21 May 2024
 | 21 May 2024
Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).

NitroNet – A deep-learning NO2 profile retrieval prototype for the TROPOMI satellite instrument

Leon Kuhn, Steffen Beirle, Sergey Osipov, Andrea Pozzer, and Thomas Wagner

Abstract. We introduce "NitroNet", a deep learning model for the prediction of tropospheric NO2 profiles from satellite column measurements. NitroNet is a neural network, which was trained on synthetic NO2 profiles from the regional chemistry and transport model WRF-Chem, operated on a European domain for the month of May 2019. This WRF-Chem simulation was constrained by in-situ and satellite measurements, which were used to optimize important simulation parameters (e.g. the boundary layer scheme). The NitroNet model receives vertical NO2 column densities (VCDs) from the TROPOMI satellite instrument and ancillary variables (meteorology, emissions, etc.) as input, from which it reproduces NO2 concentration profiles. Training of the neural network is conducted on a filtered dataset, meaning that NO2 profiles with strong disagreement (> 20 %) to colocated TROPOMI column measurements are discarded.

We present a first evaluation of NitroNet on a variety of geographical domains (Europe, US west coast, India, and China) and different seasons. For this purpose, we validate the NO2 profiles predicted by NitroNet against monthly-mean satellite, in-situ, and MAX-DOAS measurements. The training data were previously validated against the same datasets. During summertime, NitroNet shows small biases and strong correlations to all three datasets (bias = +6.7 % and R = 0.95 for TROPOMI NO2 VCDs, bias = −10.5 % and R = 0.75 for AirBase surface concentrations). In the comparison to TROPOMI satellite data, NitroNet even shows significantly lower errors and stronger correlation than a direct comparison with WRF-Chem numerical results. During wintertime considerable low biases arise, because the summertime training data is not fully representative of all atmospheric wintertime characteristics (e.g. longer NO2 lifetimes). Nonetheless, the wintertime performance of NitroNet is surprisingly good, and comparable to that of classic RCT models. NitroNet can demonstrably be used outside the geographic domain of the training data with only slight performance reductions. What makes NitroNet unique compared to similar existing deep learning models is the inclusion of synthetic model data, which has important benefits: Due to the lack of NO2 profile measurements, empirical models are limited to the prediction of surface concentrations learned from in-situ measurements. NitroNet, however, can predict full tropospheric NO2 profiles. Furthermore, in-situ measurements of NO2 are known to suffer from biases, often larger than +20 %, due to cross sensitivities to photooxidants, which empirical models inevitably reproduce.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Leon Kuhn, Steffen Beirle, Sergey Osipov, Andrea Pozzer, and Thomas Wagner

Status: open (until 30 Jun 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Leon Kuhn, Steffen Beirle, Sergey Osipov, Andrea Pozzer, and Thomas Wagner
Leon Kuhn, Steffen Beirle, Sergey Osipov, Andrea Pozzer, and Thomas Wagner


Total article views: 206 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
153 47 6 206 4 7
  • HTML: 153
  • PDF: 47
  • XML: 6
  • Total: 206
  • BibTeX: 4
  • EndNote: 7
Views and downloads (calculated since 21 May 2024)
Cumulative views and downloads (calculated since 21 May 2024)

Viewed (geographical distribution)

Total article views: 197 (including HTML, PDF, and XML) Thereof 197 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 12 Jun 2024
Short summary
This paper presents a new machine-learning model, which allows to compute NO2 concentration profiles from satellite observations. The neural network was trained on synthetic data from the regional chemistry and transport model WRF-Chem. It is the first model of this kind. We present a thorough model validation study, including different seasons and regions of the world.