Sentence embeddings reduce reconstruction error by 81% in Darcy-flow inversion by providing categorical geological constraints, with limited added value from within-class text detail.
Water Resources Research 56, e2019WR026731
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
QCPIKAN is a quantum-classical physics-informed KAN that claims exponential high-frequency error convergence and superior accuracy over prior QCPINNs on single-phase, transport, and two-phase seepage PDEs.
Latent diffusion model parameterization allows MCMC and SMC to outperform latent-space ESMDA in data mismatch and uncertainty reduction for 3D subsurface DA, while model-space ESMDA produces unrealistic posteriors.
A variational autoencoder plus conditional latent diffusion model with a physics-informed residual corrector generates synthetic fields that improve symbolic regression recovery on sparse heat conduction, Navier-Stokes, and gravitational data.
citing papers explorer
-
What Do Language Priors Contribute to Darcy-Flow Inversion? A Mechanistic Audit
Sentence embeddings reduce reconstruction error by 81% in Darcy-flow inversion by providing categorical geological constraints, with limited added value from within-class text detail.
-
Quantum-classical physics-informed Kolmogorov-Arnold networks for PDEs
QCPIKAN is a quantum-classical physics-informed KAN that claims exponential high-frequency error convergence and superior accuracy over prior QCPINNs on single-phase, transport, and two-phase seepage PDEs.
-
Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
Latent diffusion model parameterization allows MCMC and SMC to outperform latent-space ESMDA in data mismatch and uncertainty reduction for 3D subsurface DA, while model-space ESMDA produces unrealistic posteriors.
-
Data Enrichment for Symbolic Regression Using Diffusion Models
A variational autoencoder plus conditional latent diffusion model with a physics-informed residual corrector generates synthetic fields that improve symbolic regression recovery on sparse heat conduction, Navier-Stokes, and gravitational data.