In this paper we present a statistical method to build three-dimensional gas distribution maps from gas sensor and wind measurements obtained with a mobile robot in uncontrolled environments. The particular contribution of this paper is to introduce and evaluate an algorithm for 3D statistical gas distribution mapping, that takes into account airflow information. 3D-Kernel DM+V/W algorithm uses a multivariate Gaussian weighting function to model the information provided by the gas sensors and an ultrasonic anemometer. The proposed algorithm is evaluated with respect to the ability of the obtained models to predict unseen measurements. The results based on 15 trials with a mobile robot in an indoor environment show improvements in the model performance when using the 3D kernel DM+V/W algorithm. Moreover the model is able to adapt to the dynamical changes of the environment learning the hyper-parameter from the sensors readings.