Automatic atmospheric correction for shortwave hyperspectral remote sensing data using a time-dependent deep neural network

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: This is version 3 of this Preprint.


Download Preprint


Jian Sun, Fangcao Xu, Guido Cervone, Melissa Gervais, Christelle Wauthier, Mark Salvador


Atmospheric correction is an essential step in hyperspectral imaging and target detection from spectrometer remote sensing data. State-of-the-art atmospheric correction algorithms either require filed-measurements or prior knowledge of atmospheric characteristics to improve the predicted accuracy, which are computational expensive and unsuitable for real time application. In this paper, we propose a time-dependent neural network for automatic atmospheric correction and target detection using multi-scan hyperspectral data under different elevation angles. Results show that the proposed network has the capacity to accurately provide atmospheric characteristics and estimate precise reflectivity spectra for different materials, including vegetation, sea ice, and ocean. In addition, experiments are designed to investigate the time dependency of the proposed network. The error analysis confirms that our proposed network is capable of estimating atmospheric characteristics under both hourly and diurnally varying environments. Both the predicted results and error analysis are promising and demonstrate that our network has the ability of providing accurate atmospheric correction and target detection in real-time.



Earth Sciences, Other Earth Sciences, Physical Sciences and Mathematics


Deep learning, Atmospheric Correction, Hyperspectral, Neural Networks, Reflectivity


Published: 2020-07-10 10:12

Last Updated: 2020-07-10 17:59

Older Versions

GNU Lesser General Public License (LGPL) 2.1

Additional Metadata

Data Availability (Reason not available):
Synthetic data

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.