At the core of any flight schedule is the four dimensional (4D) trajectories which are comprised of three spatial dimensions with time added as the fourth dimension. Each trajectory contains spatial and temporal features that are associated with uncertainties that make the prediction process complex. Because of the increasing demand for air transportation, airports and airlines must have optimized schedules to best use the airports’ infrastructure potential. This is possible using advanced trajectory prediction methods. This paper proposes a novel hybrid deep learning model to extract spatial and temporal features considering the uncertainty for Hartsfield–Jackson Atlanta International Airport (ATL). Automatic Dependent Surveillance-Broadcast (ADS–B) with a vast amount of spatial and temporal flight attribute data, are used in this paper as input to the models. This research is conducted in three steps: (a) data preprocessing; (b) prediction by a hybrid Convolutional Neural Network and Gated Recurrent Unit (CNN-GRU) along with a three dimensional (3D-CNN) model; (c) The third and last step is the comparison of the model's performance with the proposed model by examining the experimental results. The deep model uncertainty is considered using Mont-Carlo dropout (MC-Dropout). Mont-Carlo dropouts are added to the network layers to enhance the model's prediction performance by a robust approach of switching off between different neurons. The results show that the proposed model has low error measurements compared to the other models (i.e., 3D CNN, CNN-GRU). The model with MC-dropout reduces the error further by an average of 21 %.