DOI: 10.1016/j.atmosenv.2014.03.049
Scopus记录号: 2-s2.0-84897953051
论文题名: Ensemble forecasting with machine learning algorithms for ozone, nitrogendioxide and PM10 on the Prev'Air platform
作者: Debry E ; , Mallet V
刊名: Atmospheric Environment
ISSN: 0168-2563
EISSN: 1573-515X
出版年: 2014
卷: 91 起始页码: 71
结束页码: 74
语种: 英语
英文关键词: Chemical transport models
; Ensemble forecast
; Nitrogen dioxide
; Operational forecasting
; Ozone
; Particulate matter
; Sequential aggregation
; Threshold exceedance
Scopus关键词: Air quality
; Learning algorithms
; Models
; Nitrogen oxides
; Ozone
; Pollution
; Regression analysis
; Chemical transport models
; Ensemble forecasts
; Nitrogen dioxides
; Operational forecasting
; Particulate Matter
; Threshold exceedance
; Forecasting
; nitrogen dioxide
; ozone
; air quality
; algorithm
; assessment method
; atmospheric modeling
; atmospheric pollution
; concentration (composition)
; data set
; ensemble forecasting
; nitrogen dioxide
; ozone
; particulate matter
; pollutant
; air pollutant
; air quality
; algorithm
; article
; boundary layer
; forecasting
; machine learning
; particulate matter
; physical model
; prediction
; prev air platform
; priority journal
; weight
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: This paper presents the application of an ensemble forecasting approach to the Prev'Air operational platform. This platform aims at forecasting maps, on a daily basis, for ozone, nitrogendioxide and particulate matter. It relies on several air quality models which differ by their physical parameterizations, their input data and numerical strategies, so that one model may perform better with respect to observations for a given pollutant, at a given time and location. We apply sequential aggregation methods to this ensemble of models, which has already proved good potential in previous research papers. Compared to these studies, the novelties of this paper are the variety of models, the real operational context, which requires robustness assessment, and the application to several pollutants. In this paper, we first introduce the ensemble forecasting methods and the operational platform Prev'Air along with its models. Then, the sequential aggregation performance and robustness are assessed using two different data sets.The results with the discounted ridge regression method show that the errors of the forecasts are respectively reduced by at least 29%, 35% and 19% for hourly, daily and pea O3 concentrations, by 19%, 26% and 20% for hourly, daily and peak NO2 concentrations, and finally by 17%, 19% and 11% for hourly, daily and peak PM10 concentrations. At last, we give a first insight of the ensemble ability to forecast threshold exceedances. © 2014 Elsevier Ltd. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/80851
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: INERIS BP 2, Parc Technologique Alata, 60550 Verneuil en Halatte, France; INRIA, Domaine de Voluceau, Rocquencourt - BP 105, 78153 Le Chesnay Cedex, France; CEREA, Joint Laboratory École des Ponts ParisTech/EDF R and D, Université Paris Est, Marne-la-Vallée, France
Recommended Citation:
Debry E,, Mallet V. Ensemble forecasting with machine learning algorithms for ozone, nitrogendioxide and PM10 on the Prev'Air platform[J]. Atmospheric Environment,2014-01-01,91