[R-sig-Geo] Release of SITS version 1.4.2-1

[Gilberto Camara]

Dear R-SIG-GEO,

We would like to announce the release of version 1.4.2-1 of the “sits” package. The improvements of this version include: 

(a) Support for vector data cubes, including visualisation
(b) Object-based time series analysis using spatio-temporal segmentation
(c) Improved support for GPU usage when running deep learning algorithms
(d) New function to clean values by modal filter in classified images
(e) Experimental support for Sentinel-1 images available on MPC
(f) Improve summary function to include cloud cover information
(g) General bug fixes

“sits” is a long-term project for improving land use and land cover classification using big EO data. The package provides an end-to-end environment for LUCC analysis. Users are supported by an on-line book (https://e-sensing.github.io/sitsbook/). It has reached TRL 9 status, being used operational for LUCC mapping in large areas of Brazil. 

Such an ambitious endeavour would not be possible without the substantial contribution of the R-SIG-GEO community, including but not limited to the following experts:

- Daniel Baston for “exactextractr”
- David Cooley for “geojsonsf"
- Edzer Pebesma for “sf/stars”
- Jakub Nowosad for “supercells”
= Joshua O’Brien for “gdalUtilities"
- Marius Appel for “gdalcubes”
- Martijn Tennekes for “tmap”
- Robert Hijmans for “terra”,
- Tim Appelhans for “leafem”

Many thanks to all of you, and most especially to Roger, an inspiration to us all.

All the best
Gilberto
============================
Prof Dr Gilberto Camara
Senior Researcher
National Institute for Space Research (INPE), Brazil
https://gilbertocamara.org/
=============================