Skip to main content
Fig. 9 | Plant Methods

Fig. 9

From: Atmospheric correction of vegetation reflectance with simulation-trained deep learning for ground-based hyperspectral remote sensing

Fig. 9

A randomly chosen sample of 99 spectral reflectance curves from the testing set, showing the actual simulated spectral reflectance in black, each of the Enc-Dec CNN model predicted spectral reflectance in light blue, obtained by multiplying the model’s output \(\Delta\)reflectance by the median simulated spectral reflectance and convolving the result using the FWHM of 6 nm. The median model predicted spectral reflectance is shown in blue, and the median \(r^2\) and associated 1\(\sigma\) uncertainty from all models are listed at the top of each plot

Back to article page

Plant Methods

ISSN: 1746-4811