A Coupled Deep Learning Model for Estimating Surface NO2 Levels from Remote Sensing Data: 15-Year Study Over the Contiguous United States

Ghahremanloo, Masoud; Lops, Yannic; Choi, Yunsoo; Mousavinezhad, Seyedali; Jung, Jia

doi:10.1029/2022jd037010

Title: A Coupled Deep Learning Model for Estimating Surface NO₂ Levels from Remote Sensing Data: 15-Year Study Over the Contiguous United States

Journal Article · Wed Jan 11 00:00:00 EST 2023 · Journal of Geophysical Research: Atmospheres

DOI:https://doi.org/10.1029/2022jd037010· OSTI ID:1909187

^[1];

^[1]; Mousavinezhad, Seyedali ^[1]; Jung, Jia ^[1]

Univ. of Houston, TX (United States)

This study proposes a novel two-step deep learning (DL) model for estimating surface NO₂ concentrations using satellite data over the contiguous United States (CONUS) from 2005 to 2019. The first phase of the model uses partial convolutional neural network (PCNN), an advanced DL model that accurately imputes gaps between surface NO₂ stations and creates 5,478 daily-mean NO₂ grids (PCNN-NO₂) of the 2005-2019 period over the study area. We then feed the PCNN-NO₂, along with other predictor variables, into a deep neural network (DNN) to estimate surface NO₂ levels, achieving exceptional performance with a correlation coefficient of 0.975 to 0.978, a mean absolute bias of 0.99 ppb to 1.38 ppb, and a root mean square error of 1.47 ppb to 1.97 ppb. Spatial cross-validation results also indicate strong spatial performance of PCNN-DNN surface NO₂ estimates. In addition to its accurate estimates, the PCNN-DNN model consistently generates estimated NO₂ grids without any missing values, improving the quality of various applications such as emission reduction strategies and public health studies. Between 2005 and 2019, the 5,478 daily estimated NO₂ grids over the CONUS reveal significant reductions in NO₂ levels in fourteen major urban environments: Washington D.C. (-43%), New York (-45%), Los Angeles (-38%), Chicago (-25%), Boston (-43%), Houston (-34%), Dallas (-40%), Philadelphia (-41%), Phoenix (-38%), Detroit (-20%), Denver (-23%), Atlanta (-0.7%), Cincinnati (-38%), and Pittsburgh (-56%). Furthermore, the study shows that the denser urban regions that in-situ stations are installed in, the higher the difference between in-situ observations and regional-mean NO₂ levels.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Atmospheric Radiation Measurement (ARM) Data Center

Sponsoring Organization:: USDOE Office of Science (SC), Biological and Environmental Research (BER); National Aeronautics and Space Administration (NASA)

Grant/Contract Number:: AC05-76RL01830; NNH19ZDA001N-AURAST

OSTI ID:: 1909187

Journal Information:: Journal of Geophysical Research: Atmospheres, Vol. 128, Issue 2; ISSN 2169-897X

Publisher:: American Geophysical UnionCopyright Statement

Country of Publication:: United States

Language:: English

References (62)

