prepro: Preprocessing in autopls
In autopls: Partial Least Squares Regression with Backward Selection of Predictors

Description Usage Arguments Details Value Author(s) References See Also

Used for preprocessing predictor data in functions autopls and predict.autopls

1	prepro(X, method = 'bn')

`X`	predictors as vector, matrix, raster brick or raster stack
`method`	type of preprocessing (currently only brightness normalization coded as “bn”)

The function is called within autopls and predict.autopls. The only implemented option is currently “bn”, which is a brightness normalization according to Feilhauer et al. (2010). Raster brick and raster stack are objects of package raster.

Returns the transformed matrix or raster object.

Hannes Feilhauer

Feilhauer. H., Asner, G.P., Martin, R.E., Schmidtlein, S. (2010): Brightness-normalized Partial Least Squares regression for hyperspectral data. Journal of Quantitative Spectroscopy and Radiative Transfer 111: 1947–1957.

autopls, predict.autopls

autopls documentation built on May 2, 2019, 9:39 a.m.