GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values
arXiv:2508.14083v3 Announce Type: replace Abstract: The ubiquity of missing data in urban intelligence systems, attributable to adverse environmental conditions and equipment failures, poses a significant challenge to the efficacy of downstream applications, notably in the realms of traffic forecasting and energy consumption prediction. Therefore, it is imperative to develop a robust spatio-temporal learning methodology capable of extracting meaningful insights from incomplete datasets. Despite the existence of methodologies for spatio-temporal graph forecasting in the presence of missing valu
The increasing complexity of urban systems and the prevalence of incomplete datasets necessitate advanced AI methodologies for robust spatio-temporal analysis.
This research addresses a critical limitation in urban intelligence, enabling more reliable forecasting in areas like traffic and energy despite real-world data imperfections.
Spatio-temporal graph forecasting models can now effectively handle missing data, improving accuracy and applicability in dynamic urban environments.
- · Urban planners
- · Smart city developers
- · Logistics companies
- · Energy grid operators
- · Traditional forecasting methods
- · Systems highly sensitive to data gaps
Improved accuracy in traffic prediction and energy demand forecasting.
More efficient resource allocation and infrastructure management in smart cities.
Enhanced resilience and responsiveness of urban systems to real-time disruptions and environmental changes.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG