fit_fc: Applies the Fit-FC spatiotemporal data fusion model
In mmontesinosanmartin/stfusion: What the package does (short line)

Description Usage Arguments Details Value References

Predicts the fine image at a time t2 based on a fine image from a previous moment time t1 and two coarse images, from t1 and t2

1	fit_fc(f1, c1, c2, sngb.lr, sngb.wg, nsim, scale = c(0, 1))

`f1`	fine image from t1 as a `RasterBrick`
`c1`	coarse image from t1 as a `RasterBrick`
`c2`	coarse image from t2 as a `RasterBrick`
`nsim`	number of similar pixels in each neighborhood
`scale`	the dynamic range of the image (default, `c(0,255)`
`r`	number that defines the radius of the neighborhood
`spw`	number with the weight of the spatial dependence

Applies the Fit-FC method as described in Wang and Atkinson (2018). In the same study, authors set the Fit-FC model to r=15 and nsim=30 to downscale Sentinel-3 images (300x300m) to Sentinel-2 resolution (10x10m).

the fine image predicted at t2 as a RasterBrick

Wang, Q., & Atkinson, P. M. (2018). Spatio-temporal fusion for daily Sentinel-2 images. Remote Sensing of Environment, 204, 31-42.

mmontesinosanmartin/stfusion documentation built on Jan. 8, 2021, 12:54 a.m.