Thermal depth profile reconstruction by neural network recognition of the photothermal frequency spectrum

A new neural network technique for reconstructing the depth profile of thermally inhomogeneous materials from a photothermal spectrum is presented. The possibilities and limits of this kind of photothermal depth profiling are examined. The effect of the network architecture and several profile and signal parameters on the reconstruction quality are evaluated. Statistical forecasts are provided for the accuracy of the reconstructed profiles for various levels of Gaussian noise in the signal and at various depths.