R-SITS package 1.5.2 launched - supports many MPC collections

[gilbertocamara]

We are pleased to inform you that version 1.5.2 of the R-SITS package is available on CRAN! R-SITS is an end-to-end solution for LUCC mapping of big Earth observation data using ML and DL methods to classify satellite image time series.

1. Supports access to MPC collections SENTINEL-1-RTC, SENTINEL-1-GRD, SENTINEL-2-L2A, LANDSAT-C2-L2, COP-DEM-GLO-30, MOD09A1-6.1, MOD10A1-6.1, and MOD13Q1-6.1.
2. Builds regular data cubes from MPC collections, enabling multi-source analytics (SAR + optical + DEM +…).
3. Includes functions for quality assessment of training samples using self-organized maps and methods to reduce training samples imbalance.
4. Provides machine learning algorithms including support vector machines, random forests, extreme gradient boosting, multi-layer perceptrons, temporal convolution neural networks, and temporal attention encoders.
5. Performs efficient classification of big Earth observation data cubes and includes functions for post-classification smoothing based on Bayesian inference.
6. Includes methods for estimating area and assessing accuracy of land change using best practices.

See more at Preface | sits: Satellite Image Time Series Analysis on Earth Observation Data Cubes and GitHub - e-sensing/sits: Satellite image time series in R