PulseAugur
LIVE 10:01:05
research · [2 sources] ·
0
research

New framework integrates functional priors into Bayesian PINN inversion

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have developed a new framework called fpBPINN to integrate functional priors into Bayesian inversion problems solved with physics-informed neural networks (PINNs). This framework addresses the challenge of defining prior distributions in function space rather than the typical weight space of neural networks. The study introduces two methods, FPI-BPINN and fParVI-PINN, and demonstrates their effectiveness in seismic traveltime tomography and Darcy-flow permeability inversion, showing accurate posterior distribution estimation. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces a novel method for incorporating physical constraints into Bayesian inversion, potentially improving accuracy in scientific modeling.

RANK_REASON The cluster contains an academic paper detailing a new methodology for solving inverse problems using neural networks.

Read on arXiv stat.ML →

COVERAGE [2]

  1. arXiv stat.ML TIER_1 · Ryoichiro Agata, Tomohisa Okazaki ·

    Functional-prior-based Bayesian PDE-constrained inversion using PINNs

    arXiv:2605.07060v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDE-constrained inverse problems, but their extension to Bayesian inversion still faces a fundamental difficulty: prior distributions are typically…

  2. arXiv stat.ML TIER_1 · Tomohisa Okazaki ·

    Functional-prior-based Bayesian PDE-constrained inversion using PINNs

    Physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDE-constrained inverse problems, but their extension to Bayesian inversion still faces a fundamental difficulty: prior distributions are typically defined in the weight space of neural networks, w…

RELATED ENTITIES

RELATED TOPICS