Fig. 13From: Atmospheric correction of vegetation reflectance with simulation-trained deep learning for ground-based hyperspectral remote sensingA randomly chosen sample of 99 scans showing the ratio of apparent reflectances of vegetation as computed using the Compound Ratio (red), together with the ratio of the atmospheric and solar corrected spectral reflectances as predicted by each of the 10 independently trained Enc-Dec CNN models (blue)Back to article page