Modified planar rotator (MPR) method

MPR is a spatial prediction method for data with missing values on a regular grid

MPR is a novel conditional simulation method for the efficient prediction of missing data on two-dimensional Cartesian grids, based on the modified planar rotator (MPR) model. The MPR captures spatial correlations using nearest-neighbor spin interactions and does not rely on Gaussian assumptions. The only model parameter is the reduced temperature, which we estimate by means of an ergodic specific energy matching principle. We propose an efficient hybrid Monte Carlo algorithm that leads to fast relaxation of the MPR model and allows vectorization. Consequently, the MPR computational time scales approximately linearly with system size. This makes it more suitable for big data sets, such as satellite and radar images, than conventional geostatistical approaches. The performance (accuracy and computational speed) of the MPR model is validated with Gaussian synthetic and non-Gaussian real data (atmospheric heat release measurements and Walker-lake DEM-based concentrations) via comparisons with standard gap-filling methods (for more details see the paper on https://arxiv.org/pdf/1710.03038.pdf).