New framework uses Equivariant Neural Fields for scalable travel-time prediction

Researchers have introduced Equivariant Neural Eikonal Solvers, a new framework that combines Equivariant Neural Fields with Neural Eikonal Solvers. This approach uses a shared neural network backbone conditioned on signal-specific latent variables to model various Eikonal solutions. The integration of Equivariant Neural Fields ensures that transformations of the latent point cloud lead to predictable changes in the Eikonal solution, offering enhanced representation efficiency and geometric grounding. The framework accurately models Eikonal travel-time solutions across different Riemannian manifolds, demonstrating superior performance, scalability, and user controllability compared to existing methods in seismic travel-time modeling. AI

IMPACT This framework offers improved scalability and controllability for complex physics-informed modeling tasks.

RANK_REASON The cluster contains a research paper detailing a novel framework for Eikonal travel-time prediction using neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Alejandro García-Castellanos
• Equivariant Neural Eikonal Solvers
• Equivariant Neural Fields
• Euclidean
• Hyperbolica
• Lie group
• Neural Eikonal Solvers
• neural operator
• physics-informed neural networks
• Position-orientation adaptive smoothing of diffusion weighted magnetic resonance data (POAS)
• Riemannian manifold
• seismic travel-time modeling
• Spherical

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →