Predicting maximum pitting corrosion depth in buried transmission pipelines: Insights from tree-based machine learning and identification of influential factors

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 187, P. 1269 - 1285

Published: May 9, 2024

Pitting corrosion is a primary type of external that poses critical challenge in the oil and gas industry, potentially leading to severe environmental, health, economic consequences if left unaddressed. Researchers have attempted comprehend forecast it through diverse methods, including machine learning artificial intelligence. However, achieving precise estimation pitting growth while considering influence various environmental operational factors remains concern. This study aims develop model by employing tree-based algorithms, Decision Tree, Random Forest, LightGBM, CatBoost, XGBoost, enhance prediction accuracy maximum depth buried transmission pipelines also facilitating interpretability. The Forest was found be best-performing with mean absolute error (MAE) 0.588. Beyond accuracy, present analysis contributes practical insights for industry application. First, identifies pipes at high risk under challenging conditions, enabling targeted preventive measures. Secondly, model's interpretation, utilising game-theoretic Shapely values permutation importance, informs strategic decisions on burial new pipes, ultimately extending their lifespan. These applications emphasise potential our findings significantly improve safety, reliability, mitigation strategies pipeline operations.

Language: Английский

---

Integrated convolution and self-attention for improving peptide toxicity prediction

Bioinformatics, Journal Year: 2024, Volume and Issue: 40(5)

Published: May 1, 2024

Abstract Motivation Peptides are promising agents for the treatment of a variety diseases due to their specificity and efficacy. However, development peptide-based drugs is often hindered by potential toxicity peptides, which poses significant barrier clinical application. Traditional experimental methods evaluating peptide time-consuming costly, making process inefficient. Therefore, there an urgent need computational tools specifically designed predict accurately rapidly, facilitating identification safe candidates drug development. Results We provide here novel approach, CAPTP, leverages power convolutional self-attention enhance prediction from amino acid sequences. CAPTP demonstrates outstanding performance, achieving Matthews correlation coefficient approximately 0.82 in both cross-validation settings on independent test datasets. This performance surpasses that existing state-of-the-art predictors. Importantly, maintains its robustness generalizability even when dealing with data imbalances. Further analysis reveals certain sequential patterns, particularly head central regions crucial determining toxicity. insight can significantly inform guide design safer drugs. Availability implementation The source code freely available at https://github.com/jiaoshihu/CAPTP.

Language: Английский

---

Imbalanced rock burst assessment using variational autoencoder-enhanced gradient boosting algorithms and explainability

Underground Space, Journal Year: 2024, Volume and Issue: 17, P. 226 - 245

Published: Jan. 21, 2024

We conducted a study to evaluate the potential and robustness of gradient boosting algorithms in rock burst assessment, established variational autoencoder (VAE) address imbalance dataset, proposed multilevel explainable artificial intelligence (XAI) tailored for tree-based ensemble learning. collected 537 data from real-world records selected four critical features contributing occurrences. Initially, we employed visualization gain insight into data's structure performed correlation analysis explore distribution feature relationships. Then, set up VAE model generate samples minority class due imbalanced distribution. In conjunction with VAE, compared evaluated six state-of-the-art models, including classical logistic regression model, prediction. The results indicated that outperformed single VAE-classifier original classifier, VAE-NGBoost yielding most favorable results. Compared other resampling methods combined NGBoost datasets, such as synthetic oversampling technique (SMOTE), SMOTE-edited nearest neighbours (SMOTE-ENN), SMOTE-tomek links (SMOTE-Tomek), yielded best performance. Finally, developed XAI using sensitivity analysis, Tree Shapley Additive exPlanations (Tree SHAP), Anchor provide an in-depth exploration decision-making mechanics VAE-NGBoost, further enhancing accountability models predicting

Language: Английский

---

Automatic digitalization of railway interlocking systems engineering drawings based on hybrid machine learning methods

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127532 - 127532

Published: April 1, 2025

Language: Английский

---

Spatial Mapping and Prediction of Groundwater Quality Using Ensemble Learning Models and SHapley Additive exPlanations with Spatial Uncertainty Analysis

Water, Journal Year: 2024, Volume and Issue: 16(17), P. 2375 - 2375

Published: Aug. 24, 2024

The spatial mapping and prediction of groundwater quality (GWQ) is important for sustainable management, but several research gaps remain unexplored, including the inaccuracy interpolation, limited consideration geological environment human activity effects, limitation to specific pollutants, unsystematic indicator selection. This study utilized entropy-weighted water index (EWQI), LightGBM model, pressure-state-response (PSR) framework SHapley Additive exPlanations (SHAP) analysis address above gaps. normalized importance (NI) shows that NO3− (0.208), Mg2+ (0.143), SO42− (0.110), Cr6+ (0.109) Na+ (0.095) should be prioritized as parameters remediation, skewness EWQI distribution indicates although most sampled locations have acceptable GWQ, a few areas suffer from severely poor GWQ. PSR identifies 13 indicators environments activities SMP Despite high AUROCs (0.9074, 0.8981, 0.8885, 0.9043) across four random training testing sets, it was surprising significant uncertainty observed, with Pearson correlation coefficients (PCCs) 0.5365 0.8066. We addressed this issue by using spatial-grid average probabilities maps. Additionally, population nighttime light are key indicators, while net recharge, land use cover (LULC), degree urbanization lowest importance. SHAP highlights both positive negative impacts on identifying point-source pollution main cause GWQ in area. Due field, future studies focus six aspects: multi-method assessment, quantitative relationships between comparisons various models, application selection, development methods reduce uncertainty, explainable machine learning techniques management.

Language: Английский

---

Guided analysis of fracture toughness and hydrogen-induced embrittlement crack growth rate in quenched-and-tempered steels using machine learning

International Journal of Pressure Vessels and Piping, Journal Year: 2024, Volume and Issue: 210, P. 105247 - 105247

Published: June 18, 2024

Language: Английский

---

Risk prediction based on oversampling technology and ensemble model optimized by tree-structured parzed estimator

International Journal of Disaster Risk Reduction, Journal Year: 2024, Volume and Issue: 111, P. 104753 - 104753

Published: Aug. 12, 2024

Language: Английский

---

Tunnel lining defects identification using TPE-CatBoost algorithm with GPR data: A model test study

Tunnelling and Underground Space Technology, Journal Year: 2024, Volume and Issue: 157, P. 106275 - 106275

Published: Dec. 18, 2024

Language: Английский

---

DEM parameter calibration based on multi-objective Bayesian optimization and prior physical information

Acta Geotechnica, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 16, 2025

Language: Английский

---

Integrating PCA and XGBoost for Predicting UACLC of Steel-Reinforced Concrete-Filled Square Steel Tubular Columns at Elevated Temperatures

Case Studies in Construction Materials, Journal Year: 2025, Volume and Issue: unknown, P. e04456 - e04456

Published: Feb. 1, 2025

Language: Английский

---