Deep Learning Estimation of Daily Ground‐Level NO 2 Concentrations From Remote Sensing Data
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
The limited number of nitrogen dioxide (NO 2 ) surface measurements calls for the development of highly accurate approaches to estimating surface NO 2 concentrations. In this study, we leverage a new satellite instrument, the TROPOspheric Monitoring Instrument (TROPOMI), along with other predictor variables, to estimate daily surface NO 2 concentrations over Texas in 2019. We use the deep convolutional neural network (Deep‐CNN), an advanced deep learning algorithm, to obtain estimates and achieve a correlation coefficient ( R ) of 0.91, an index of agreement (IOA) of 0.95, and a mean absolute bias (MAB) of 1.75 ppb in surface NO 2 estimation. Additionally, we leverage a novel approach, shapley additive explanations (SHAP), to describe how Deep‐CNN understands each predictor variable. The SHAP results show that the Deep‐CNN model has an advanced understanding of the data set, revealing that TROPOMI closely captures levels of NO 2 . In addition, we show the superiority of our Deep‐CNN model at estimating surface NO 2 over other well‐known machine learning and regression models in the field, including the support vector machines (SVM), random forest (RF), and multiple linear regression (MLR). Although SVM and RF show strong capabilities at estimating surface NO 2 concentrations, their accuracy is inferior to that of the Deep‐CNN model, ranking second and third in model accuracy in this study. The MLR, however, shows a poor ability at NO 2 estimation and ranks last among all models. Testing the impact of sample size on model performance, we also show that, compared to other models, Deep‐CNN needs more samples to trigger its strength at surface NO 2 estimation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These challenges can lead to model confusion and a distorted representation of the actual responses, even in ML algorithms such as random forest methods (Ghahremanloo et al., 2021).”
From Enhancing River Channel Dimension Estimation: A Machine Learning Approach Leveraging the National Water Model, Hydrographic Networks, and Landscape Characteristics (2024) · cites this paper as Ghahremanloo et al., 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Chai, T., & Draxler, R. R. (2014) · Geoscientific Model Development · doi:10.5194/gmd-7-1247-2014 · Cited by 8,761
Willmott, C., & Matsuura, K. (2005) · Climate Research · doi:10.3354/cr030079 · Cited by 7,958 · cited 1×
“More information regarding the differences between RMSE and MAB can be found in previous studies (Chai & Draxler, 2014; Willmott & Matsuura, 2005; Willmott et al., 2009).”
ResultHow many subjects does it take to do a regression analysis
Green, S. B. (1991) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr2603_7 · Cited by 3,916
Texas A&M International University, Kock, N., Lynn, G., & Stevens Institute of Technology (2012) · Journal of the Association for Information Systems · doi:10.17705/1jais.00302 · Cited by 3,783 · cited 1×
“Using the VIF approach to test multicollinearity, several studies (Cenfetelli & Bassellier, 2009; Kline, 2015; Kock & Lynn, 2012; Petter et al., 2007) have reported different values for the VIF threshold.”
Methodvan Dyk, D. A., & Meng, X.-L. (2001) · Journal of Computational and Graphical Statistics · doi:10.1198/10618600152418584 · Cited by 1,052
Assessing PM 2.5 Exposures with High Spatiotemporal Resolution across the Continental United States
Di, Q., Kloog, I., Koutrakis, P., Lyapustin, A., Wang, Y., & Schwartz, J. (2016) · Environmental Science & Technology · doi:10.1021/acs.est.5b06121 · Cited by 510
Shapley additive explanations for NO2 forecasting
Vega García, M., & Aznarte, J. L. (2020) · Ecological Informatics · doi:10.1016/j.ecoinf.2019.101039 · Cited by 346
Research works printed but not linked: 80
- Abdolahnejad A., 2018, Mortality and morbidity due to exposure to ambient NO2, SO2, and O3 in Isfahan in 2013–2014, International Journal of Preventive Medicine, 9
- 10.1175/BAMS-86-9-1249 · DOI · Paper page
- 10.5194/acp-17-8211-2017 · doi:10.5194/acp-17-8211-2017
- 10.1175/1520-0493(1980)108<1046:TCOEPT>2.0.CO;2 · DOI · Paper page
- 10.2307/20650323 · DOI · Paper page
- Center for International Earth Science Information Network—CIESIN—Columbia University, 2018, Gridded population of the World, Version 4 (GPWv4): Population density, Revision 11
- 10.1016/j.atmosenv.2011.07.021 · DOI
- 10.1016/j.scitotenv.2019.06.349 · doi:10.1016/j.scitotenv.2019.06.349
- 10.1029/2009GL039381 · DOI
- 10.1038/jes.2014.89 · DOI
- 10.1016/j.neuroimage.2018.06.001 · DOI · Paper page
- 10.1021/acs.est.9b03107 · doi:10.1021/acs.est.9b03107
- 10.5094/APR.2015.056 · doi:10.5094/apr.2015.056
