Explainable Ensemble Learning Approaches for Predicting the Compression Index of Clays DOI Creative Commons
Qi Ge,

Y. Xia,

Junwei Shu

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(10), P. 1701 - 1701

Published: Sept. 25, 2024

Accurate prediction of the compression index (cc) is essential for geotechnical infrastructure design, especially in clay-rich coastal regions. Traditional methods determining cc are often time-consuming and inconsistent due to regional variability. This study presents an explainable ensemble learning framework predicting clays. Using a comprehensive dataset 1080 global samples, four key input variables—liquid limit (LL), plasticity (PI), initial void ratio (e0), natural water content w—were leveraged accurate prediction. Missing data were addressed with K-Nearest Neighbors (KNN) imputation, effectively filling gaps while preserving dataset’s distribution characteristics. Ensemble techniques, including Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Extreme (XGBoost), Stacking model, applied. Among these, model demonstrated highest predictive performance Root Mean Squared Error (RMSE) 0.061, Absolute (MAE) 0.043, Coefficient Determination (R2) value 0.848 on test set. Model interpretability was ensured through SHapley Additive exPlanations (SHAP), e0 identified as most influential predictor. The proposed significantly improves both accuracy interpretability, offering valuable tool enhance design efficiency environments.

Language: Английский

Hybridization of Stochastic Hydrological Models and Machine Learning Methods for Improving Rainfall-Runoff Modelling DOI Creative Commons

Sianou Ezéckiel Houénafa,

Olatunji Johnson,

Erick Kiplangat Ronoh

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104079 - 104079

Published: Jan. 1, 2025

Language: Английский

Citations

3
A hybrid deep learning model for predicting atmospheric corrosion in steel energy structures under maritime conditions based on time-series data DOI Creative Commons
Mohamed El Amine Ben Seghier, Tam T. Truong, Christian Feiler

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104417 - 104417

Published: Feb. 1, 2025

Language: Английский

Citations

1
Machine Learning Prediction of Permeability Distribution in the X Field Malay Basin Using Elastic Properties DOI Creative Commons

Zaky Ahmad Riyadi,

John Oluwadamilola Olutoki, Maman Hermana

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103421 - 103421

Published: Nov. 1, 2024

Language: Английский

Citations

4
Automated Image-Based Condition Assessment of Built Environment: A State-of-the-Art Investigation of Damage Characteristics and Detection Requirements DOI Creative Commons
Leila Farahzadi,

Ibrahim Odeh,

Mahdi Kioumarsi

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104978 - 104978

Published: April 1, 2025

Language: Английский

Citations

0
Corrosion fatigue degradation of FRP tendon after acidic corrosion coupling with sustaining/fatigue loading DOI
Xia Liu, Xin Wang, Jingyang Zhou

et al.

Engineering Structures, Journal Year: 2025, Volume and Issue: 335, P. 120383 - 120383

Published: April 21, 2025

Language: Английский

Citations

0
ADVANCED PREDICTIVE MODELING OF SHEAR STRENGTH IN STAINLESS-STEEL COLUMN WEB PANELS USING EXPLAINABLE AI INSIGHTS DOI Creative Commons
Sina Sarfarazi, Rabee Shamass, Federico Guarracino

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103454 - 103454

Published: Nov. 1, 2024

Language: Английский

Citations

2
Explainable Ensemble Learning Approaches for Predicting the Compression Index of Clays DOI Creative Commons
Qi Ge,

Y. Xia,

Junwei Shu

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(10), P. 1701 - 1701

Published: Sept. 25, 2024

Accurate prediction of the compression index (cc) is essential for geotechnical infrastructure design, especially in clay-rich coastal regions. Traditional methods determining cc are often time-consuming and inconsistent due to regional variability. This study presents an explainable ensemble learning framework predicting clays. Using a comprehensive dataset 1080 global samples, four key input variables—liquid limit (LL), plasticity (PI), initial void ratio (e0), natural water content w—were leveraged accurate prediction. Missing data were addressed with K-Nearest Neighbors (KNN) imputation, effectively filling gaps while preserving dataset’s distribution characteristics. Ensemble techniques, including Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Extreme (XGBoost), Stacking model, applied. Among these, model demonstrated highest predictive performance Root Mean Squared Error (RMSE) 0.061, Absolute (MAE) 0.043, Coefficient Determination (R2) value 0.848 on test set. Model interpretability was ensured through SHapley Additive exPlanations (SHAP), e0 identified as most influential predictor. The proposed significantly improves both accuracy interpretability, offering valuable tool enhance design efficiency environments.

Language: Английский

Citations

0