干旱区生态环境知识资源中心(Arid): A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery

Arid

DOI	10.1029/2021EA001788
	A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery
	Berndt, E. B.; Elmer, N. J.; Junod, R. A.; Fuell, K. K.; Harkema, S. S.; Burke, A. R.; Feemster, C. M.
通讯作者	Berndt, EB (corresponding author), NASA, Marshall Space Flight Ctr, Huntsville, AL 35812 USA. ; Berndt, EB ; Elmer, NJ (corresponding author), Short Term Predict Res & Transit Ctr, Huntsville, AL 35899 USA.
来源期刊	EARTH AND SPACE SCIENCE
EISSN	2333-5084
出版年	2021
卷号	8 期号:6
英文摘要	Airborne dust has broad adverse effects on human activity, including aviation, human health, and agriculture. Remote sensing observations are used to detect dust and aerosols in the atmosphere using long established techniques. False color Red-Green-Blue (RGB) imagery using band differences sensitive to dust absorption (Dust RGB) is currently used operationally to assist forecasters and decision-makers in identifying dust at night, but there are still limitations, subjectivity, and nuances to image interpretation making night-time dust identification difficult even for experts. This study applies machine learning to the problem of night-time dust detection with a simple random forest (RF) model using Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery, band differences sensitive to dust absorption, and Dust RGB color components as inputs to the model. The RF model achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels and 99.96% of no-dust pixels for all dust images in the validation data set. The addition of a single null case to the training data set drastically reduces error in labeling no-dust pixels as dust from 45% to 14.5%. Application of the machine learning model to the April 13-14, 2019 dust event demonstrates the ability of the model to identify dust during night-time hours when visual dust detection is limited by the cooling ground surface characteristics.
英文关键词	dust geostationary infrared machine learning multispectral remote sensing
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000667881300014
WOS关键词	DESERT DUST ; DIFFERENCE ; RETRIEVAL ; TRANSPORT ; PRODUCTS ; IMPACT
WOS类目	Astronomy & Astrophysics ; Geosciences, Multidisciplinary
WOS研究方向	Astronomy & Astrophysics ; Geology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/362952
作者单位	[Berndt, E. B.] NASA, Marshall Space Flight Ctr, Huntsville, AL 35812 USA; [Elmer, N. J.] Univ Space Res Assoc, Huntsville, AL USA; [Junod, R. A.; Fuell, K. K.] Univ Alabama, Earth Syst Sci Ctr, Huntsville, AL 35899 USA; [Harkema, S. S.; Burke, A. R.; Feemster, C. M.] Univ Alabama, Coll Atmospher & Earth Sci, Huntsville, AL 35899 USA; [Berndt, E. B.; Elmer, N. J.; Junod, R. A.; Fuell, K. K.; Harkema, S. S.; Burke, A. R.; Feemster, C. M.] Short Term Predict Res & Transit Ctr, Huntsville, AL 35899 USA
推荐引用方式 GB/T 7714	Berndt, E. B.,Elmer, N. J.,Junod, R. A.,et al. A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery[J],2021,8(6).
APA	Berndt, E. B..,Elmer, N. J..,Junod, R. A..,Fuell, K. K..,Harkema, S. S..,...&Feemster, C. M..(2021).A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery.EARTH AND SPACE SCIENCE,8(6).
MLA	Berndt, E. B.,et al."A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery".EARTH AND SPACE SCIENCE 8.6(2021).