Using the satellite-derived NDVI to assess ecological responses to environmental change Pettorelli, Nathalie; Vik, Jon Olav; Mysterud, Atle Trends in Ecology & Evolution, Vol. 20, Issue 9 https://doi.org/10.1016/j.tree.2005.05.011	journal	September 2005
Daily Ambient NO ₂ Concentration Predictions Using Satellite Ozone Monitoring Instrument NO ₂ Data and Land Use Regression Lee, Hyung Joo; Koutrakis, Petros Environmental Science & Technology https://doi.org/10.1021/es404845f	journal	February 2014
Impact of the ozone monitoring instrument row anomaly on the long-term record of aerosol products Torres, Omar; Bhartia, Pawan K.; Jethva, Hiren Atmospheric Measurement Techniques, Vol. 11, Issue 5 https://doi.org/10.5194/amt-11-2701-2018	journal	January 2018
Relationships between the planetary boundary layer height and surface pollutants derived from lidar observations over China: regional pattern and influencing factors Su, Tianning; Li, Zhanqing; Kahn, Ralph Atmospheric Chemistry and Physics, Vol. 18, Issue 21 https://doi.org/10.5194/acp-18-15921-2018	journal	January 2018
Global Emissions of Trace Gases, Particulate Matter, and Hazardous Air Pollutants from Open Burning of Domestic Waste Wiedinmyer, Christine; Yokelson, Robert J.; Gullett, Brian K. Environmental Science & Technology, Vol. 48, Issue 16 https://doi.org/10.1021/es502250z	journal	July 2014
Validation of the North American Land Data Assimilation System (NLDAS) retrospective forcing over the southern Great Plains Luo, Lifeng; Robock, Alan; Mitchell, Kenneth E. Journal of Geophysical Research: Atmospheres, Vol. 108, Issue D22 https://doi.org/10.1029/2002jd003246	journal	November 2003
Importance of input data normalization for the application of neural networks to complex industrial problems Sola, J.; Sevilla, J. IEEE Transactions on Nuclear Science, Vol. 44, Issue 3 https://doi.org/10.1109/23.589532	journal	June 1997
Estimating daily high-resolution PM2.5 concentrations over Texas: Machine Learning approach Ghahremanloo, Masoud; Choi, Yunsoo; Sayeed, Alqamah Atmospheric Environment, Vol. 247 https://doi.org/10.1016/j.atmosenv.2021.118209	journal	February 2021
A Comprehensive Framework for Image Inpainting Bugeau, Aurélie; Bertalmío, Marcelo; Caselles, Vicent IEEE Transactions on Image Processing, Vol. 19, Issue 10 https://doi.org/10.1109/tip.2010.2049240	journal	October 2010
Changes in the ozone chemical regime over the contiguous United States inferred by the inversion of NOx and VOC emissions using satellite observation Jung, Jia; Choi, Yunsoo; Mousavinezhad, Seyedali Atmospheric Research, Vol. 270 https://doi.org/10.1016/j.atmosres.2022.106076	journal	June 2022
Long-term NOx trends over large cities in the United States during the great recession: Comparison of satellite retrievals, ground observations, and emission inventories Tong, Daniel Q.; Lamsal, Lok; Pan, Li Atmospheric Environment, Vol. 107 https://doi.org/10.1016/j.atmosenv.2015.01.035	journal	April 2015
Estimating Ground-Level PM _2.5 in the Eastern United States Using Satellite Remote Sensing Liu, Yang; Sarnat, Jeremy A.; Kilaru, Vasu Environmental Science & Technology, Vol. 39, Issue 9 https://doi.org/10.1021/es049352m	journal	May 2005
Estimating ground-level PM2.5 concentrations in the Southeastern United States using MAIAC AOD retrievals and a two-stage model Hu, Xuefei; Waller, Lance A.; Lyapustin, Alexei Remote Sensing of Environment, Vol. 140 https://doi.org/10.1016/j.rse.2013.08.032	journal	January 2014
Temperature-Vegetation-soil Moisture Dryness Index (TVMDI) Amani, Meisam; Salehi, Bahram; Mahdavi, Sahel Remote Sensing of Environment, Vol. 197 https://doi.org/10.1016/j.rse.2017.05.026	journal	August 2017
Estimating emissions from fires in North America for air quality modeling Wiedinmyer, Christine; Quayle, Brad; Geron, Chris Atmospheric Environment, Vol. 40, Issue 19 https://doi.org/10.1016/j.atmosenv.2006.02.010	journal	June 2006
Spatiotemporal estimation of satellite-borne and ground-level NO2 using full residual deep networks Li, Lianfa; Wu, Jiajie Remote Sensing of Environment, Vol. 254 https://doi.org/10.1016/j.rse.2020.112257	journal	March 2021
Development of a Land Surface Model. Part II: Data Assimilation Pleim, Jonathan E.; Xiu, Aijun Journal of Applied Meteorology, Vol. 42, Issue 12 https://doi.org/10.1175/1520-0450(2003)042<1811:DOALSM>2.0.CO;2	journal	December 2003
Hyperspectral image reconstruction by deep convolutional neural network for classification Li, Yunsong; Xie, Weiying; Li, Huaqing Pattern Recognition, Vol. 63 https://doi.org/10.1016/j.patcog.2016.10.019	journal	March 2017
Global patterns of current and future road infrastructure Meijer, Johan R.; Huijbregts, Mark A. J.; Schotten, Kees C. G. J. Environmental Research Letters, Vol. 13, Issue 6 https://doi.org/10.1088/1748-9326/aabd42	journal	May 2018
Changes in OMI tropospheric NO2 columns over Europe from 2004 to 2009 and the influence of meteorological variability Zhou, Yipin; Brunner, Dominik; Hueglin, Christoph Atmospheric Environment, Vol. 46 https://doi.org/10.1016/j.atmosenv.2011.09.024	journal	January 2012
