Calibration of spectra in presence of non-stationary background using unsupervised physics-informed deep learning

HIGHLIGHTS

SUMMARY

    The authors present an innovative method to estimate Ib(λ), and thus calculate Id(λ) e c, by using a physics-informed neural_network. In Section "Deep learning architecture", the authors provide a methodology to estimate a good value of α for this neural_network. The loss function is modified as follows: 2  N====dIp,b=2   Ltot,multi class=Lrec + αLreg=I( ) - cp,j I0,j - Ip,b +α, d j=1 where cp,j is the concentration and I0,j is the reference spectrum of the j-th agent respectively and N is the number of agents. In . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?