A Deep Learning Approach for Meter-Scale Air Quality Estimation in Urban Environments Using Very High-Resolution Satellite Imagery

Abstract

BACKGROUND AND AIM: Air Quality (AQ) is currently measured using ground monitoring stations which require funding and infrastructure to support and lack spatial coverage. In contrast, high-resolution commercial satellite imagery (⪯2 m/pixel) can be produced for almost any location on Earth and is readily available. The goal of this project is to develop a pipeline that uses MAXAR satellite imagery to produce meter-scale, continuous maps of AQ for any city around the globe, with greater resolution and coverage than existing methods. METHODS: We developed a Deep Neural Network (DNN) model that can produce AQ estimates for previously unseen urban locations using satellite imagery. The model is based on the VGG-16 pretrained neural network architecture. We used this architecture to extract spatial features from satellite imagery that are passed on to Fully Connected layers to produce an estimate of PM2.5 and NO2 concentrations. We partitioned satellite imagery into 612,248 patches and fed these patches into the model to produce a 100m (200m) continuous grid of PM2.5 (NO2) estimates. RESULTS:We fed the high-resolution (0.5m–2.5m) commercial satellite imagery to a DNN to learn the association between visual urban features and air pollutants. The developed model, which solely uses satellite imagery, was tested and evaluated using both ground monitoring observations and land-use regression modeled PM2.5 and NO2 concentrations over London, Vancouver (BC), Los Angeles, and New York City. The results demonstrate a low error with a total RMSE 2 µg/m3 and highlight the contribution of specific urban features, such as green areas and roads, to continuous meter-scale AQ estimations. CONCLUSIONS:This approach offers promise for scaling to global applications in developed and developing urban environments. Further analysis on domain transferability will enable application of a parsimonious model based merely on satellite images to create meter-scale AQ maps in developing cities, where current and historical ground data is limited. KEYWORDS: Air quality. Remote Sensing, Urban environment, Deep learning, Satellite Imagery