This paper addresses geospatial interpolation for meteorological measurements in which we estimate the values of climatic metrics at unsampled sites with existing observations. Providing climatological and meteorological conditions covering a large region is potentially useful in many applications, such as smart grid. However, existing research works on interpolation either cause a large number of complex calculations or are lack of high accuracy. We propose a Bayesian compressed sensing based non-parametric statistical model to efficiently perform the spatial interpolation task. Student-t priors are employed to model the sparsity of unknown signals' coefficients, and the Approximated Variational Inference (AVI) method is provided for effective and fast learning. The presented model has been deployed at IBM, targeting for aiding the intelligent management of smart grid. The evaluations on two real world datasets demonstrate that our algorithm achieves state-of-the-art performance in both effectiveness and efficiency.