sits (version 1.5.3)

sits_classify: Classify time series or data cubes

Description

This function classifies a set of time series or data cube using a trained model prediction model created by sits_train.

The sits_classify function takes three types of data as input and produce there types of output. Users should call sits_classify but be aware that the parameters are different for each type of input.

• sits_classify.sits is called when the input is a set of time series. The output is the same set with the additional column predicted.

• sits_classify.raster_cube is called when the input is a regular raster data cube. The output is a probability cube, which has the same tiles as the raster cube. Each tile contains a multiband image; each band contains the probability that each pixel belongs to a given class. Probability cubes are objects of class "probs_cube".

• sits_classify.vector_cube is called for vector data cubes. Vector data cubes are produced when closed regions are obtained from raster data cubes using sits_segment. Classification of a vector data cube produces a vector data structure with additional columns expressing the class probabilities for each object. Probability cubes for vector data cubes are objects of class "probs_vector_cube".

Usage

sits_classify(data, ml_model, ...)
# S3 method for tbl_df
sits_classify(data, ml_model, ...)
# S3 method for derived_cube
sits_classify(data, ml_model, ...)
# S3 method for default
sits_classify(data, ml_model, ...)

Value

Time series with predicted labels for each point (tibble of class "sits") or a data cube with probabilities for each class (tibble of class "probs_cube").

Arguments

data

Data cube (tibble of class "raster_cube")

ml_model

R model trained by sits_train

...

Other parameters for specific functions.

Author

Rolf Simoes,

Gilberto Camara,

Felipe Carvalho,

Felipe Carlos,