A Modified Empirical Model for Predicting Liquefaction in Partially Saturated Sands

Geotechnical and Geological Engineering, Journal Year: 2025, Volume and Issue: 43(5)

Published: April 21, 2025

Language: Английский

---

Soft voting ensemble classifier for liquefaction prediction based on SPT data

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(8)

Published: May 3, 2025

Language: Английский

---

Experimental and Machine Learning-Based Analysis of Oxide Ratios in Alumina-Silicate Geopolymer Formation

Iranian Journal of Science and Technology Transactions of Civil Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: May 8, 2025

Language: Английский

---

Prediction and Factor Analysis of Liquefaction Ground Subsidence Based on Machine-Learning Techniques

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(7), P. 2713 - 2713

Published: March 23, 2024

Liquefaction is a significant challenge in the fields of earthquake risk assessment and soil dynamics, as it has potential to cause extensive damage buildings infrastructure through ground failure. During 2011 Great East Japan Earthquake, Urayasu City Chiba Prefecture experienced severe liquefaction, leading evacuation losses due effect liquefaction on roads. Therefore, developing quantitative predictions subsidence caused by understanding its contributing factors are imperative preparing for future mega-earthquakes. This research novel because previous primarily focused predictive models determining presence or absence there few examples available magnitude after occurred. study extracts features from existing datasets builds model, supplemented factor analysis. Using Cabinet Office Japan’s Nankai Trough Megathrust Earthquake liquefaction-induced was designated dependent variable. A gradient-boosted decision-tree (GDBT) prediction model then developed. Additionally, Shapley additive explanations (SHAP) method employed analyze contribution each feature results. The found that XGBoost outperformed LightGBM terms accuracy, with predicted values closely aligned actual measurements, thereby proving effectiveness predicting liquefaction. Furthermore, demonstrated assessments, which were previously challenging, can now be interpreted using SHAP factors. enables accountable wide-area subsidence.

Language: Английский

---

Modeling Static Liquefaction Susceptibility of Saturated Clayey Sand using Advanced Machine-Learning techniques

Transportation Infrastructure Geotechnology, Journal Year: 2024, Volume and Issue: 11(5), P. 2903 - 2931

Published: April 27, 2024

Language: Английский

---