Establishment of Air Quality Forecast Model Based on Deep Learning

Author(s):  
Ruifeng Guo ◽  
Yuanjing Ma ◽  
Shuai Wang ◽  
Yiming Du ◽  
Shihai Wang
Author(s):  
Daiwen Kang ◽  
Brian K. Eder ◽  
Rohit Mathur ◽  
Shaocai Yu ◽  
Kenneth L. Schere

2020 ◽  
Author(s):  
Xiaoyi Zhao ◽  
Debora Griffin ◽  
Vitali Fioletov ◽  
Chris McLinden ◽  
Alexander Cede ◽  
...  

<p>The TROPOspheric Monitoring Instrument (TROPOMI) on-board the Sentinel-5 Precursor satellite (launched on 13 October 2017) is a nadir-viewing spectrometer measuring reflected sunlight in the ultraviolet, visible, near-infrared, and shortwave infrared spectral ranges. The measured spectra are used to retrieve total columns of trace gases, including nitrogen dioxide (NO<sub>2</sub>). In this study, Pandora NO<sub>2</sub> measurements made at three sites located in or north of the Greater Toronto Area (GTA) are used to evaluate the TROPOMI NO<sub>2</sub> data products, including the standard Royal Netherlands Meteorological Institute (KNMI) NO<sub>2</sub> data product and a research data product developed by Environment and Climate Change Canada (ECCC) using a high-resolution regional air quality forecast model (used in the airmass factor calculation).</p><p>TROPOMI pixels located upwind and downwind from the Pandora sites were analyzed using a new wind-based validation method that increases the number of coincident measurements by about a factor of five compared to standard techniques. Using this larger number of coincident measurements, this work shows that both TROPOMI and Pandora instruments can reveal detailed spatial patterns (i.e., horizontal distributions) of local and transported NO<sub>2</sub> emissions, which can be used to evaluate regional air quality changes. The TROPOMI ECCC NO<sub>2</sub> research data product shows improved agreement with Pandora measurements compared to the TROPOMI standard tropospheric NO<sub>2</sub> data product, demonstrating the benefit of using the high-resolution regional air quality forecast model to derive NO<sub>2</sub> airmass factors.</p>


2006 ◽  
Vol 40 (26) ◽  
pp. 4894-4905 ◽  
Author(s):  
Brian Eder ◽  
Daiwen Kang ◽  
Rohit Mathur ◽  
Shaocai Yu ◽  
Ken Schere

2009 ◽  
Vol 43 (3) ◽  
pp. 724-733 ◽  
Author(s):  
Daniel Q. Tong ◽  
Rohit Mathur ◽  
Daiwen Kang ◽  
Shaocai Yu ◽  
Kenneth L. Schere ◽  
...  

2009 ◽  
Vol 9 (6) ◽  
pp. 27063-27098
Author(s):  
F. L. Herron-Thorpe ◽  
J. K. Vaughan ◽  
B. K. Lamb ◽  
G. H. Mount

Abstract. Results from a regional air quality forecast model, AIRPACT-3, are compared to OMI tropospheric NO2 integrated column densities for an 18 month period over the Pacific Northwest. AIRPACT column densities were well correlated with cloud-free monthly averages of tropospheric NO2 (R=0.75) to NASA retrievals for months without wildfires, but were poorly correlated with significant model overpredictions (R=0.21) for months with wildfires when OMI and AIRPACT were compared over the entire domain. AIRPACT forecasted higher NO2 in some US urban areas, and lower NO2 in many Canadian urban areas, when compared to OMI. There are significant changes in results after spatially averaging model results to the daily OMI swath. Also, it is shown that applying the averaging kernel to model results in cloudy conditions has a large effect, but applying the averaging kernel in cloud free conditions has little effect. The KNMI and NASA retrievals of tropospheric NO2 from OMI (collection 3) are compared. The NASA product is shown to be significantly different than the KNMI tropospheric NO2 product, i.e. July 2007 (R=0.60) and January 2008 (R=0.69).


2002 ◽  
Vol 42 (11) ◽  
pp. 1551-1560 ◽  
Author(s):  
R. San JosÉ ◽  
I. Salas ◽  
A. MartÍn ◽  
J.L. PÉrez ◽  
A.B. Carpintero ◽  
...  

2010 ◽  
Vol 10 (18) ◽  
pp. 8839-8854 ◽  
Author(s):  
F. L. Herron-Thorpe ◽  
B. K. Lamb ◽  
G. H. Mount ◽  
J. K. Vaughan

Abstract. Results from a regional air quality forecast model, AIRPACT-3, are compared to OMI tropospheric NO2 integrated column densities for an 18 month period over the Pacific Northwest. AIRPACT column densities are well correlated (r=0.75) to cloud-free (<35%) retrievals of tropospheric NO2 for monthly averages without wildfires, but are poorly correlated (r=0.21) with significant model over-predictions for months with wildfires when OMI and AIRPACT are compared over the entire domain. AIRPACT predicts higher NO2 in some northwestern US urban areas, and lower NO2 in the Vancouver, BC urban area, when compared to OMI. Model results are spatially averaged to the daily OMI swath. The Dutch KNMI (DOMINO) and NASA (Standard Product) retrievals of tropospheric NO2 from OMI (Collection-3) are compared. The NASA product is shown to be significantly different than the KNMI tropospheric NO2 product. The average difference in tropospheric columns, after applying the averaging kernels of the respective products to the model results, is shown to be larger in the summer (±50%) than winter (±20%).


Sign in / Sign up

Export Citation Format

Share Document