Contributions of meteorology to ozone variations: Application of deep learning and the Kolmogorov-Zurbenko filter Sadeghi, Bavand; Ghahremanloo, Masoud; Mousavinezhad, Seyedali Environmental Pollution, Vol. 310 https://doi.org/10.1016/j.envpol.2022.119863	journal	October 2022
Outdoor, but not indoor, nitrogen dioxide exposure is associated with persistent cough during the first year of life Esplugues, Ana; Ballester, Ferran; Estarlich, Marisa Science of The Total Environment, Vol. 409, Issue 22 https://doi.org/10.1016/j.scitotenv.2011.08.007	journal	October 2011
Soil moisture estimation using land surface temperature and soil temperature at 5 cm depth Ghahremanloo, Masoud; Mobasheri, Mohammad Reza; Amani, Meisam International Journal of Remote Sensing, Vol. 40, Issue 1 https://doi.org/10.1080/01431161.2018.1501167	journal	July 2018
Predicting daily PM2.5 concentrations in Texas using high-resolution satellite aerosol optical depth Zhang, Xueying; Chu, Yiyi; Wang, Yuxuan Science of The Total Environment, Vol. 631-632 https://doi.org/10.1016/j.scitotenv.2018.02.255	journal	August 2018
MOD13C1 MODIS/Terra Vegetation Indices 16-Day L3 Global 0.05Deg CMG V006 Didan, Kamel NASA EOSDIS Land Processes DAAC https://doi.org/10.5067/MODIS/MOD13C1.006	dataset	January 2015
U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28	book	November 2015
Predicting Fine-Scale Daily NO ₂ for 2005–2016 Incorporating OMI Satellite Data Across Switzerland de Hoogh, Kees; Saucy, Apolline; Shtein, Alexandra Environmental Science & Technology, Vol. 53, Issue 17 https://doi.org/10.1021/acs.est.9b03107	journal	August 2019
Vertical structure and interaction of ozone and fine particulate matter in spring at Nanjing, China: The role of aerosol's radiation feedback Qu, Yawei; Wang, Tijian; Wu, Hao Atmospheric Environment, Vol. 222 https://doi.org/10.1016/j.atmosenv.2019.117162	journal	February 2020
Impact of the COVID-19 outbreak on air pollution levels in East Asia Ghahremanloo, Masoud; Lops, Yannic; Choi, Yunsoo Science of The Total Environment, Vol. 754 https://doi.org/10.1016/j.scitotenv.2020.142226	journal	February 2021
The Fire INventory from NCAR (FINN): a high resolution global model to estimate the emissions from open burning Wiedinmyer, C.; Akagi, S. K.; Yokelson, R. J. Geoscientific Model Development, Vol. 4, Issue 3 https://doi.org/10.5194/gmd-4-625-2011	journal	January 2011
The climatology of planetary boundary layer height in China derived from radiosonde and reanalysis data Guo, Jianping; Miao, Yucong; Zhang, Yong Atmospheric Chemistry and Physics, Vol. 16, Issue 20 https://doi.org/10.5194/acp-16-13309-2016	journal	January 2016
Short-Term Effects of Nitrogen Dioxide on Mortality and Susceptibility Factors in 10 Italian Cities: The EpiAir Study Chiusolo, Monica; Cadum, Ennio; Stafoggia, Massimo Environmental Health Perspectives, Vol. 119, Issue 9 https://doi.org/10.1289/ehp.1002904	journal	September 2011
Kriging interpolation method and its application in retrieval of MODIS aerosol optical depth Yu, Chao; Chen, Liangfu; Su, Lin 2011 19th International Conference on Geoinformatics https://doi.org/10.1109/GeoInformatics.2011.5981052	conference	June 2011
Human-level control through deep reinforcement learning Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David Nature, Vol. 518, Issue 7540 https://doi.org/10.1038/nature14236	journal	February 2015
Impacts of control strategies, the Great Recession and weekday variations on NO 2 columns above North American cities de Foy, Benjamin; Lu, Zifeng; Streets, David G. Atmospheric Environment, Vol. 138 https://doi.org/10.1016/j.atmosenv.2016.04.038	journal	August 2016
Network bias in air quality monitoring design Loperfido, Nicola; Guttorp, Peter Environmetrics, Vol. 19, Issue 7 https://doi.org/10.1002/env.951	journal	November 2008
Cubic convolution interpolation for digital image processing Keys, R. IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 29, Issue 6 https://doi.org/10.1109/tassp.1981.1163711	journal	December 1981
A comprehensive study of the COVID-19 impact on PM2.5 levels over the contiguous United States: A deep learning approach Ghahremanloo, Masoud; Lops, Yannic; Choi, Yunsoo Atmospheric Environment, Vol. 272 https://doi.org/10.1016/j.atmosenv.2022.118944	journal	March 2022
A global single-sensor analysis of 2002-2011 tropospheric nitrogen dioxide trends observed from space: GLOBAL NO ₂ TRENDS OBSERVED FROM SPACE Schneider, P.; van der A., R. J. Journal of Geophysical Research: Atmospheres, Vol. 117, Issue D16 https://doi.org/10.1029/2012jd017571	journal	August 2012
An Indirect Data Assimilation Scheme for Deep Soil Temperature in the Pleim–Xiu Land Surface Model Pleim, Jonathan E.; Gilliam, Robert Journal of Applied Meteorology and Climatology, Vol. 48, Issue 7 https://doi.org/10.1175/2009JAMC2053.1	journal	July 2009
Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: 2. A neural network approach Gupta, Pawan; Christopher, Sundar A. Journal of Geophysical Research, Vol. 114, Issue D20 https://doi.org/10.1029/2008jd011497	journal	January 2009
Qualitative and quantitative evaluation of MODIS satellite sensor data for regional and urban scale air quality Engel-Cox, Jill A.; Holloman, Christopher H.; Coutant, Basil W. Atmospheric Environment, Vol. 38, Issue 16 https://doi.org/10.1016/j.atmosenv.2004.01.039	journal	May 2004
