A comparison of gap-filling approaches for Landsat-7 satellite data

  • Gaohong Yin (Creator)
  • Gregoire Mariethoz (Creator)
  • Ying Sun (Creator)
  • Matthew McCabe (Creator)
  • Gregoire Mariethoz (Creator)



The purpose of this study is to assess the relative performance of four different gap-filling approaches across a range of land-surface conditions, including both homogeneous and heterogeneous areas as well as in scenes with abrupt changes in landscape elements. The techniques considered in this study include: (1) Kriging and co-Kriging; (2) geostatistical neighbourhood similar pixel interpolator (GNSPI); (3) a weighted linear regression (WLR) algorithm; and (4) the direct sampling (DS) method. To examine the impact of image availability and the influence of temporal distance on the selection of input training data (i.e. time separating the training data from the gap-filled target image), input images acquired within the same season (temporally close) as well as in different seasons (temporally far) to the target image were examined, as was the case of using information only within the target image itself. Root mean square error (RMSE), mean spectral angle (MSA), and coefficient of determination ($\textit{R}$$^{2}$) were used as the evaluation metrics to assess the prediction results. In addition, the overall accuracy (OA) and kappa coefficient ($\textit{kappa}$) were used to assess a land-cover classification based on the gap-filled images. Results show that all of the gap-filling approaches provide satisfactory results for the homogeneous case, with $\textit{R}$$^{2}$ > 0.93 for bands 1 and 2 in all cases and $\textit{R}$$^{2}$ > 0.80 for bands 3 and 4 in most cases. For the heterogeneous example, GNSPI performs the best, with $\textit{R}$$^{2}$ > 0.85 for all tested cases. WLR and GNSPI exhibit equivalent accuracy when a temporally close input image is used (i.e. WLR and GNSPI both have an $\textit{R}$$^{2}$ equal to 0.89 for band 1). For the case of abrupt changes in scene elements or in the absence of ancillary data, the DS approach outperforms the other tested methods.
Date made available2017

Cite this