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

Abstract:

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.