Radon and CO2 measurements on the ground floor of a building were combined with meteorological data and analyzed using artificial intelligence. Neural networks from the field of machine learning were used. After training the neural networks, a high level of accuracy was achieved in both the training and the prediction. A correlation matrix was used to identify the most important parameters influencing the radon and CO2 contents. Wind speed, wind gusts, and wind direction have the greatest influence on the radon and CO2 values: the more wind, the lower the gas values. An evaluation over the course of the day revealed maximum gas levels at night, when air temperatures are at their lowest. Northern winds lead to the highest gas values due to suction effects.