A New Air Pollution Source Identification Method Based on Remotely Sensed Aerosol and Improved Glowworm Swarm Optimization

作者：Chen, Yunping^*; Wang, Shudong; Han, Weihong; Xiong, Yajv; Wang, Wenhuan; Tong, Ling

来源：IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8): 3454-3464.

DOI：10.1109/JSTARS.2017.2690943

• Aerosols
• air pollution
• artificial intelligence
• pollution control
• remote sensing

Air pollution sources generally cannot be identified as the specific factories but certain industries. Focusing on this issue, a new method, based on an improved glowworm swarm optimization and remotely sensed imagery, was proposed to precisely orientate and quantify air pollution sources in this study. In addition, meteorological data and GIS information were also used to backtrack the pollution source. After that, in order to quantify the pollution of each factory in the study areas, three pollution indices, pollution gross (PG), pollution intensity, and area-normalized pollution (ANP), were proposed. As a result, the polluting contribution of each factory was listed, and the most polluting factories, which were bulletined as the key monitoring factories by the local authority, were accurately extracted. Among the pollution indices, ANP is the most robust, reliable, and recommended. Furthermore, the result also shows factory pollution background information achieved from the historical remote sensing data which can be used to improve the precision of identification. To our knowledge, this study provides the first attempt to address the problem of identifying a pollution source as originating from an individual factory based on remote sensing data. The proposed method provides a useful tool for air quality management, and the result would be meaningful to environmental and economic issue.

• 出版日期2017-8
• 单位电子科技大学