A per-instance learned graph-network transfer between coarse and fine discrete-field optimizations improves Darcy and EIT coefficient reconstructions without surrogates or pretraining.
Computational Methods for Inverse Problems
2 Pith papers cite this work, alongside 2,380 external citations. Polarity classification is still indexing.
2
Pith papers citing it
2,380
external citations · OpenAlex
years
2026 2representative citing papers
Curlometer analysis of Swarm data and simulations shows FACs depart from stationarity below 100 km, time-shifted estimates diverge at meso-scales, and poor tetrahedral geometry produces spurious perpendicular currents unless mitigated by quality filters.
citing papers explorer
-
ResiPhy-MDNF: A Residual-Based Physics-Aware Multilevel Discrete Neural Field Framework for PDE-Constrained Inverse Problems
A per-instance learned graph-network transfer between coarse and fine discrete-field optimizations improves Darcy and EIT coefficient reconstructions without surrogates or pretraining.
-
On the curlometer measurement of field-aligned and perpendicular currents in low Earth orbit: Swarm observations and whole geospace simulations
Curlometer analysis of Swarm data and simulations shows FACs depart from stationarity below 100 km, time-shifted estimates diverge at meso-scales, and poor tetrahedral geometry produces spurious perpendicular currents unless mitigated by quality filters.