Classifies a block of data using multicores. It breaks the data into horizontal blocks and divides them between the available cores.
Reads data from a file using Rgdal, then cleans the data for NAs and missing values. The clean data is stored in a data table that has all the time instances for all pixels of the block. The algorithm then classifies data on an year by year basis. For each year, it extracts the sub-blocks for each band.
After all cores process their blocks, it joins the result and then writes it in the classified images for each corresponding year.
.sits_classify_multicores(coverage, coverage_class, samples, ml_model,
interval, filter, memsize, multicores)Tibble with metadata for a RasterBrick.
Taster layer objects to be written.
Tibble with samples used for training the classification model.
A model trained by sits_train.
Classification interval.
Smoothing filter to be applied to the data.
Memory available for classification (in GB).
Number of cores.
List of the classified raster layers.