Assessment of Remote Sensing Data to Model PM10 Estimation in Cities with a Low Number of Air Quality Stations: A Case of Study in Quito, Ecuador

Researchers developed an artificial neuronal network (ANN) model using remote sensing data to estimate PM10 concentrations in Quito, Ecuador, achieving the highest accuracy (R² = 0.68, RMSE = 6.22) among tested methods. This approach offers a viable solution for cities with limited air quality monitoring infrastructure. The study compared Landsat-7 ETM+, Landsat-8 OLI/TIRS, and Aqua-Terra/MODIS satellite data alongside land use regression techniques, demonstrating that ANN outperforms traditional models in predicting PM10 levels. By leveraging publicly available remote sensing datasets, this method provides a scalable tool for air quality assessment in urban environments with sparse ground measurements.

Alvarez-Mendoza, C. I., Teodoro, A. C., Torres, N., & Vivanco, V. (2019). Assessment of Remote Sensing Data to Model PM10 Estimation in Cities with a Low Number of Air Quality Stations: A Case of Study in Quito, Ecuador. Environments, 6(7), 85. https://doi.org/10.3390/environments6070085