EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

National ground-level NO2 predictions via satellite imagery driven convolutional neural networks

Elton L. Cao

Frontiers in Environmental Science · 15.12.2023 · 11

DOI: 10.3389/fenvs.2023.1285471 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Environmental Science, online erschienen am 15.12.2023. Verfasst von Elton L. Cao. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Outdoor air pollution, specifically nitrogen dioxide (NO 2 ), poses a global health risk. Land use regression (LUR) models are widely used to estimate ground-level NO 2 concentrations by describing the satellite land use characteristics of a given location using buffer distance averages of variables. However, information may be leaked in this approach as averages ignore the variances within the averaged region. Therefore, in this study, we leverage a convolutional neural network (CNN) architecture to directly pass data grids of various satellite data for the prediction of U.S. national ground-level NO 2 . We designed CNN architectures of various complexity which inputs both satellite and meteorological reanalysis data, testing both high and low resolution data grids. Our resulting model accurately predicted NO 2 concentrations at both daily ( R 2 = 0.892, RMSE = 2.259, MAE = 1.534) and annual ( R 2 = 0.952, RMSE = 0.988, MAE = 0.690) temporal scales, with coarse resolution imagery and simple CNN architectures displaying the best and most efficient performance. Furthermore, the CNN outperforms traditional buffer distance models, including random forest (RF), feedforward neural network (FNN), and multivariate linear regression (MLR) approaches, resulting in the MLR performing the poorest at daily ( R 2 = 0.625, RMSE = 4.281, MAE = 3.102) and annual ( R 2 = 0.758, RMSE = 2.218, MAE = 1.652) scales. With the success of the CNN in this approach, satellite land use variables continue to be useful for the prediction of NO 2 . Using this computationally inexpensive model, we encourage the globalization of advanced LUR models as a low-cost alternative to traditional NO 2 monitoring.

Zitieren

APA

Cao, E. L. (2023). National ground-level NO2 predictions via satellite imagery driven convolutional neural networks. Frontiers in Environmental Science, 11. https://doi.org/10.3389/fenvs.2023.1285471

Vancouver

Cao EL. National ground-level NO2 predictions via satellite imagery driven convolutional neural networks. Frontiers in Environmental Science. 2023;11. doi:10.3389/fenvs.2023.1285471

BibTeX
@article{Cao2023,
  author = {Cao, Elton L.},
  title = {National ground-level NO2 predictions via satellite imagery driven convolutional neural networks},
  journal = {Frontiers in Environmental Science},
  year = {2023},
  volume = {11},
  doi = {10.3389/fenvs.2023.1285471}
}
Kostenlos starten →