Random forests for statistical modeling of experimental data for CuBr vapor lasers used as brightness amplifiers

This study demonstrates the high capabilities of data mining and the random forest (RF) machine learning technique for processing experimental data in the field of laser equipment and technology and extracting significant information from these. The subject of study is the copper bromide vapor laser, used as a brightness amplifier and as an active medium in active optical systems actively developed in recent years. Published data from 465 experiments on this type of laser are statistically examined. RF regression models are built to predict the output power as a basic laser characteristic. The dependence of the output power on the input electric power, the pulse repetition frequency, the pressure of the additional gases in the discharge, and other operating and geometric parameters of the laser is determined. The models fit up to 98% of the experimentally measured laser output power data.