Geographic Data Analysis and Modeling

Reading, writing, manipulating, analyzing and modeling of spatial data. This package has been superseded by the "terra" package < https://CRAN.R-project.org/package=terra>.

Color Palettes Inspired by Works at the Metropolitan Museum of Art

Palettes Inspired by Works at the Metropolitan Museum of Art in New York. Currently contains over 50 color schemes and checks for colorblind-friendliness of palettes. Colorblind accessibility checked using the '{colorblindcheck} package by Jakub Nowosad'< https://jakubnowosad.com/colorblindcheck/>.

Similarity and Distance Quantification Between Probability Functions

Computes 46 optimized distance and similarity measures for comparing probability functions (Drost (2018) ). These comparisons between probability functions have their foundations in a broad range of scientific disciplines from mathematics to ecology. The aim of this package is to provide a core framework for clustering, classification, statistical inference, goodness-of-fit, non-parametric statistics, information theory, and machine learning tasks that are based on comparing univariate or multivariate probability functions.

'CARTOColors' Palettes

Provides color schemes for maps and other graphics designed by 'CARTO' as described at < https://carto.com/carto-colors/>. It includes four types of palettes: aggregation, diverging, qualitative, and quantitative.

Creates Co-Occurrence Matrices of Spatial Data

Builds co-occurrence matrices based on spatial raster data. It includes creation of weighted co-occurrence matrices (wecoma) and integrated co-occurrence matrices (incoma; Vadivel et al. (2007) ).

Superpixels of Spatial Data

Creates superpixels based on input spatial data. This package works on spatial data with one variable (e.g., continuous raster), many variables (e.g., RGB rasters), and spatial patterns (e.g., areas in categorical rasters). It is based on the SLIC algorithm (Achanta et al. (2012) ), and readapts it to work with arbitrary dissimilarity measures.

Colors for all

Color palettes for all people, including those with color vision deficiency. Popular color palette series have been organized by type and have been scored on several properties such as color-blind-friendliness and fairness (i.e. do colors stand out equally?). Own palettes can also be loaded and analysed. Besides the common palette types (categorical, sequential, and diverging) it also includes cyclic and bivariate color palettes. Furthermore, a color for missing values is assigned to each palette.

Access Elevation Data from Various APIs

Several web services are available that provide access to elevation data. This package provides access to many of those services and returns elevation data either as an 'sf' simple features object from point elevation services or as a 'raster' object from raster elevation services. In future versions, 'elevatr' will drop support for 'raster' and will instead return 'terra' objects. Currently, the package supports access to the Amazon Web Services Terrain Tiles < https://registry.opendata.aws/terrain-tiles/>, the Open Topography Global Datasets API < https://opentopography.org/developers/>, and the USGS Elevation Point Query Service < https://apps.nationalmap.gov/epqs/>.

Additional Functions for 'GeoPAT' 2

Supports analysis of spatial data processed with the 'GeoPAT' 2 software < https://github.com/Nowosad/geopat2>. Available features include creation of a grid based on the 'GeoPAT' 2 grid header file and reading a 'GeoPAT' 2 text outputs.

'caret' Applications for Spatial-Temporal Models

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. CAST includes functions to improve spatial or spatial-temporal modelling tasks using 'caret'. It includes the newly suggested 'Nearest neighbor distance matching' cross-validation to estimate the performance of spatial prediction models and allows for spatial variable selection to selects suitable predictor variables in view to their contribution to the spatial model performance. CAST further includes functionality to estimate the (spatial) area of applicability of prediction models. Methods are described in Meyer et al. (2018) ; Meyer et al. (2019) ; Meyer and Pebesma (2021) ; Milà et al. (2022) ; Meyer and Pebesma (2022) ; Linnenbrink et al. (2024) ; Schumacher et al. (2025) . The package is described in detail in Meyer et al. (2026) .