4.7 Article

NeSNet: A Deep Network for Estimating Near-Surface Pollutant Concentrations

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2023.3244719

Keywords

Atmospheric pollutants; ground observations; nitrogen dioxide; ozone; satellite measurements; sulfur dioxide.

Ask authors/readers for more resources

With the increase in atmospheric pollution, continuous monitoring of atmospheric gas concentration has become crucial. Satellite monitoring offers a global coverage alternative to traditional in situ measurement strategies. However, satellite measurements do not provide information on vertical concentration profiles, leading to the need for estimation methods. Our research proposes a convolutional neural network, called the near-surface network, which is designed to estimate near-surface concentrations of atmospheric trace gases using only vertical column density (VCD) values.
With the threat of atmospheric pollution on the rise in recent years, round-the-clockmonitoring of the concentration of atmospheric gases has become utterly necessary. As opposed to traditional in situmeasurement strategies, satellitemonitoring offers a convenient alternative for truly global coverage. However, satellite measurements do not provide information about the vertical profile of concentration, and estimation methods must be used to deduce near-surface concentration. Existing works that address this problem often adopt approaches that use auxiliary variables such as meteorological parameters and population density information alongwith vertical column density (VCD) measurements. In remote areas where such information is not available, these methods are likely to fail. In our work, we propose a near-surface network, a convolutional neural network that has been designed to perform the estimation of near-surface concentrations of atmospheric trace gases using only VCD values. We demonstrate the working of our method for nitrogen dioxide (NO (2)), sulfur dioxide (SO2), and ozone (O-3). The proposed method shows RMSE scores of 6.272, 7.20, and 16.03 mu g/m(3) for SO2, NO2, and O-3, respectively. We also perform a detailed analysis of the impact of various factors on model performance. In the future, this method also use to determine the concentration of additional air pollutants including PM 2.5 and PM 10. To possibly improve the effectiveness of the model, other meteorological variables, such as temperature, relative humidity, wind speed, and wind direction can be incorporated.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available