48

Predicting Global Variations in Outdoor PM2.5 Concentrations using Satellite Images and Deep Convolutional Neural Networks

Abstract

Here we present a new method of estimating global variations in outdoor PM2.5_{2.5} concentrations using satellite images combined with ground-level measurements and deep convolutional neural networks. Specifically, new deep learning models were trained over the global PM2.5_{2.5} concentration range (<<1-436 μ\mug/m3^3) using a large database of satellite images paired with ground level PM2.5_{2.5} measurements available from the World Health Organization. Final model selection was based on a systematic evaluation of well-known architectures for the convolutional base including InceptionV3, Xception, and VGG16. The Xception architecture performed best and the final global model had a root mean square error (RMSE) value of 13.01 μ\mug/m3^3 (R2^2=0.75) in the disjoint test set. The predictive performance of our new global model (called IMAGE-PM2.5_{2.5}) is similar to the current state-of-the-art model used in the Global Burden of Disease study but relies only on satellite images as input. As a result, the IMAGE-PM2.5_{2.5} model offers a fast, cost-effective means of estimating global variations in long-term average PM2.5_{2.5} concentrations and may be particularly useful for regions without ground monitoring data or detailed emissions inventories. The IMAGE-PM2.5_{2.5} model can be used as a stand-alone method of global exposure estimation or incorporated into more complex hierarchical model structures.

View on arXiv
Comments on this paper