Figures & data
Figure 1. Scatterplot and a GAM fitted line for Normalized Difference Vegetation Index (NDVI) (Y) and ETM + Band 4 (X). Data are standardized. The R package mgcv was used to fit the GAM (Wood Citation2006; Hastie and Tibshirani Citation1990).
![Figure 1. Scatterplot and a GAM fitted line for Normalized Difference Vegetation Index (NDVI) (Y) and ETM + Band 4 (X). Data are standardized. The R package mgcv was used to fit the GAM (Wood Citation2006; Hastie and Tibshirani Citation1990).](/cms/asset/5f89f86d-c6d4-4570-88a3-7b7a5e4634af/tgsi_a_1179441_f0001_b.gif)
Figure 2. Alpha blending scatterplot of a subset (1000 × 1000) of the same data in Figure 1, with alpha value set to 0.05. The alpha value specifies the level of transparency for the data points, ranging from 1 for opaque to 0 for black. Even at such a low alpha level, excessive overplotting remains a problem.
![Figure 2. Alpha blending scatterplot of a subset (1000 × 1000) of the same data in Figure 1, with alpha value set to 0.05. The alpha value specifies the level of transparency for the data points, ranging from 1 for opaque to 0 for black. Even at such a low alpha level, excessive overplotting remains a problem.](/cms/asset/8d14fd45-4a17-48ed-8866-85920a14b369/tgsi_a_1179441_f0002_b.gif)
Figure 3. Two-dimensional binned kernel smoothing scatterplot.
![Figure 3. Two-dimensional binned kernel smoothing scatterplot.](/cms/asset/7ef7df9b-7b98-4832-a875-33c0d6bcc026/tgsi_a_1179441_f0003_b.gif)
Figure 4. Scatterplot with contours. Due to the lack of sufficient memory to render the plot with the large data-set in Figure 2, 10,000 data points are randomly generated from a standard normal distribution.
![Figure 4. Scatterplot with contours. Due to the lack of sufficient memory to render the plot with the large data-set in Figure 2, 10,000 data points are randomly generated from a standard normal distribution.](/cms/asset/2eb1f84d-f801-4c70-a2f6-ec47b07c8943/tgsi_a_1179441_f0004_b.gif)
Figure 5. Binned scatterplot with the same data in Figure 2.
![Figure 5. Binned scatterplot with the same data in Figure 2.](/cms/asset/29ca6c53-940b-43db-9d16-f874f60c49c5/tgsi_a_1179441_f0005_oc.gif)
Figure 6. Nested lattice hexagon binning with the same data in Figure 2.
![Figure 6. Nested lattice hexagon binning with the same data in Figure 2.](/cms/asset/f1155d44-3e87-424b-9465-e9565d69473f/tgsi_a_1179441_f0006_oc.gif)
Table 1. Summary statistics of the simulated data-set.
Figure 7. Simulated data-set X (left) and Y (right).
![Figure 7. Simulated data-set X (left) and Y (right).](/cms/asset/d4ebdf6b-7846-4aea-92ab-4ebb6d81088f/tgsi_a_1179441_f0007_b.gif)
Figure 9. Remote sensing data-set used in the experiment.
![Figure 9. Remote sensing data-set used in the experiment.](/cms/asset/a5bf7e71-f503-41d5-a80f-30ff728489a3/tgsi_a_1179441_f0009_oc.gif)
Table 2. Summary statistics of the remote sensing data-set.
Figure 10. Illustrations of sample sites for three sampling schemes: random (left), regular (center), and hexagon stratified random (right). The background image is for the variable X, with 100 rows by 100 columns. Variable Y is not shown here. Effective sample size () was calculated based on ρx = 0.9658, ρy = 0.5136, ρxy = 0.4688. Due to geometric restrictions, actual sample sizes are 2809, for regular sampling, and 2438, for hexagon stratified random sampling.
![Figure 10. Illustrations of sample sites for three sampling schemes: random (left), regular (center), and hexagon stratified random (right). The background image is for the variable X, with 100 rows by 100 columns. Variable Y is not shown here. Effective sample size () was calculated based on ρx = 0.9658, ρy = 0.5136, ρxy = 0.4688. Due to geometric restrictions, actual sample sizes are 2809, for regular sampling, and 2438, for hexagon stratified random sampling.](/cms/asset/9a1c4f93-6094-48b3-a3c7-3524b0712b00/tgsi_a_1179441_f0010_oc.gif)
Table 3. Summary statistics for simulated variables from the resampled sets.
Figure 11. Spatially simplified scatterplot consisting of the point cloud and local/global fitting lines overlays on the same graphic features from the original data.
![Figure 11. Spatially simplified scatterplot consisting of the point cloud and local/global fitting lines overlays on the same graphic features from the original data.](/cms/asset/b9adb53e-3749-48f4-9d5c-adf836825944/tgsi_a_1179441_f0011_oc.gif)
Figure 12. Spatially simplified scatterplots (point clouds with local/global fits) from three resampling schemes (left: random sampling; center: regular sampling; right: hexagon stratified sampling).
![Figure 12. Spatially simplified scatterplots (point clouds with local/global fits) from three resampling schemes (left: random sampling; center: regular sampling; right: hexagon stratified sampling).](/cms/asset/78c32a69-2871-4d27-914e-d677e92e44a3/tgsi_a_1179441_f0012_oc.gif)
Figure 13. A random sample (n = 1326, right) of the hexagon stratified random sample set (n = 2438, left).
![Figure 13. A random sample (n = 1326, right) of the hexagon stratified random sample set (n = 2438, left).](/cms/asset/ddbc1391-0e7a-4ce6-8005-f92a9a77ee8d/tgsi_a_1179441_f0013_oc.gif)
Figure 14. Spatially simplified scatterplot of the simulated data using a two-stage resampling scheme.
![Figure 14. Spatially simplified scatterplot of the simulated data using a two-stage resampling scheme.](/cms/asset/bf642304-b1cd-400e-966a-f5d224abfbac/tgsi_a_1179441_f0014_oc.gif)
Table 4. Summary of resampling statistics for the remote sensing data-set.
Figure 15. An overlay of scatterplots from the original data and the resampled set.
![Figure 15. An overlay of scatterplots from the original data and the resampled set.](/cms/asset/11dbb29f-f274-402d-93f4-07c07551f065/tgsi_a_1179441_f0015_oc.gif)
Figure 16. Scatterplot of data from the stage-two regular resampling.
![Figure 16. Scatterplot of data from the stage-two regular resampling.](/cms/asset/379612f6-82ef-4aca-a91c-070050ce73d4/tgsi_a_1179441_f0016_oc.gif)