Multi-Spectrum Hierarchical Segmentation Algorithm: A New Aerosol Optical Thickness Retrieval Algorithm for Urban Areas

Retrieving aerosol optical thickness (AOT) from remote-sensing images of urban areas remains challenging, especially for bright-reflecting land surfaces. In this study, a novel algorithm, called multi-spectrum hierarchical segmentation (MSHS), was developed to retrieve the AOTs for urban surfaces. In this algorithm, the apparent reflectance of multiple shortwave infrared (SWIR) bands was employed and divided into tiny segments successively and hierarchically. Each segment was further segmented into object and nonobject parts using the Otsu algorithm in the coastal band. Hereafter, the congeneric apparent reflectance pixels of the object part were extracted, and the surface reflectance of this congener was obtained based on the minimum reflectivity and 6S model. AOT was then retrieved based on a precalculated lookup table (LUT) using the coastal band. Aerosol Robotic Network (AERONET) sun/sky radiometer measurements from 2013 to 2019 from Beijing, China, were used for validation. Results showed that the 30-m AOT retrievals obtained using Landsat-8 images exhibited good consistency with the ground-based measurements, with an overall correlation coefficient of ~0.871, expected error of ~59.04%, root mean square error of ~0.148, and mean absolute error of ~0.096. Compared to dense dark vegetation (DDV) algorithm, MSHS algorithm exhibited higher correlation and lower error. This implied that this new algorithm can help in characterizing aerosol distribution patterns within a city in a more refined way and provide support for tracing air pollution sources.