DOI: 10.1016/j.atmosenv.2015.06.032
Scopus记录号: 2-s2.0-84938849391
论文题名: The forecasting research of early warning systems for atmospheric pollutants: A case in Yangtze River Delta region
作者: Song Y ; , Qin S ; , Qu J ; , Liu F
刊名: Atmospheric Environment
ISSN: 0168-2563
EISSN: 1573-515X
出版年: 2015
卷: 118 起始页码: 58
结束页码: 69
语种: 英语
英文关键词: Adaptive neuro-fuzzy (ANF) model
; Dynamic interval forecasts
; Emissions distribution
; Forecasting and early warning systems
; Particle matter (PM)
Scopus关键词: Air quality
; Air quality standards
; Artificial intelligence
; Distribution functions
; Forecasting
; Pollution
; Adaptive neuro-fuzzy
; Artificial intelligence algorithms
; Atmospheric pollutants
; Deterministic forecasts
; Different distributions
; Forecasting and early warnings
; Interval forecasts
; Particle matter
; River pollution
; air quality
; algorithm
; atmospheric modeling
; atmospheric pollution
; data set
; emission control
; environmental monitoring
; forecasting method
; fuzzy mathematics
; particulate matter
; pollutant source
; air pollutant
; air quality standard
; algorithm
; ambient air
; Article
; artificial intelligence
; China
; computer model
; concentration (parameters)
; early warning system
; environmental monitoring
; environmental parameters
; forecasting
; measurement accuracy
; particulate matter
; prediction
; priority journal
; probability
; river
; uncertainty
; China
; Yangtze Delta
Scopus学科分类: Environmental Science: Water Science and Technology
; Earth and Planetary Sciences: Earth-Surface Processes
; Environmental Science: Environmental Chemistry
英文摘要: The issue of air quality regarding PM pollution levels in China is a focus of public attention. To address that issue, to date, a series of studies is in progress, including PM monitoring programs, PM source apportionment, and the enactment of new ambient air quality index standards. However, related research concerning computer modeling for PM future trends estimation is rare, despite its significance to forecasting and early warning systems. Thereby, a study regarding deterministic and interval forecasts of PM is performed. In this study, data on hourly and 12 h-averaged air pollutants are applied to forecast PM concentrations within the Yangtze River Delta (YRD) region of China. The characteristics of PM emissions have been primarily examined and analyzed using different distribution functions. To improve the distribution fitting that is crucial for estimating PM levels, an artificial intelligence algorithm is incorporated to select the optimal parameters. Following that step, an ANF model is used to conduct deterministic forecasts of PM. With the identified distributions and deterministic forecasts, different levels of PM intervals are estimated. The results indicate that the lognormal or gamma distributions are highly representative of the recorded PM data with a goodness-of-fit R2 of approximately 0.998. Furthermore, the results of the evaluation metrics (MSE, MAPE and CP, AW) also show high accuracy within the deterministic and interval forecasts of PM, indicating that this method enables the informative and effective quantification of future PM trends. © 2015 . Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/81569
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: School of Statistics, Dongbei University of Finance and Economics, Dalian, China; MOE Key Laboratory of Western China's Environmental Systems, College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, China; Department Mathematics and Statistics, York University, 4700 Keele Street, Toronto, ON, Canada; Information Center for Global Change Studies, Lanzhou Information Center, Chinese Academy of Sciences, Lanzhou, China
Recommended Citation:
Song Y,, Qin S,, Qu J,et al. The forecasting research of early warning systems for atmospheric pollutants: A case in Yangtze River Delta region[J]. Atmospheric Environment,2015-01-01,118