A Scientometrics Review of Soil Properties Prediction Using Soft Computing Approaches

Khatti, Jitendra; Grover, Kamaldeep Singh

doi:10.1007/s11831-023-10024-z

Cited by 21 publications

(9 citation statements)

References 188 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, the performance of the estimation is presented in the terms of the coefficient of determination ( R 2 ), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), the Mean Absolute Error (MAE), Variance Accounted For (VAF), Index of Scatter (IOS), agreement index (IOA), Mean absolute percentage error (MAPE), Weighted Mean absolute percentage error (WMAPE), Performance Index (PI), and a20index are computed. These metrics are frequently employed to assess regression issues [ 63 , 64 ]. RMSE, MSE, MAE, MAPE, WMAPE, and IOS indicated the error prediction.…”

Section: Model Development Results and Discussionmentioning

confidence: 99%

“…These analyses of sensitivity may take on either a linear or nonlinear form. Numerous scholars have employed the cosine amplitude method (CAM) in conducting sensitivity analysis [ 64 , 65 ]. CAM determines the sensitivity of input variables using below equation: where X i is the i th input, and X j I the j th output.…”

Section: Model Development Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Fereidooni,

Karimi,

Ghasemi

2024

PLoS ONE

View full text Add to dashboard Cite

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.

show abstract

Section: Model Development Results and Discussionmentioning

confidence: 99%

Section: Model Development Results and Discussionmentioning

confidence: 99%

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

Fereidooni,

Karimi,

Ghasemi

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…For instance, references 16 – 18 demonstrate modeling using the cosine amplitude method, and relevant algorithms were then employed to analyze and predict various engineering issues. Simultaneously, numerous machine learning studies to solve engineering problems have proposed several valuable and innovative designs 19 – 22 .…”

Section: Introductionmentioning

confidence: 99%

Calibration of contact parameters of sandy soil for planting tiger nut based on non-linear tools

Qi,

Chen,

Yang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

A methodology combining physical experiments with simulation was employed to acquire contact parameters of sandy soil precisely for planting tiger nuts in the desert area of Xinjiang. The stacking angle under different parameter combinations was applied as a response value. Through the Plackett–Burman test, several factors that have a significant influence were determined. The steepest ascent test was conducted to establish the finest scope of values for these parameters. The stacking angle was considered the response variable, and non-linear tools were used to optimize these parameters for simulation. The findings showed that applying response surface methodology (RSM) resulted in a relative error of 1.24%. In the case of BP-GA, the relative error compared to the physical test value was 0.34%, while for BP, it was 2.18%. After optimization using Wavelet Neural Network (WNN), the relative error was reduced to only 0.15%. Results suggest that WNN outperforms the RSM model, and the sandy soil model and parameters generated using WNN can be effectively utilized for discrete element simulation research.

show abstract

“…frequently employed to assess regression issues [63,64]. RMSE, MSE, MAE, MAPE, WMAPE, and IOS indicated the error prediction.…”

Section: Plos Onementioning

confidence: 99%

“…linear or nonlinear form. Numerous scholars have employed the cosine amplitude method (CAM) in conducting sensitivity analysis [64,65]. CAM determines the sensitivity of input variables using below equation:…”

Section: Plos Onementioning

confidence: 99%

Untitled

View full text Add to dashboard Cite

A Scientometrics Review of Soil Properties Prediction Using Soft Computing Approaches

Cited by 21 publications

References 188 publications

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

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

Calibration of contact parameters of sandy soil for planting tiger nut based on non-linear tools

Untitled

Contact Info

Product

Resources

About