Deep Learning Framework to Extract Hourly Gap-Free Surface NO2 Concentrations from TEMPO NO2 Columns
Authors:
- Masoud GhahremanlooMGMasoud Ghahremanloo
- Caroline NowlanCNCaroline Nowlan
- Gonzalo González AbadGAGonzalo González Abad
- Xiong LiuXLXiong Liu
- Cecilia GarrafoCGCecilia Garrafo
Preprint
- 23 October 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
TEMPO (Tropospheric Emissions: Monitoring of Pollution), a geostationary satellite instrument, enables continuous daytime monitoring of NO2 over North America. Here, we develop a novel deep learning (DL) framework to extract hourly (daylight) ~2×2 km2 surface NO2 concentrations from TEMPO tropospheric column density of NO2 (TrpNO2) for August 2, 2023, to December 31, 2024. First, we impute low-quality and missing pixels in TEMPO NO2 columns, improving performance against Pandora from a correlation coefficient (R) of 0.40 and a percentage mean absolute bias (MABP) of 101% for low-quality pixels to R=0.69 and MABP=34%. This gap-filling step is critical, as it recovers approximately 32% of pixels in our TEMPO domain. Second, we fuse gap-free TrpNO2 with in-situ NO2 observations to generate preliminary surface NO2 grids (”TEMPO-Fused NO2”). Third, a residual neural network (ResNet) incorporates TEMPO-Fused NO2 and other variables to generate the final surface NO2 product over the TEMPO domain. Unlike point-based NO2 monitoring stations, our product provides gap-free surface NO2 maps across TEMPO domain, substantially enhancing NO2 monitoring capabilities. Validation against in-situ stations shows a very high accuracy of this DL framework at surface NO2 estimation (R=0.98, mean absolute bias (MAB)=0.8 ppb, and MABP=12%). The model also generalizes well spatially (R=0.95; MABP=21%) and temporally (R=0.98; MABP=13%) and remains accurate within imputed regions (R=0.97; MABP=17%) and rural environments (R=0.93; MABP=25%). The DL framework accurately captures surface NO2 concentrations during high-NO2 episodes (R=0.94; MABP=12%). We also provide hourly grids of NO2 estimation epistemic uncertainty to aid users in identifying pixels that require cautious interpretation.Keywords
This publication has 39 references indexed in Scilit:
- An Intercomparison of Deep-Learning Methods for Super-Resolution Bias-Correction (SRBC) of Indian Summer Monsoon Rainfall (ISMR) Using CORDEX-SA SimulationsAsia-Pacific Journal of Atmospheric Sciences, 2023
- Spatiotemporal estimation of TROPOMI NO2 column with depthwise partial convolutional neural networkNeural Computing and Applications, 2023
- Deep learning mapping of surface MDA8 ozone: The impact of predictor variables on ozone levels over the contiguous United StatesEnvironmental Pollution, 2023
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- On the use of data from commercial NOx analyzers for air pollution studiesAtmospheric Environment, 2019
- The short-term effects of air pollution on respiratory diseases and lung cancer mortality in Hefei: A time-series analysisRespiratory Medicine, 2019
- Tropospheric emissions: Monitoring of pollution (TEMPO)Journal of Quantitative Spectroscopy and Radiative Transfer, 2017
- Biases in long-term NO2 averages inferred from satellite observations due to cloud selection criteriaRemote Sensing of Environment, 2012
- Requirements for the GMES Atmosphere Service and ESA's implementation concept: Sentinels-4/-5 and -5pRemote Sensing of Environment, 2012
- Fundamentals of Atmospheric Modeling2005