A Spatial Interpolation Method for Meteorological Data Based on a Hybrid Kriging and Machine Learning Approach

Abstract

Conventional spatial interpolation methods for meteorological data are usually based on linear interpolation. However, with the improvements in the temporal and spatial resolution of observational data, local neighbouring stations are susceptible to the influence of underlying surface changes and high terrain gradients. Moreover, for interpolation at a single time point, the inability to extract continuous change information effectively from adjacent times limits the interpolation performance. In this paper, an improved hybrid deep learning-kriging method is proposed that combines a graph neural networks (GNNs) prediction model with the kriging interpolation algorithm. The GNNs considers dynamic changes over time and combines spatial and temporal information to estimate (interpolate) meteorological data at target weather stations using reanalysis data as input. The experimental results show that the hybrid method exhibits good performance in interpolating station data in complex terrain areas and under uneven surface conditions. The interpolation effectiveness of this method is markedly improved compared to that of traditional kriging methods. Moreover, when applied to station-to-grid interpolation, the hybrid method still provides better interpolation results than those of kriging methods. Therefore, this research provides a new method and perspective for meteorological data interpolation.