A gapless 0.05° daytime-hourly tropospheric NO<sub>2</sub> dataset (2019–2024) over key Asian hotspots reconstructed using physics-aware deep learning

Gao, Hongrui; He, Qin; Qin, Kai; Kim, Jhoon; Loyola, Diego; Tiwari, Pravash; Lu, Lingxiao; Cohen, Jason B.

doi:10.5194/essd-18-7883-2026

Articles | Volume 18, issue 10

https://doi.org/10.5194/essd-18-7883-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-18-7883-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 10

Data description article

|

29 Oct 2026

Data description article |

| 29 Oct 2026

A gapless 0.05° daytime-hourly tropospheric NO₂ dataset (2019–2024) over key Asian hotspots reconstructed using physics-aware deep learning

Hongrui Gao, Qin He, Kai Qin, Jhoon Kim, Diego Loyola, Pravash Tiwari, Lingxiao Lu, and Jason B. Cohen

Data sets

A gapless 0.05° hourly tropospheric NO2 dataset (2019–2024) over key Asian hotspots reconstructed using physics‑aware deep learning Hongrui Gao et al. https://doi.org/10.5281/zenodo.20427767

TROPOMI Level 2 Nitrogen Dioxide total column products (Version 02) Copernicus Sentinel-5P https://doi.org/10.5270/S5P-9bnp8q8

MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 0.05Deg CMG V061 M. Friedl and D. Sulla-Menashe https://doi.org/10.5067/MODIS/MCD12C1.061

ETOPO 2022 15 arc-second global relief model NOAA National Centers for Environmental Information https://doi.org/10.25921/FD45-GT74

ERA5 hourly data on single levels from 1940 to present Copernicus Climate Change Service https://doi.org/10.24381/cds.adbb2d47

ERA5 hourly data on pressure levels from 1940 to present Copernicus Climate Change Service https://doi.org/10.24381/cds.bd0915c6

CAMS global reanalysis (EAC4) Copernicus Atmosphere Monitoring Service https://doi.org/10.24381/d58bbf47

Short summary

This study provides a continuous daytime-hourly tropospheric nitrogen dioxide dataset over four Asian pollution hotspots from 2019 to 2024, reconstructed using satellite observations, meteorological reanalysis, and physics-aware machine learning. The dataset fills observational gaps, captures fine-scale spatial and diurnal dynamics, and supports regional air-quality and health impact studies.

A gapless 0.05° daytime-hourly tropospheric NO2 dataset (2019–2024) over key Asian hotspots reconstructed using physics-aware deep learning

Data sets

A gapless 0.05° daytime-hourly tropospheric NO₂ dataset (2019–2024) over key Asian hotspots reconstructed using physics-aware deep learning