Separation of e⁺e^- → e⁺e^- and e⁺e^- → π⁺π^- events based on the difference in the energy deposition profiles in SND detector calorimeter.

The technique of discrimination of the e⁺e^- → e⁺e^- and e⁺e^- → π⁺π^- events in energy range 0.5 < s < 1 GeV based on the difference in the energy deposition in calorimeter of SND detector was developed by applying machine learning method. Identification efficiency for e⁺e^- → e⁺e^- and e⁺e^- → π⁺π^- events is estimated to be in the range from 99.3 to 99.8%. Contribution of the identification efficiencies errors to the total error of e⁺e^- → π⁺π^- cross section is less than 0.2% for the most energy points.