The short-term effects of air pollution on respiratory diseases and lung cancer mortality in Hefei: A time-series analysis Zhu, Furong; Ding, Rui; Lei, Ruoqian Respiratory Medicine, Vol. 146 https://doi.org/10.1016/j.rmed.2018.11.019	journal	January 2019
Image Inpainting for Irregular Holes Using Partial Convolutions Liu, Guilin; Reda, Fitsum A.; Shih, Kevin J. Computer Vision – ECCV 2018 https://doi.org/10.1007/978-3-030-01252-6_6	book	January 2018
Satellite-Derived Correlation of SO2, NO2, and Aerosol Optical Depth with Meteorological Conditions over East Asia from 2005 to 2015 Lin, Chin-An; Chen, Yi-Chun; Liu, Chian-Yi Remote Sensing, Vol. 11, Issue 15 https://doi.org/10.3390/rs11151738	journal	July 2019
Improving National Air Quality Forecasts with Satellite Aerosol Observations Al-Saadi, Jassim; Szykman, James; Pierce, R. Bradley Bulletin of the American Meteorological Society, Vol. 86, Issue 9 https://doi.org/10.1175/bams-86-9-1249	journal	September 2005
Role of Sea Fog Over the Yellow Sea on Air Quality With the Direct Effect of Aerosols Jung, Jia; Choi, Yunsoo; Wong, David C. Journal of Geophysical Research: Atmospheres, Vol. 126, Issue 5 https://doi.org/10.1029/2020jd033498	journal	March 2021
ImageNet classification with deep convolutional neural networks Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E. Communications of the ACM, Vol. 60, Issue 6 https://doi.org/10.1145/3065386	journal	May 2017
Deep Learning Estimation of Daily Ground‐Level NO ₂ Concentrations From Remote Sensing Data Ghahremanloo, Masoud; Lops, Yannic; Choi, Yunsoo Journal of Geophysical Research: Atmospheres, Vol. 126, Issue 21 https://doi.org/10.1029/2021jd034925	journal	November 2021
A comprehensive investigation of surface ozone pollution in China, 2015–2019: Separating the contributions from meteorology and precursor emissions Mousavinezhad, Seyedali; Choi, Yunsoo; Pouyaei, Arman Atmospheric Research, Vol. 257 https://doi.org/10.1016/j.atmosres.2021.105599	journal	August 2021
Data augmentation for improving deep learning in image classification problem Mikolajczyk, Agnieszka; Grochowski, Michal 2018 International Interdisciplinary PhD Workshop (IIPhDW) https://doi.org/10.1109/IIPHDW.2018.8388338	conference	May 2018
Estimating the spatiotemporal variation of NO2 concentration using an adaptive neuro-fuzzy inference system Yeganeh, Bijan; Hewson, Michael G.; Clifford, Samuel Environmental Modelling & Software, Vol. 100 https://doi.org/10.1016/j.envsoft.2017.11.031	journal	February 2018
Review of the Governing Equations, Computational Algorithms, and Other Components of the Models-3 Community Multiscale Air Quality (CMAQ) Modeling System Byun, Daewon; Schere, Kenneth L. Applied Mechanics Reviews, Vol. 59, Issue 2 https://doi.org/10.1115/1.2128636	journal	January 2006
Assessing PM _2.5 Exposures with High Spatiotemporal Resolution across the Continental United States Di, Qian; Kloog, Itai; Koutrakis, Petros Environmental Science & Technology, Vol. 50, Issue 9 https://doi.org/10.1021/acs.est.5b06121	journal	April 2016
Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach Wei, Jing; Huang, Wei; Li, Zhanqing Remote Sensing of Environment, Vol. 231 https://doi.org/10.1016/j.rse.2019.111221	journal	September 2019
Assessment of the magnitude and recent trends in satellite-derived ground-level nitrogen dioxide over North America Kharol, S. K.; Martin, R. V.; Philip, S. Atmospheric Environment, Vol. 118 https://doi.org/10.1016/j.atmosenv.2015.08.011	journal	October 2015
Trends in OMI NO ₂ observations over the United States: effects of emission control technology and the economic recession Russell, A. R.; Valin, L. C.; Cohen, R. C. Atmospheric Chemistry and Physics, Vol. 12, Issue 24 https://doi.org/10.5194/acp-12-12197-2012	journal	January 2012
Increase in tropospheric nitrogen dioxide over China observed from space Richter, Andreas; Burrows, John P.; Nüß, Hendrik Nature, Vol. 437, Issue 7055 https://doi.org/10.1038/nature04092	journal	September 2005
Application of a Partial Convolutional Neural Network for Estimating Geostationary Aerosol Optical Depth Data Lops, Yannic; Pouyaei, Arman; Choi, Yunsoo Geophysical Research Letters, Vol. 48, Issue 15 https://doi.org/10.1029/2021gl093096	journal	July 2021
Annual application and evaluation of the online coupled WRF–CMAQ system over North America under AQMEII phase 2 Hogrefe, Christian; Pouliot, George; Wong, David Atmospheric Environment, Vol. 115 https://doi.org/10.1016/j.atmosenv.2014.12.034	journal	August 2015
Estimating PM _2.5 Concentrations in the Conterminous United States Using the Random Forest Approach Hu, Xuefei; Belle, Jessica H.; Meng, Xia Environmental Science & Technology, Vol. 51, Issue 12 https://doi.org/10.1021/acs.est.7b01210	journal	June 2017
The Relationships between PM2.5 and Meteorological Factors in China: Seasonal and Regional Variations Yang, Qianqian; Yuan, Qiangqiang; Li, Tongwen International Journal of Environmental Research and Public Health, Vol. 14, Issue 12 https://doi.org/10.3390/ijerph14121510	journal	December 2017

