Dear R-SIG-GEO We are pleased to inform you that version 1.5.4 of “sits” is available on CRAN. This package provides an end-to-end toolkit for land-use and land-cover classification using big Earth observation datasets. Advances in version 1.5.4 include support for spatiotemporal segmentation of data cubes using an extended version of the SNIC algorithm and performance optimisations for increased GPU efficiency.
The online book describing the “sits” package (https://e-sensing.github.io/sitsbook/) has also been much updated. The package and the online book have benefited from a software review held under the guidance of the ROpenSci community, chaired by Mark Padgham. We appreciate the key contributions of reviewers: Lorena Abad (in memoriam), Michael Summer, Edzer Pebesma, Jakub Nowosad and Alex Leith. For those in our community interested in multilanguage interoperability of geospatial software, “sits” 1.5.4 includes a Python API via a Python wrapper (https://github.com/e-sensing/pysits). There is no measurable impact on performance. Best regards Gilberto ============================ Prof Dr Gilberto Camara Senior Researcher Getulio Vargas Foundation (FGV) National Institute for Space Research (INPE), Brazil https://gilbertocamara.org/ ============================= _______________________________________________ R-sig-Geo mailing list [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-geo
