Physics-Informed Neural Network for Stability Analysis of Embankments Supported by GESCs with Bending Deformation
Abstract
Abstract The stability assessment of embankments on soft soils improved with geosynthetic-encased stone columns (GESCs) is complex, particularly when considering the bending deformation of columns under seismic loading. This study proposes a novel physics-informed neural network (PINN) framework, integrating a conventional machine learning model with a physical constraint (column bending deformation) to reformulate the loss function for enhanced prediction accuracy. A high-quality dataset is generated through the proposed and validated theoretical method that incorporates the bending moment contribution of GESCs. A set of specific equations accounting for the bending deformation of the column is derived and directly integrated into the PINN model as a physical law. The trained PINN successfully learns the complex mapping from 15 input geotechnical and geometric parameters to critical outputs of the factor of safety (FS), the critical bending moment ( M u ), compressive strength ( f c ), and the compression central angle ( α ). Validation and test results demonstrate exceptional predictive accuracy, with coefficients of determination exceeding 99%. Furthermore, a global sensitivity analysis quantifies the direct mutual influence of each input parameter. The developed PINN model can rapidly achieve the probabilistic stability assessment and optimized design of GESC-supported embankments.
Read the paper
Related studies
- Preliminary Toxicity Analysis of 3DCRT versus IMRT on the High Dose Arm of the RTOG 0126 Prostate Cancer Trial
- Adaptive Radiotherapy for Head and Neck Cancer: Initial Clinical Outcomes from a Prospective Trial
- American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology
- Motion Management Strategies and Technical Issues Associated with Stereotactic Body Radiotherapy of Thoracic and Upper Abdominal Tumors: A Review from NRG Oncology
- High-dose-rate interstitial brachytherapy as a monotherapy for localized prostate cancer: treatment description and preliminary results of a phase I/II clinical trial
- Highly efficient training, refinement, and validation of a knowledge-based plan quality control system for radiotherapy clinical trials
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.