EnsClustering {CSTools}

Ensemble clustering

Description

This function performs a clustering on members/starting dates and returns a number of scenarios, with representative members for each of them. The clustering is performed in a reduced EOF space.

Usage

EnsClustering(
  data,
  lat,
  lon,
  time_moment = "mean",
  numclus = NULL,
  lon_lim = NULL,
  lat_lim = NULL,
  variance_explained = 80,
  numpcs = NULL,
  time_percentile = 90,
  time_dim = NULL,
  cluster_dim = "member",
  verbose = T
)

Arguments

data

A matrix of dimensions 'dataset member sdate ftime lat lon' containing the variables to be analysed. Latitudinal dimension accepted names: 'lat', 'lats', 'latitude', 'y', 'j', 'nav_lat'. Longitudinal dimension accepted names: 'lon', 'lons','longitude', 'x', 'i', 'nav_lon'.

lat

Vector of latitudes.

lon

Vector of longitudes.

time_moment

Decides the moment to be applied to the time dimension. Can be either 'mean' (time mean), 'sd' (standard deviation along time) or 'perc' (a selected percentile on time). If 'perc' the keyword 'time_percentile' is also used.

numclus

Number of clusters (scenarios) to be calculated. If set to NULL the number of ensemble members divided by 10 is used, with a minimum of 2 and a maximum of 8.

lon_lim

List with the two longitude margins in 'c(-180,180)' format.

lat_lim

List with the two latitude margins.

variance_explained

variance (percentage) to be explained by the set of EOFs. Defaults to 80. Not used if numpcs is specified.

numpcs

Number of EOFs retained in the analysis (optional).

time_percentile

Set the percentile in time you want to analyse (used for 'time_moment = "perc").

time_dim

String or character array with name(s) of dimension(s) over which to compute statistics. If omitted c("ftime", "sdate", "time") are searched in this order.

cluster_dim

Dimension along which to cluster. Typically "member" or "sdate". This can also be a list like c("member", "sdate").

verbose

Logical for verbose output

Value

A list with elements $cluster (cluster assigned for each member), $freq (relative frequency of each cluster), $closest_member (representative member for each cluster), $repr_field (list of fields for each representative member), composites (list of mean fields for each cluster), $lon (selected longitudes of output fields), $lat (selected longitudes of output fields).

Author(s)

Federico Fabiano - ISAC-CNR, [e-mail]

Ignazio Giuntoli - ISAC-CNR, [e-mail]

Danila Volpi - ISAC-CNR, [e-mail]

Paolo Davini - ISAC-CNR, [e-mail]

Jost von Hardenberg - ISAC-CNR, [e-mail]

Examples

exp <- array(abs(rnorm(1152))*275, dim = c(dataset = 1, member = 4, 
                                          sdate = 6, ftime = 3, 
                                          lat = 4, lon = 4))
lon <- seq(0, 3)
lat <- seq(48, 45)
res <- EnsClustering(exp, lat = lat, lon = lon, numclus = 2,
                    cluster_dim = c("member", "dataset", "sdate"))