sits_kohonen: Cluster a set of satellite image time series using SOM

In luizassis/sits: Satellite Image Time Series Analysis

Description

This function uses package "kohonen" (self-organized maps) to find clusters in satellite image time series.

Usage

sits_kohonen(data.tb, bands = NULL, grid_xdim = 5, grid_ydim = 5,
  rlen = 100, alpha = c(0.05, 0.01), ...)

Arguments

data.tb	a SITS tibble the list of time series to be clustered
bands	the bands to be clusterized.
grid_xdim	x dimension of the SOM grid (used only in 'kohonen' or 'kohonen-dendogram' methods). Defaul is 5.
grid_ydim	y dimension of the SOM grid
rlen	the number of times the complete data set will be presented to the SOM grid
alpha	learning rate, a vector of two numbers indicating the amount of change. Default is to decline linearly from 0.05 to 0.01 over rlen updates.
...	Additional parameters to be passed to kohonen::supersom function

Value

clusters.tb a SITS tibble with the clusters time series or cluster' members time series according to return_member parameter. If return_members are FALSE, the returning SITS table will contain a new collumn called 'n_members' informing how many members has each cluster.

Author(s)

Gilberto Camara, [e-mail]

Rolf Simoes, [e-mail]

Lorena Alves, [e-mail]

References

'kohonen' package (https://CRAN.R-project.org/package=kohonen)

luizassis/sits documentation built on May 30, 2019, 7:15 p.m.