We study the problem of short term wind speed prediction, which is a critical factor for effective wind power generation. This is a challenging task due to the complex and stochastic behavior of the wind environment. Observing various periods in the wind speed time series present different patterns, we suggest a nonlinear adaptive framework to model various hidden dynamic processes. The model is essentially data driven, which leverages non-parametric Heteroscdastic Gaussian Process to model relevant patterns for short term prediction. We evaluate our model on two different real world wind speed datasets from National Data Buoy Center. We compare our results to state-of-arts algorithms to show improvement in terms of both Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).