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

TL;DR

This paper introduces a deep learning model using satellite images to estimate global outdoor PM2.5 pollution levels, achieving accuracy comparable to current methods but with greater simplicity and broader applicability.

Contribution

The study develops the IMAGE-PM2.5 model based solely on satellite images, providing a fast, cost-effective alternative for global PM2.5 estimation without ground measurements.

Findings

Xception architecture performed best among tested models.

Final model achieved RMSE of 13.01 μg/m³ and R² of 0.75.

Model's performance is comparable to state-of-the-art methods.

Abstract

Here we present a new method of estimating global variations in outdoor PM$_{2.5}$ concentrations using satellite images combined with ground-level measurements and deep convolutional neural networks. Specifically, new deep learning models were trained over the global PM$_{2.5}$ concentration range ($<$1-436 $\mu$g/m$^3$) using a large database of satellite images paired with ground level PM$_{2.5}$ 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 $\mu$g/m$^3$ (R$^2$=0.75) in the disjoint test set. The predictive performance of our new global model (called IMAGE-PM$_{2.5}$) 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-PM$_{2.5}$ model offers a fast, cost-effective means of estimating global variations in long-term average PM$_{2.5}$ concentrations and may be particularly useful for regions without ground monitoring data or detailed emissions inventories. The IMAGE-PM$_{2.5}$ model can be used as a stand-alone method of global exposure estimation or incorporated into more complex hierarchical model structures.