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

TL;DR

AirRadar employs deep neural networks to accurately estimate air quality in unmonitored regions across China, reducing reliance on costly monitoring stations and enhancing real-time environmental assessment.

Contribution

This paper introduces AirRadar, a novel deep learning model that reconstructs air quality data in unmonitored areas using learnable mask tokens and a two-stage process, improving spatial inference accuracy.

Findings

Outperforms multiple baseline models in accuracy.

Effective with varying degrees of unobserved data.

Validated on a large dataset from 1,085 stations across China.

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.