16], regularization method [17], the method based on Bayesian reasoning [18,19], machine learning methods [6,14,20]. Among them, the regularization method has received extensive attention and application in many fields, including CGLS algorithm [21,22], ADMM algorithm [23,24], Tikhonov algorithm [5], LASSO algorithm [25], LARS algorithm [26], etc.…”