ModelIGNNK / 学习式克里金GNN
IGNNK
A learned kriging interpolation model based on graph neural networks, used for inductive node inference in spatiotemporal forecasting.
Timeline (last 90 days)
Nov 4
In inductive prediction on unseen stations, OmniST outperforms nearest-neighbor interpolation and also outperforms the learned kriging GNN (IGNNK), and only OmniST carries coverage guarantees.
Unverified50%