AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

2025-01-22

AI Summary

To address the challenge of nationwide real-time air quality assessment caused by sparse monitoring station coverage, this paper proposes AirRadar—a deep neural network-based spatiotemporal reconstruction method. Its core innovation lies in a learnable masked token mechanism that models spatial dependencies and cross-regional distributional shifts in two stages, enabling robust air quality inference under sparse observations. Relying solely on data from the existing 1,085 national monitoring stations, AirRadar accurately reconstructs real-time PM₂.₅ and other key pollutants in uninstrumented regions. Evaluated on full-year real-world data, it significantly outperforms multiple baseline methods. Notably, it maintains high accuracy even when 50% of station data are missing. The implementation is publicly available.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is constrained by their significant costs. To address this limitation, we introduce emph{AirRadar}, a deep neural network designed to accurately infer real-time air quality in locations lacking monitoring stations by utilizing data from existing ones. By leveraging learnable mask tokens, AirRadar reconstructs air quality features in unmonitored regions. Specifically, it operates in two stages: first capturing spatial correlations and then adjusting for distribution shifts. We validate AirRadar's efficacy using a year-long dataset from 1,085 monitoring stations across China, demonstrating its superiority over multiple baselines, even with varying degrees of unobserved data. The source code can be accessed at https://github.com/CityMind-Lab/AirRadar.

Problem

• Air Quality Estimation
• China
• Monitoring Stations

Innovation

• AirRadar
• Air Quality Prediction
• Machine Learning