Three edge-type physics-informed DeepONets coupled by a vertex flux optimization can solve drift-diffusion on metric graphs and recover initial conditions and edge velocities from sensor data.
Solid lines report training loss of various terms, dashed lines report validation loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
Three edge-type physics-informed DeepONets coupled by a vertex flux optimization can solve drift-diffusion on metric graphs and recover initial conditions and edge velocities from sensor data.