Score: 0

STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach

Published: August 22, 2025 | arXiv ID: 2508.16161v1

By: Yujie Li , Zezhi Shao , Chengqing Yu and more

Potential Business Impact:

Fixes missing data for better predictions.

Business Areas:
Geospatial Data and Analytics, Navigation and Mapping

Spatio-temporal tasks often encounter incomplete data arising from missing or inaccessible sensors, making spatio-temporal kriging crucial for inferring the completely missing temporal information. However, current models struggle with ensuring the validity and generalizability of inferred spatio-temporal patterns, especially in capturing dynamic spatial dependencies and temporal shifts, and optimizing the generalizability of unknown sensors. To overcome these limitations, we propose Spatio-Temporal Aware Graph Adversarial Neural Network (STA-GANN), a novel GNN-based kriging framework that improves spatio-temporal pattern validity and generalization. STA-GANN integrates (i) Decoupled Phase Module that senses and adjusts for timestamp shifts. (ii) Dynamic Data-Driven Metadata Graph Modeling to update spatial relationships using temporal data and metadata; (iii) An adversarial transfer learning strategy to ensure generalizability. Extensive validation across nine datasets from four fields and theoretical evidence both demonstrate the superior performance of STA-GANN.

Country of Origin
🇨🇳 China

Page Count
11 pages

Category
Computer Science:
Machine Learning (CS)