ISI Net: A novel paradigm integrating interpretability and intelligent selection in ensemble learning for accurate wind power forecasting DOI
Bingjie Liang, Zhirui Tian

Energy Conversion and Management, Год журнала: 2025, Номер 332, С. 119752 - 119752

Опубликована: Апрель 2, 2025

Язык: Английский

Estimating Carbon Dioxide Solubility in Brine Using Mixed Effects Random Forest Based on Genetic Algorithm: Implications for Carbon Dioxide Sequestration in Saline Aquifers DOI
Grant Charles Mwakipunda,

AL-Wesabi Ibrahim,

Allou Koffi Franck Kouassi

и другие.

SPE Journal, Год журнала: 2024, Номер 29(11), С. 6530 - 6546

Опубликована: Сен. 20, 2024

Summary Accurate prediction of carbon dioxide (CO2) solubility in brine is crucial for the success capture and storage (CCS) by means geological formations like aquifers. This study investigates effectiveness a novel genetic algorithm-mixed effects random forest (GA-MERF) model estimating CO2 brine. The model’s performance compared with established methods group method data handling (GMDH), backpropagation neural networks (BPNN), traditional thermodynamic models. GA-MERF utilizes experimental collected from literature, encompassing key factors influencing solubility: temperature (T), pressure (P), salinity. These are used to train validate ability predict values. results demonstrate superiority other Notably, achieves high coefficient determination (R) 0.9994 unseen data, indicating strong correlation between estimated actual Furthermore, exhibits exceptionally low error metrics, root mean squared (RMSE) 2×10-8 absolute (MAE) 1.8×10-11, signifying outstanding accuracy Beyond its accuracy, offers an additional benefit—reduced computational time models investigated, 65 seconds. efficiency makes particularly attractive tool real-world applications where rapid reliable predictions critical. In conclusion, this presents as powerful efficient predicting Its superior existing previous literature highlights potential valuable researchers engineers working on CCS projects utilizing aquifer storage. rates, reduced make promising candidate advancing development effective technologies.

Язык: Английский

Процитировано

9

An Efficient and Interpretable Stacked Model for Wind Speed Estimation Based on Ensemble Learning Algorithms DOI

Ankit Jha,

Vansh Goel,

Manish Kumar

и другие.

Energy Technology, Год журнала: 2024, Номер 12(6)

Опубликована: Апрель 24, 2024

Wind energy has gained tremendous attention recently due to its abundance potential and obviate the adverse impacts of fossil fuel consumption. However, efficient development operation wind systems require precise accurate speed prediction. To fulfill this aim, machine learning algorithms have shown prowess in accurately predicting study proposes an interpretable stacked ensemble with ridge regressor utilizing ML such as catboost (CB), gradient boost (GB), multilayer perceptron (MLP), random forest (RF) a base model. The models’ estimations are integrated by applying enhance accuracy estimation. dataset consists 87 600 samples from which 80% used for training. proposed approach provides interpretability prediction results through Shapley additive explanations feature importance analysis. result method is calculated comparing estimation outcomes each model CB, GB, MLP, RF terms error metrics root mean squared (RMSE) absolute (MAE). outperforms others reduction RMSE 19.89% MAE 24% respectively.

Язык: Английский

Процитировано

8

Predicting employee attrition and explaining its determinants DOI Creative Commons
Shahin Manafi Varkiani, Francesco Pattarin, Tommaso Fabbri

и другие.

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126575 - 126575

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1

An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification DOI Creative Commons

Bin Lv,

Haixia Gong,

Dong Bin

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(4), С. 1893 - 1893

Опубликована: Фев. 12, 2025

This study proposes an explainable extreme gradient boosting (XGBoost) model for predicting the international roughness index (IRI) and identifying key influencing factors. A comprehensive dataset integrating multiple data sources, such as structure, climate traffic load, is constructed. voting-based feature selection strategy adopted to identify factors, which are used inputs prediction model. Multiple machine learning (ML) models trained predict IRI with constructed dataset, XGBoost performs best coefficient of determination (R2) reaching 0.778. Finally, interpretable techniques including importance, Shapley additive explanations (SHAP) partial dependency plots (PDPs) employed reveal mechanism factors on IRI. The results demonstrate that conditions load play a critical role in deterioration provides relatively universal perspective factor identification, outputs proposed method contribute making scientific maintenance strategies roads some extent.

Язык: Английский

Процитировано

1

ISI Net: A novel paradigm integrating interpretability and intelligent selection in ensemble learning for accurate wind power forecasting DOI
Bingjie Liang, Zhirui Tian

Energy Conversion and Management, Год журнала: 2025, Номер 332, С. 119752 - 119752

Опубликована: Апрель 2, 2025

Язык: Английский

Процитировано

1