A Novel Approach for Emergency Mitigation of Settlement of In-Service Pile Foundations in Permafrost Regions

Опубликована: Янв. 1, 2025

Язык: Английский

---

A Framework for Estimating Matric Suction in Compacted Fine‐Grained Soils Based on a Machine Learning‐Assisted Conceptual Model

International Journal for Numerical and Analytical Methods in Geomechanics, Год журнала: 2025, Номер unknown

Опубликована: Апрель 3, 2025

ABSTRACT In this study, a hybrid black‐ and white‐box machine learning (ML) framework is proposed for matric suction estimation in compacted fine‐grained soils, utilizing ML techniques, namely, particle swarm optimized support vector regression (PSO‐SVR) multi‐gene genetic programming (MGGP). This objective achieved through developing novel ML‐based method designing requisite soil parameters, including new parameter, the “effective degree of aggregation”. parameter captures influence varying structures associated with different initial water content conditions soils estimating suction. Additionally, sensitivity analyses are performed to better understand significance effective aggregation other critical properties. Explicit equations derived from MGGP models, enabling their use using spreadsheets alleviating reliance on complex tools. The models promising prediction hydro‐mechanical behavior related properties, facilitating application conventional geotechnical engineering practice.

Язык: Английский

---

A new model for predicting thermal conductivity of unsaturated soils using the soil-water characteristic curve

International Journal of Heat and Mass Transfer, Год журнала: 2025, Номер 247, С. 127153 - 127153

Опубликована: Апрель 26, 2025

Язык: Английский

---