气候变化领域集成服务门户(CCPortal): DecSolNet: A noise resistant missing information recovery framework for daily satellite NO2 columns

CCPortal

DOI	10.1016/j.atmosenv.2020.118143
	DecSolNet: A noise resistant missing information recovery framework for daily satellite NO2 columns
	Zhu S.; Xu J.; Yu C.; Wang Y.; Efremenko D.S.; Li X.; Sui Z.
发表日期	2021
ISSN	1352-2310
卷号	246
英文摘要	A novel statistical method (hereafter referred to as DecSolNet) for reconstructing satellite NO2 columns is introduced. The method has been developed and evaluated by comparing its performance with four benchmark models in three scenarios. When the amount of satellite data is limited, DecSolNet outperforms the benchmark models and its performance does not degrade with noisy inputs. The implementation of DecSolNet consists of: (1) feature extraction, sequential data decomposition in both temporal and frequency domains; (2) NO2 columns reconstruction by training a deep neural network. In three cross-validations, the averaged R2 score of DecSolNet reaches 0.9, which is better than that of the most benchmark models. The multi-layer perceptron (MLP) has a higher R2 score, but it degrades greatly with noisy inputs, while the performance of DecSolNet remains robust with an R2 of ~ 0.8. The bias of DecSolNet is small with an average of 1.61 μg/m3. In addition, DecSolNet is a reliable learning machine, the averaged loss and standard deviation are 0.42 μg/m3 and 0.04 μg/m3, respectively. © 2020 Elsevier Ltd
关键词	Data reconstruction Deep learning EMD NO2 columns Remote sensing Time series decomposition
语种	英语
scopus关键词	Benchmarking; Deep neural networks; Multilayer neural networks; Nitrogen oxides; Satellites; Benchmark models; Cross validation; Frequency domains; Learning machines; Missing information; Multi layer perceptron; Sequential data; Standard deviation; Learning systems; nitrogen dioxide; Article; controlled study; cross validation; decomposition; deep neural network; feature extraction; Hilbert Huang transform; machine learning; meteorology; multilayer perceptron; noise; priority journal; statistical analysis; time series analysis
来源期刊	ATMOSPHERIC ENVIRONMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/248623
作者单位	Department of Geography, University of Exeter, Rennes Drive, Exeter, EX4 4RJ, United Kingdom; Remote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, Weßling, 82234, Germany; Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, 100094, China; Key Laboratory of Radiometric Calibration and Validation for Environmental Satellites, National Satellite Meteorological Center, China Meteorological Administration, Beijing, 100081, China; China Centre for Resources Satellite Data and Application, Beijing, 100092, China
推荐引用方式 GB/T 7714	Zhu S.,Xu J.,Yu C.,et al. DecSolNet: A noise resistant missing information recovery framework for daily satellite NO2 columns[J],2021,246.
APA	Zhu S..,Xu J..,Yu C..,Wang Y..,Efremenko D.S..,...&Sui Z..(2021).DecSolNet: A noise resistant missing information recovery framework for daily satellite NO2 columns.ATMOSPHERIC ENVIRONMENT,246.
MLA	Zhu S.,et al."DecSolNet: A noise resistant missing information recovery framework for daily satellite NO2 columns".ATMOSPHERIC ENVIRONMENT 246(2021).