A staged U-Net with ConvLSTM and super-resolution predicts 3D plume dispersion up to three orders of magnitude faster than LES, outperforming a high-resolution baseline on test simulations.
Camps-Valls, D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Staged Deep Learning Approach to Spatial Refinement in 3D Temporal Atmospheric Transport
A staged U-Net with ConvLSTM and super-resolution predicts 3D plume dispersion up to three orders of magnitude faster than LES, outperforming a high-resolution baseline on test simulations.