Development of nonlinear empirical models to forecast daily PM 2.5 and ozone levels in three large Chinese cities

Citation data:

Atmospheric Environment, ISSN: 1352-2310, Vol: 147, Page: 209-223

Publication Year:
2016
Usage 297
Abstract Views 295
Link-outs 2
Captures 12
Readers 11
Exports-Saves 1
Citations 2
Citation Indexes 2
DOI:
10.1016/j.atmosenv.2016.10.003
Author(s):
Baolei Lv, W. Geoffrey Cobourn, Yuqi Bai
Publisher(s):
Elsevier BV
Tags:
Environmental Science, Earth and Planetary Sciences
article description
Empirical regression models for next-day forecasting of PM and O air pollution concentrations have been developed and evaluated for three large Chinese cities, Beijing, Nanjing and Guangzhou. The forecast models are empirical nonlinear regression models designed for use in an automated data retrieval and forecasting platform. The PM model includes an upwind air quality variable, PM24, to account for regional transport of PM, and a persistence variable (previous day PM concentration). The models were evaluated in the hindcast mode with a two-year air quality and meteorological data set using a leave-one-month-out cross validation method, and in the forecast mode with a one-year air quality and forecasted weather dataset that included forecasted air trajectories. The PM models performed well in the hindcast mode, with coefficient of determination (R) values of 0.54, 0.65 and 0.64, and normalized mean error (NME) values of 0.40, 0.26 and 0.23 respectively, for the three cities. The O models also performed well in the hindcast mode, with R values of 0.75, 0.55 and 0.73, and NME values of 0.29, 0.26 and 0.24 in the three cities. The O models performed better in summertime than in winter in Beijing and Guangzhou, and captured the O variations well all the year round in Nanjing. The overall forecast performance of the PM and O models during the test year varied from fair to good, depending on location. The forecasts were somewhat degraded compared with hindcasts from the same year, depending on the accuracy of the forecasted meteorological input data. For the O models, the model forecast accuracy was strongly dependent on the maximum temperature forecasts. For the critical forecasts, involving air quality standard exceedences, the PM model forecasts were fair to good, and the O model forecasts were poor to fair.

This article has 0 Wikipedia mention.