- 10.1016/j.atmosenv.2004.01.039 · DOI · Paper page
- Eslami E., 2019, A real‐time hourly ozone prediction system using deep convolutional neural network, Neural Computing & Applications, 1
- 10.1016/S0034-4257(96)00067-3 · DOI · Paper page
- 10.1016/j.atmosenv.2021.118209 · DOI
- 10.1016/j.scitotenv.2020.142226 · DOI · Paper page
- 10.1080/01431161.2018.1501167 · doi:10.1080/01431161.2018.1501167
- 10.1029/2018GL081095 · DOI · Paper page
- 10.3390/rs11020112 · doi:10.3390/rs11020112
- 10.1080/10962247.2015.1007220 · doi:10.1080/10962247.2015.1007220
- 10.1177/0142331217708242 · DOI · Paper page
- 10.1016/j.rse.2013.08.032 · DOI · Paper page
- 10.1016/j.atmosenv.2015.11.019 · DOI
- Huete A., 1999, MODIS vegetation index (MOD13), Algorithm Theoretical Basis Document, 3, 295
- 10.1016/0021-8502(94)00098-J · doi:10.1016/0021-8502(94)00098-j
- 10.1016/j.atmosenv.2015.09.019 · DOI
- 10.1109/TASSP.1981.1163711 · DOI · Paper page
- 10.1016/j.atmosenv.2015.08.011 · DOI
- 10.1038/nbt0908-1011 · DOI · Paper page
- Kline R. B., 2015, Principles and practice of structural equation modeling
- 10.1021/es302673e · DOI · Paper page
- 10.1021/es400744g · DOI · Paper page
- 10.1109/72.554195 · DOI · Paper page
- Lee H. J., 2014, Daily ambient NO2 concentration predictions using satellite ozone monitoring instrument NO2 data and land use regression, Environmental science & technology, 48, 2305
- 10.1007/s10489-009-0176-9 · doi:10.1007/s10489-009-0176-9
- 10.3390/ijerph16030454 · DOI
- 10.1016/j.rse.2020.112257 · DOI
- 10.1002/2017GL075710 · DOI · Paper page
- 10.2166/nh.2016.149 · DOI
- 10.3390/rs11151738 · DOI
- 10.1109/TGRS.1995.8746027 · doi:10.1109/tgrs.1995.8746027 · Paper page
- 10.1016/j.envint.2020.105823 · DOI · Paper page
- 10.1080/15481603.2018.1426091 · DOI · Paper page
- 10.3390/ijerph120403506 · DOI
- Lops Y., 2019, Real‐time 7‐day forecast of pollen counts using a deep convolutional neural network, Neural Computing & Applications, 1
- 10.1029/2002JD003246 · DOI · Paper page
- 10.3390/s7112636 · DOI · Paper page
- 10.1088/1748-9326/aabd42 · DOI · Paper page
- 10.1016/j.catena.2019.104421 · DOI
- 10.1016/j.procs.2020.07.012 · DOI
- OMI Team, 2012, Ozone Monitoring Instrument (OMI) data user’s guide
- 10.1016/j.envpol.2019.113395 · DOI · Paper page
- Pedregosa F., 2011, Scikit‐learn: Machine learning in Python, Journal of Machine Learning Research, 12, 2825
- 10.1016/j.atmosenv.2019.117162 · DOI
- 10.1016/j.neunet.2019.09.033 · DOI
- 10.1029/2005JD006328 · DOI · Paper page
- 10.1023/B:STCO.0000035301.49549.88 · DOI · Paper page
- Srivastava N., 2014, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15
- 10.5194/acp-18-15921-2018 · DOI · Paper page
- 10.5194/amt-11-2701-2018 · DOI · Paper page
- 10.1080/22797254.2019.1605624 · DOI
- 10.3390/ijerph17176228 · DOI
- 10.1016/j.rse.2019.111221 · DOI · Paper page
- 10.1289/ehp.0900844 · DOI · Paper page
- 10.1021/jp984488q · doi:10.1021/jp984488q
- 10.1029/JC090iC05p08995 · DOI · Paper page
- 10.1016/j.atmosenv.2008.10.005 · DOI · Paper page
- 10.1016/j.ymssp.2012.09.005 · DOI
- 10.1016/j.apr.2020.10.008 · doi:10.1016/j.apr.2020.10.008
- 10.1109/TASLP.2014.2364452 · DOI · Paper page
- 10.1016/j.ymssp.2006.10.005 · DOI · Paper page
- 10.1016/j.jclepro.2019.04.231 · doi:10.1016/j.jclepro.2019.04.231
- 10.3390/ijerph14121510 · DOI
- 10.1016/j.envpol.2017.03.079 · doi:10.1016/j.envpol.2017.03.079
- 10.1016/j.envsoft.2017.11.031 · DOI
- 10.1080/01431160500306906 · DOI · Paper page
- 10.1016/j.atmosenv.2020.117451 · DOI
- 10.1016/j.rmed.2018.11.019 · DOI
Cited by
Modaresi Rad, A., Johnson, J. M., Ghahremani, Z., Coll, J., & Frazier, N. (2024) · Journal of Geophysical Research: Machine Learning and Computation · doi:10.1029/2024jh000173 · Cited by 11
Metadata
- Authors
- Ghahremanloo, M., Lops, Y., Choi, Y., & Yeganeh, B.
- Affiliations
- Department of Earth and Atmospheric Sciences University of Houston Houston TX USA
- Faculty of Civil, Water, and Environmental Engineering Shahid Beheshti University Tehran Iran
- Venue
- Journal of Geophysical Research: Atmospheres
- Publisher
- American Geophysical Union (AGU)
- Published
- 2021-11-08
- Volume
- 126
- Issue
- 21
- ISSN
- 2169-897X
- 2169-8996
- Cited by
- 94
- References
- 12
- Language
- en
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep Learning Estimation of Daily Ground‐Level NO 2 Concentrations From Remote Sensing Data. https://app.cochat.ai/papers/10.1029/2021jd034925
- The paper
- Ghahremanloo, M., Lops, Y., Choi, Y., & Yeganeh, B. (2021). Deep Learning Estimation of Daily Ground‐Level NO 2 Concentrations From Remote Sensing Data. Journal of Geophysical Research: Atmospheres. https://doi.org/10.1029/2021jd034925
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.