Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching
arXiv:2610.31677v1 Announce Type: new Abstract: We present a surrogate-accelerated Bayesian history-matching framework, demonstrated on a realistic synthetic model ($N=100{,}188$ cells). The forward map $\mathcal{G}$ is replaced by a Fourier neural operator $\mathcal{G}_\theta$ trained in a closed…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv stat.ML
Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching