The spatial information of soil organic matter (SOM) is crucial for precision agriculture and environmental modeling. It is, however, difficult to obtain the regional details of SOM by dense sampling due to the high cost. Although a variety of interpolation methods are available for mapping SOM at regional scales, accurate prediction usually needs densely distributed samples and requires the interpolated variable to meet some constraints such as spatial stationarity. This paper introduces the Geographically Weighted Regression (GWR) technique as an alternative approach for SOM mapping. We interpolated the spatial distribution of SOM based on a limited number of samples with the incorporation of multiple independent variables. We also compared GWR with the ordinary least squares regression approach in mapping SOM. Results indicated that GWR could capture more local details and improve the prediction accuracy. However, more attention should be paid to the selection of independent variables.