Gaussian-Process-Regression-based Periodical Variation Analysis of the Lunar Surface Temperature with the ESA-Dresden Radio Telescope

•Gaussian distribution fitting is utilized to model the observations of the Moon.•The lunar surface temperature variation is analyzed by Gaussian Process Regression.•The lunar temperature is an approximate sinusoidal function of the Moon phase.•The temperature reaches the peak 4.80–6.25 days after the full Moon.•The temperature falls to the bottom 3.67–6.50 days after the new Moon.