Researchers have developed a Fourier Feature Physics-Informed Neural Network (FF-PINN) to address limitations in analyzing elasto-plastic problems in geotechnical engineering. Traditional Finite Element Methods (FEM) are computationally expensive, while standard Physics-Informed Neural Networks (PINNs) struggle with spectral bias, failing to accurately capture sharp gradients at elastic-plastic boundaries. The proposed FF-PINN embeds random Fourier feature mapping to mitigate spectral bias, achieving superior accuracy and reducing training time by half compared to conventional PINNs. This new framework offers a more efficient and accurate alternative for complex geotechnical analyses. AI
IMPACT This research offers a more computationally efficient and accurate AI-driven alternative for complex geotechnical engineering analyses, potentially reducing reliance on traditional, slower methods.
RANK_REASON The cluster contains an academic paper detailing a new research methodology.
Read on arXiv cs.NE (Neural & Evolutionary) →
- finite element method
- Fourier Feature Physics-Informed Neural Networks
- Geomaterials
- Non-Associative Mohr-Coulomb Model
- physics-informed neural networks
- Sompote Youwai
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
