Interpretable GNN–Residual Kriging for spatial prediction and investigation-priority zoning of soil mercury in a karst agricultural region
Introduction Soil mercury (Hg) in karst agricultural regions is commonly characterized by strong local heterogeneity, which limits the ability of conventional interpolation methods to delineate localized enrichment. Methods We developed an interpretable graph neural network–residual kriging (GNN-RK) framework for soil...
Zhizhuo Liu, Zhizhuo Liu, Junjie Ning et al.
· Frontiers in Environmental S... · 0 citations