A diffusion-contrastive GNN with virtual nodes reduces wind nowcasting MAE by 30-46% in unobserved regions on Netherlands station data compared to interpolation and regression baselines.
Mehrkanoon, Deep shared representation learning for weather elements forecasting, Knowledge-Based Systems 179 (2019) 120–128
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Diffusion-Contrastive Graph Neural Network with Virtual Nodes for Wind Nowcasting in Unobserved Regions
A diffusion-contrastive GNN with virtual nodes reduces wind nowcasting MAE by 30-46% in unobserved regions on Netherlands station data compared to interpolation and regression baselines.