The following software progress were made by the AG Umweltinformatik in the last years.
'caret' Applications for Spatial-Temporal Models
Meyer H, Reudenbach C, Nauss T (2018)
Supporting functionality to run 'caret' with spatial or spatial-temporal data. 'caret' is a frequently used package for model training and prediction using machine learning. This package includes functions to improve spatial-temporal modelling tasks using 'caret'. It prepares data for Leave-Location-Out and Leave-Time-Out cross-validation which are target-oriented validation strategies for spatial-temporal models. To decrease overfitting and improve model performances, the package implements a forward feature selection that selects suitable predictor variables in view to their contribution to the target-oriented performance. CRAN
remote: Empirical Orthogonal Teleconnections in R.
Appelhans T, Detsch F, Nauss T (2016)
Empirical orthogonal teleconnections in R. 'remote' is short for "R(-based) EMpirical Orthogonal TEleconnections". It implements a collection of functions to facilitate empirical orthogonal teleconnection analysis. Empirical Orthogonal Teleconnections (EOTs) denote a regression based approach to decompose spatio-temporal fields into a set of independent orthogonal patterns. They are quite similar to Empirical Orthogonal Functions (EOFs) with EOTs producing less abstract results. In contrast to EOFs, which are orthogonal in both space and time, EOT analysis produces patterns that are orthogonal in either space or time.
mapview: Interactive Viewing of Spatial Objects in R.
Appelhans T, Detsch F, Reudenbach C, Woellauer S (2016)
Methods to view spatial objects interactively.
gimms: Download and process GIMMS NDVI3g Data.
Detsch F (2016)
We provide a set of functions to retrieve information about GIMMS NDVI3g files currently available online; download and re-arrange the bi-monthly datasets according to creation time; import downloaded files from native binary (ENVI) format directly into R based on the widely applied 'raster' package; extract accompanying quality flags and perform quality control; calculate monthly value composites (e.g. maximum value composites, MVC) from the bi-monthly input data; and derive long-term monotonous trends from the Mann-Kendall trend test, optionally featuring pre-whitening to account for lag-1 autocorrelation.
Transformation of reflectance spectra, calculation of vegetation indices and red edge parameters, spectral resampling for hyperspectral remote sensing, simulation of reflectance and transmittance using the leaf reflectance model PROSPECT and the canopy reflectance model PROSAIL.
satellite: Manipulating satellite data with satellite.
Nauss T, Meyer H, Detsch F, Appelhans T (2016)
This smorgasbord provides a variety of functions which are useful for handling, manipulating and visualizing remote sensing data.
Our GitHub respository
Environmental Informatics Marburg
You can find a lot of other (useful) functions and scripts at our GitHub repository. Don't miss to check out e.g. Rsenal.