Segmentation of spectroscopic images of the low solar atmosphere by the self-organizing map technique

We describe the application of Semantic Segmentation by using Self Organizing Map technique to an high spatial and spectral resolution dataset acquired along H$\alpha$ line at 656.28 nm Interferometric Bi-dimensional Spectrometer installed focus plane Dunn Solar Telescope. This machine learning approach allowed us identify several features corresponding main structures solar photosphere chromosphere. The obtained results show capability flexibility this method identifying analyzing fine which characterize activity in low atmosphere. is a first successful SOM astrophysical data sets.