Similar Records

Deep Learning Estimation of Daily Ground–Level NO₂ Concentrations from Remote Sensing Data

Journal Article · Thu Oct 28 00:00:00 EDT 2021 · Journal of Geophysical Research: Atmospheres · OSTI ID:1909187

Ghahremanloo, Masoud; Lops, Yannic; Choi, Yunsoo; +1 more

An Extreme-Preserving Long-Term Gridded Daily Precipitation Data Set for the Conterminous United States

Journal Article · Fri Jul 09 00:00:00 EDT 2021 · Journal of Hydrometeorology · OSTI ID:1909187

Pierce, David W.; Su, Lu; Cayan, Daniel R.; +3 more

Climate data, analysis and models for the study of natural variability and anthropogenic change

Technical Report · Thu Jul 31 00:00:00 EDT 2014 · OSTI ID:1909187

Jones, Philip D.

Related Subjects

54 ENVIRONMENTAL SCIENCES

Title: A Coupled Deep Learning Model for Estimating Surface NO2 Levels from Remote Sensing Data: 15-Year Study Over the Contiguous United States

Citation Formats

References (62)

Similar Records

Related Subjects

Title: A Coupled Deep Learning Model for Estimating Surface NO₂ Levels from Remote Sensing Data: 15-Year Study Over the Contiguous United States