Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks 事件

Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks arXiv:2605.30167v1 Announce Type: cross Abstract: Predicting a complete spatially correlated field from sparse observations is a fundamental challenge in spatial statistics and environmental modelling. Classical interpolation methods such as Kriging rely on Gaussian process assumptions and variography, which can limit their effectiveness in non-stationary settings and require substantial domain exper