Interpretable predictive modelling of outlet temperatures in Central Alberta’s hydrothermal system using boosting-based ensemble learning incorporating Shapley Additive exPlanations (SHAP) approach

Energy, Год журнала: 2025, Номер unknown, С. 134738 - 134738

Опубликована: Янв. 1, 2025

Язык: Английский

---

Data-driven joint multiobjective prediction and optimization for tunnel-induced adjacent bridge pier displacement: A case study in China

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 142, С. 109616 - 109616

Опубликована: Янв. 8, 2025

Язык: Английский

---

Investigating the impact of fatty acid profiles on biodiesel lubricity using artificial intelligence techniques

Cleaner Engineering and Technology, Год журнала: 2025, Номер unknown, С. 100913 - 100913

Опубликована: Фев. 1, 2025

Язык: Английский

---

ShapG: New feature importance method based on the Shapley value

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 148, С. 110409 - 110409

Опубликована: Март 8, 2025

Язык: Английский

---

Explainable machine learning-based fractional vegetation cover inversion and performance optimization – A case study of an alpine grassland on the Qinghai-Tibet Plateau

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102768 - 102768

Опубликована: Авг. 10, 2024

Fractional Vegetation Cover (FVC) serves as a crucial indicator in ecological sustainability and climate change monitoring. While machine learning is the primary method for FVC inversion, there are still certain shortcomings feature selection, hyperparameter tuning, underlying surface heterogeneity, explainability. Addressing these challenges, this study leveraged extensive field data from Qinghai-Tibet Plateau. Initially, selection algorithm combining genetic algorithms XGBoost was proposed. This integrated with Optuna tuning method, forming GA-OP combination to optimize learning. Furthermore, comparative analyses of various models inversion alpine grassland were conducted, followed by an investigation into impact heterogeneity on performance using NDVI Coefficient Variation (NDVI-CV). Lastly, SHAP (Shapley Additive exPlanations) employed both global local interpretations optimal model. The results indicated that: (1) exhibited favorable terms computational cost accuracy, demonstrating significant potential tuning. (2) Stacking model achieved among seven (R2 = 0.867, RMSE 0.12, RPD 2.552, BIAS −0.0005, VAR 0.014), ranking follows: > CatBoost LightGBM RFR KNN SVR. (3) NDVI-CV enhanced result reliability excluding highly heterogeneous regions that tended be either overestimated or underestimated. (4) revealed decision-making processes perspectives. allowed deeper exploration causality between features targets. developed high-precision scheme, successfully achieving accurate proposed approach provides valuable references other parameter inversions.

Язык: Английский

---

Predictive slope stability early warning model based on CatBoost

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 28, 2024

A model for predicting slope stability is developed using Categorical Boosting (CatBoost), which incorporates 6 features to characterize the state of stability. The trained a symmetric tree as base model, utilizing ordered boosting replace gradient estimation, enhances prediction accuracy. Comparative models including Support Vector Machine (SVM), Light Gradient (LGBM), Random Forest (RF), and Logistic Regression (LR) were introduced. Five performance evaluation metrics are utilized assess predictive capabilities CatBoost model. Based on predicted probability instability calculated, early warning further established. results suggest that demonstrates 6.25% disparity in accuracy between training testing sets, achieving precision 100% an Area Under Curve (AUC) value 0.95. This indicates high level robust ordering capabilities, effectively mitigating problem overfitting. offers reasonable classifications levels, providing valuable insights both research practical applications warning.

Язык: Английский

---

Hybrid Quantum Neural Network Model with Catalyst Experimental Validation: Application for the Dry Reforming of Methane

ACS Sustainable Chemistry & Engineering, Год журнала: 2024, Номер 12(10), С. 4121 - 4131

Опубликована: Фев. 23, 2024

Machine learning (ML), which has been increasingly applied to complex problems such as catalyst development, encounters challenges in data collection and structuring. Quantum neural networks (QNNs) outperform classical ML models, artificial (ANNs), prediction accuracy, even with limited data. However, QNNs have available qubits. To address this issue, we introduce a hybrid QNN model, combining parametrized quantum circuit an ANN structure. We used the sets of dry reforming methane reaction from literature in-house experimental results compare models. The exhibited superior accuracy faster convergence rate, achieving R2 0.942 at 2478 epochs, whereas achieved 0.935 3175 epochs. For 224 points previously unreported literature, enhanced generalization performance. It showed mean absolute error (MAE) 13.42, compared MAE 27.40 for under similar training conditions. This study highlights potential powerful tool solving catalysis chemistry, demonstrating its advantages over

Язык: Английский

---

Real-time pavement temperature prediction through ensemble machine learning

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 135, С. 108870 - 108870

Опубликована: Июнь 22, 2024

Язык: Английский

---

Machine Learning-Based Estimation of Reinforced Concrete Columns Stiffness Modifiers for Improved Accuracy in Linear Response History Analysis

Journal of Earthquake Engineering, Год журнала: 2024, Номер 29(1), С. 130 - 155

Опубликована: Окт. 3, 2024

Язык: Английский

---

A Feature Importance-Based Multi-Layer CatBoost for Student Performance Prediction

IEEE Transactions on Knowledge and Data Engineering, Год журнала: 2024, Номер 36(11), С. 5495 - 5507

Опубликована: Май 3, 2024

Student performance prediction is vital for identifying at-risk students and providing support to help them succeed academically. In this paper, we propose a feature importance-based multi-layer CatBoost approach predict the students' grade in period exam. The idea construct structure with increasingly important features layer by layer. Specifically, importance are first calculated sorted ascending order. each layer, least accumulated until reaching given threshold. Then, these selected used training CatBoost. Next, trained utilized generate that adds set their within After that, all train next This process repeated used. results show proposed model has best performance. Moreover, statistical test conducted based on 20-runs of experiments validates significant superiority our over compared models demonstrates efficacy enhancing model. indicates can decision makers educational quality.

Язык: Английский

---