Mineral Dust Detection Using Satellite Data

Abstract

Mineral dust, defined as aerosol originating from the soil, can have various harmful effects to the environment and human health. The detection of dust, and particularly incoming dust storms, may help prevent some of these negative impacts. We investigated both physical and machine learning algorithms of dust aerosols detection over the Atlantic Ocean using satellite observations from Moderate Resolution Imaging Spectroradiometer (MODIS) and the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation Observation (CALIPSO). We found that the machine learning algorithms achieved a higher accuracy rate compared to those of the physical algorithms. Through combining a logistic regression algorithm with our physical understanding of dust aerosols, we were able to reach the highest detection accuracy.