A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data

TL;DR

This study develops a machine learning framework to produce high-resolution daily PM2.5 maps for Tehran using satellite AOD data, achieving significant accuracy improvements over previous methods.

Contribution

It introduces a novel framework combining data preprocessing, regression modeling, and deployment to map PM2.5 at 1 km resolution in Tehran.

Findings

Achieved daily 1 km resolution PM2.5 mapping with R2 ~0.74

Model RMSE was better than 9.0 mg/m3

First high-resolution PM2.5 mapping in Tehran

Abstract

This paper investigates the possibility of high resolution mapping of PM2.5 concentration over Tehran city using high resolution satellite AOD (MAIAC) retrievals. For this purpose, a framework including three main stages, data preprocessing; regression modeling; and model deployment was proposed. The output of the framework was a machine learning model trained to predict PM2.5 from MAIAC AOD retrievals and meteorological data. The results of model testing revealed the efficiency and capability of the developed framework for high resolution mapping of PM2.5, which was not realized in former investigations performed over the city. Thus, this study, for the first time, realized daily, 1 km resolution mapping of PM2.5 in Tehran with R2 around 0.74 and RMSE better than 9.0 mg/m3. Keywords: MAIAC; MODIS; AOD; Machine learning; Deep learning; PM2.5; Regression