Evaluation and analysis of liquefaction potential of gravelly soils using explainable probabilistic machine learning model

Computers and Geotechnics, Год журнала: 2024, Номер 167, С. 106051 - 106051

Опубликована: Янв. 8, 2024

Язык: Английский

---

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

---

Interpretable prediction of thermal sensation for elderly people based on data sampling, machine learning and SHapley Additive exPlanations (SHAP)

Building and Environment, Год журнала: 2023, Номер 242, С. 110602 - 110602

Опубликована: Июль 8, 2023

Язык: Английский

---

Liquefaction Potential Assessment of Soils Using Machine Learning Techniques: A State-of-the-Art Review from 1994–2021

International Journal of Geomechanics, Год журнала: 2023, Номер 23(7)

Опубликована: Апрель 28, 2023

Machine learning (ML) has emerged as a powerful tool for prediction of systems behavior in many engineering disciplines. A few applications ML techniques are available geotechnical and other fields civil engineering. The existing review studies on the application conventional earthquake geotechnics broader areas but not specific to liquefaction phenomenon. Studies exist potential cohesionless soils using with varying degree success. More needed formalize use seismic assessment. In this review, an attempt is made critically literature applied analysis. published from 1994 2021 been collected, reviewed, presented systematically form easy understand tables figures. labeled based data requirement techniques, methods, in-situ tests. summary table highlights relative importance input variables dataset required Limitations methods models, large database, comparison four developed probabilistic analysis included. gap outlined followed by way forward future research. It concluded that there need update database modify algorithms so they become computationally efficient reliable

Язык: Английский

---

A Scientometrics Review of Soil Properties Prediction Using Soft Computing Approaches

Archives of Computational Methods in Engineering, Год журнала: 2023, Номер 31(3), С. 1519 - 1553

Опубликована: Ноя. 24, 2023

Язык: Английский

---

State-of-the-art review on the use of AI-enhanced computational mechanics in geotechnical engineering

Artificial Intelligence Review, Год журнала: 2024, Номер 57(8)

Опубликована: Июль 5, 2024

Abstract Significant uncertainties can be found in the modelling of geotechnical materials. This attributed to complex behaviour soils and rocks amidst construction processes. Over past decades, field has increasingly embraced application artificial intelligence methodologies, thus recognising their suitability forecasting non-linear relationships intrinsic review offers a critical evaluation AI methodologies incorporated computational mechanics for engineering. The analysis categorises four pivotal areas: physical properties, mechanical constitutive models, other characteristics relevant Among various analysed, ANNs stand out as most commonly used strategy, while methods such SVMs, LSTMs, CNNs also see significant level application. widely algorithms are Artificial Neural Networks (ANN), Random Forest (RF), Support Vector Machines (SVM), representing 35%, 19%, 17% respectively. extensive is domain accounting 59%, followed by applications at 16%. efficacy intrinsically linked type datasets employed, selected model input. study outlines future research directions emphasising need integrate physically guided adaptive learning mechanisms enhance reliability adaptability addressing multi-scale multi-physics coupled problems geotechnics.

Язык: Английский

---

Explainable Sinkhole Susceptibility Mapping Using Machine-Learning-Based SHAP: Quantifying and Comparing the Effects of Contributing Factors in Konya, Türkiye

Applied Sciences, Год журнала: 2025, Номер 15(6), С. 3139 - 3139

Опубликована: Март 13, 2025

Sinkholes, naturally occurring formations in karst regions, represent a significant environmental hazard, threatening infrastructure, agricultural lands, and human safety. In recent years, machine learning (ML) techniques have been extensively employed for sinkhole susceptibility mapping (SSM). However, the lack of explainability inherent these methods remains critical issue decision-makers. this study, Konya Closed Basin was mapped using an interpretable model based on SHapley Additive exPlanations (SHAP). The Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Machine (LightGBM) algorithms were employed, interpretability results enhanced through SHAP analysis. Among compared models, RF demonstrated highest performance, achieving accuracy 95.5% AUC score 98.8%, consequently selected development final map. analyses revealed that factors such as proximity to fault lines, mean annual precipitation, bicarbonate concentration difference are most variables influencing formation. Additionally, specific threshold values quantified, effects contributing analyzed detail. This study underscores importance employing eXplainable Artificial Intelligence (XAI) natural hazard modeling, SSM example, thereby providing decision-makers with more reliable comparable risk assessment.

Язык: Английский

---

Comparison of diverse machine learning algorithms for forest fire susceptibility mapping in Antalya, Türkiye

Advances in Space Research, Год журнала: 2024, Номер 74(2), С. 647 - 667

Опубликована: Апрель 16, 2024

Язык: Английский

---

Classification of geogrid reinforcement in aggregate using machine learning techniques

International Journal of Geo-Engineering, Год журнала: 2024, Номер 15(1)

Опубликована: Фев. 12, 2024

Abstract The present study proposes a novel ML methodology for differentiating between unstabilized aggregate specimens and those stabilized with triangular rectangular aperture geogrids. This utilizes the compiled experimental results obtained from under repeated loading into balanced, moderate-sized database. efficacy of five models, including tree-ensemble single-learning algorithms, in accurately identifying each specimen class was explored. Shapley’s additive explanation used to understand intricacies models determine global feature importance ranking input variables. All could identify an accuracy at least 0.9. outperformed when all three classes (unstabilized by geogrids) were considered, light gradient boosting machine showing best performance—an 0.94 area curve score 0.98. According explanation, resilient modulus confining pressure identified as most important features across models. Therefore, proposed may be effectively type presence geogrid reinforcement aggregates, based on few material properties performance loading.

Язык: Английский

---

Explainable machine learning-based prediction for aerodynamic interference of a low-rise building on a high-rise building

Journal of Building Engineering, Год журнала: 2023, Номер 82, С. 108285 - 108285

Опубликована: Дек. 14, 2023

Язык: Английский

---