Night-time light (NTL) data, exemplified by the Black Marble dataset, has shown significant application potential across multiple domains due to the rich information that they provide on nocturnal light emissions. However, the VNP46A2 product, which is limited by considerable challenges stemming from extensive missing values. This problem is resolved through gap-filling methods, but existing approaches mostly disregard the spatiotemporal relationships and interactions in NTL measurements, thereby constraining efforts to treat temporal abruptness of NTL data, and ineffectively addressing the issue of numerous missing values. To overcome these deficiencies, we developed a gap-filling method based on graph neural networks (GNNs) considering spatiotemporal anisotropic geometric relationships. The method includes a graph construction algorithm from spatiotemporal cubes and a GNN model capturing spatiotemporal anisotropy. Its applicability is further enhanced by the fact that its application requires no prior knowledge. Experiments demonstrated the model's high accuracy (Formula: see text = 0.95 on the test set) and strong generalization. The gap-filled NTL data closely matches actual data in terms of morphology, intensity, and spatial continuity, outperforming other four different methods in consistency and dynamism. Ablation studies confirm the model's rational design with no computational redundancy. This approach provided a novel solution for remote sensing data imputation, supporting urban studies while expanding the application prospects of daily NTL products.
Xu et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: