File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s11869-017-0514-8
- Scopus: eid_2-s2.0-85029581957
- WOS: WOS:000422939300004
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Space-time mapping of ground-level PM2.5 and NO2 concentrations in heavily polluted northern China during winter using the Bayesian maximum entropy technique with satellite data
Title | Space-time mapping of ground-level PM<inf>2.5</inf> and NO<inf>2</inf> concentrations in heavily polluted northern China during winter using the Bayesian maximum entropy technique with satellite data |
---|---|
Authors | |
Keywords | Bayesian maximum entropy Machine learning NO 2 PM 2.5 Space-time mapping |
Issue Date | 2018 |
Citation | Air Quality, Atmosphere and Health, 2018, v. 11, n. 1, p. 23-33 How to Cite? |
Abstract | The accurate and informative space-time mapping of air pollutants is a crucial component of many human exposure studies. In the present work, space-time maps of daily distributions of PM2.5 and NO2 concentrations were generated in the severely polluted northern China region using the Bayesian maximum entropy (BME) method. This method can incorporate hard PM2.5 and NO2 data (obtained at ground-level monitoring sites), and various kinds of soft (uncertain) data, including satellite data processed in terms of machine learning techniques, meteorological variables, and geographical predictors. The BME maps of space-time PM2.5 and NO2 concentrations over northern China generated during the winter season (when severe haze episodes occur frequently) were realistic and informative. As regards their numerical accuracy, for the space-time PM2.5 estimates, the tenfold cross-validation R2 and the RMSE were, respectively, 0.86 and 14.37 μg/m3; for the space-time NO2 estimates, the R2 and RMSE values were, respectively, 0.85 and 6.93 μg/m3. Lastly, it was shown that the BME method performed better than the mainstream spatiotemporal ordinary kriging technique in terms of the higher R2 values of both the predicted PM2.5 and NO2 concentration maps. |
Persistent Identifier | http://hdl.handle.net/10722/335717 |
ISSN | 2023 Impact Factor: 2.9 2023 SCImago Journal Rankings: 0.710 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jiang, Qutu | - |
dc.contributor.author | Christakos, George | - |
dc.date.accessioned | 2023-12-28T08:48:10Z | - |
dc.date.available | 2023-12-28T08:48:10Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Air Quality, Atmosphere and Health, 2018, v. 11, n. 1, p. 23-33 | - |
dc.identifier.issn | 1873-9318 | - |
dc.identifier.uri | http://hdl.handle.net/10722/335717 | - |
dc.description.abstract | The accurate and informative space-time mapping of air pollutants is a crucial component of many human exposure studies. In the present work, space-time maps of daily distributions of PM2.5 and NO2 concentrations were generated in the severely polluted northern China region using the Bayesian maximum entropy (BME) method. This method can incorporate hard PM2.5 and NO2 data (obtained at ground-level monitoring sites), and various kinds of soft (uncertain) data, including satellite data processed in terms of machine learning techniques, meteorological variables, and geographical predictors. The BME maps of space-time PM2.5 and NO2 concentrations over northern China generated during the winter season (when severe haze episodes occur frequently) were realistic and informative. As regards their numerical accuracy, for the space-time PM2.5 estimates, the tenfold cross-validation R2 and the RMSE were, respectively, 0.86 and 14.37 μg/m3; for the space-time NO2 estimates, the R2 and RMSE values were, respectively, 0.85 and 6.93 μg/m3. Lastly, it was shown that the BME method performed better than the mainstream spatiotemporal ordinary kriging technique in terms of the higher R2 values of both the predicted PM2.5 and NO2 concentration maps. | - |
dc.language | eng | - |
dc.relation.ispartof | Air Quality, Atmosphere and Health | - |
dc.subject | Bayesian maximum entropy | - |
dc.subject | Machine learning | - |
dc.subject | NO 2 | - |
dc.subject | PM 2.5 | - |
dc.subject | Space-time mapping | - |
dc.title | Space-time mapping of ground-level PM<inf>2.5</inf> and NO<inf>2</inf> concentrations in heavily polluted northern China during winter using the Bayesian maximum entropy technique with satellite data | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/s11869-017-0514-8 | - |
dc.identifier.scopus | eid_2-s2.0-85029581957 | - |
dc.identifier.volume | 11 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | 23 | - |
dc.identifier.epage | 33 | - |
dc.identifier.eissn | 1873-9326 | - |
dc.identifier.isi | WOS:000422939300004 | - |