Detection of urban fugitive dust emission sources from optical satellite remote sensing images

Urban fugitive dust emission is an open pollution source that enters the atmosphere because of the dust on the ground being lifted by the wind or human activities. Dust pollution is a major contributor to atmospheric particulate matter, making it a focus for pollution control and environmental surveillance stakeholders. The identification and monitoring of dust sources hold profound practical implications. The use of remote sensing detection method facilitates extensive coverage, high accuracy, and non-invasive monitoring of urban fugitive dust emission sources. This approach enables timely alerts about potential air pollution threats, allowing swift interventions to alleviate adverse consequences. This paper mainly studies the semantic segmentation of fugitive dust sources from remote sensing images, employing advanced deep learning algorithms. In this paper, we selected Wuhai City in China as the experimental area and created Wuhai Dust Sources Dataset. This dataset, established through high-resolution satellite remote sensing data from Gaofen-1 satellite, contains 2,648 images, capturing 707 distinct dust sources. This work evaluates four different deep learning models utilising FCN and U-Net architectures as backbones in conjunction with a variety of feature extraction convolutional neural networks. The experimental results exhibit promising detection outcomes for all four models. Among these, the U-Net combined with VGG feature extraction network has the best performance, achieving an MIoU at 81% and a Mean Precision at 92%.