A comparison of gap-filling approaches for Landsat-7 satellite data
Type
ArticleKAUST Department
Biological and Environmental Sciences and Engineering (BESE) DivisionComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Environmental Science and Engineering Program
Statistics Program
Water Desalination and Reuse Research Center (WDRC)
Date
2017-08-10Online Publication Date
2017-08-10Print Publication Date
2017-12-02Permanent link to this record
http://hdl.handle.net/10754/625993
Metadata
Show full item recordAbstract
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 (R-2) were used as the evaluation metrics to assess the prediction results. In addition, the overall accuracy (OA) and kappa coefficient (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 R-2 > 0.93 for bands 1 and 2 in all cases and R-2 > 0.80 for bands 3 and 4 in most cases. For the heterogeneous example, GNSPI performs the best, with 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 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.Citation
Yin G, Mariethoz G, Sun Y, McCabe MF (2017) A comparison of gap-filling approaches for Landsat-7 satellite data. International Journal of Remote Sensing 38: 6653–6679. Available: http://dx.doi.org/10.1080/01431161.2017.1363432.Sponsors
This work was supported by funding from King Abdullah University of Science and Technology (KAUST).Publisher
Informa UK LimitedAdditional Links
http://www.tandfonline.com/doi/full/10.1080/01431161.2017.1363432Relations
Is Supplemented By:- [Dataset]
Gaohong Yin, Gregoire Mariethoz, Sun, Y., & McCabe, M. F. (2017). A comparison of gap-filling approaches for Landsat-7 satellite data. Taylor & Francis. https://doi.org/10.6084/M9.FIGSHARE.5297071.V1. DOI: 10.6084/m9.figshare.5297071.v1 Handle: 10754/663884
ae974a485f413a2113503eed53cd6c53
10.1080/01431161.2017.1363432