Realistic wind data are essential in developing, testing, and ensuring the safety of small unmanned aerial systems in operation. We present a non-intrusive reduced order modeling (NIROM) approach to replicate realistic wind data and predict wind fields. The method uses a LES model to generate high-fidelity data. To create a reduced-order model, we use proper orthogonal decomposition to extract modes from the three-dimensional space and use specialized recurrent neural networks and long short-term memory to step in time. This paper combines the traditional approach of using computational fluid dynamic simulations to generate wind data with deep learning and reduced-order modeling techniques to devise a methodology for a non-intrusive data-based model for wind field prediction. A model of an urban subspace with a building setup in neutral atmospheric conditions is tested to demonstrate the method.