Total cross section prediction of the collisions of positrons and electrons with alkali atoms using Gradient Tree Boosting

A relatively new computational technique, namely gradient tree boosting (GTB), is presented for modeling the total cross sections of the scattering of positrons and electrons by alkali atoms in the low and intermediate energy regions. The calculations have been performed in the framework of gradient tree boosting (GTB). The GTB has been running based on the experimental data of the total collisional cross sections to produce the total cross sections for each alkali atom as a function of the incident energy of the projectile as well as the atomic number and the static dipole polarizability of the atom. Moreover our GTB model is used to predict the experimental data for total collisional cross sections that are not used in the training session. The calculated and predicted total collisional cross sections are compared with the experimental data. We find that the GTB technique shows a good match to the experimental data. To our knowledge, this is the first application of the GTB technique to the data of positron and electron collisions with alkali atoms at low and intermediate energies.