The service, starting from a multi-class shapefile containing the land cover classes in the scene, expressed in FAO-LCCS taxonomy, aims to generate a series of shapefiles, one for each different class. A numeric code is also associated to each class. The algorithm uses as input training and test data used to obtain the multi-class land cover mapping of the scene by a supervised, pixel-based classification. Within the Ailanthus workflow of the Internal Joint Intiative, it represents the step 1 and 2 of the first stage (where a multi-class problem is considered).

This service aims at creating a stack of coregistered multi-spectral raster images. It groups four multi-seasons images and stack them to obtain a unique image at native resolution (30 meters) by using the Landsat 5 sensor. It represents the Step 3 of the Ailanthus Workflow within the Internal Joint Initiative.

A set of functions for error detection and correction in point data quality datasets that are used in species distribution modelling. Includes functions for parsing and converting coordinates into decimal degrees from various formats.

The package provides features to manage the complete workflow for biodiversity data cleaning: uploading data, gathering input from users (in order to adjust cleaning procedures), cleaning data and finally, generating various reports and several versions of the data. It facilitates user-level data cleaning, designed for the inexperienced R users.

A set of tools for training, selecting, and evaluating maximum entropy (and standard logistic regression) distribution models. This package provides tools for user-controlled transformation of explanatory variables, selection of variables by nested model comparison, and flexible model evaluation and projection. It follows principles based on the maximum-likelihood interpretation of maximum entropy modeling, and uses infinitely-weighted logistic regression for model fitting.

The package includes algorithms for presence-background (Maxent) and presence-absence (GAM, GLM). It allows to construct niche models and analyze patterns of niche evolution. It acts as an interface for many popular modeling algorithms, and allows users to conduct Monte Carlo tests to address basic questions in evolutionary ecology and biogeography.

The package includes algorithms for presence-background (Maxent) and presence-absence (GAM, GLM, GBM, SVM, RF, ANN). Moreover, it contains functions for sampling bias correction, sampling pseudoabsences and background points, data partitioning, and reducing collinearity in predictors; fitting and evaluating models, ensembles of small models and ensemble models; models’ predictions, interpolation and overprediction correction.

This service aims at running various statistical analyses in RvLab on the data produced in ARMS workflow. It represents the Step 10 of the ARMS Workflow within the Internal Joint Initiative.

The package has been designed to characterize the realized niche of the species by interfacing R software with GRASS geographical information system in order to overcome issues when working with large datasets (i.e., wide areas or high resolution). This package uses classes defined in rgrass7 package to deal with spatial data and to interface R and Grass.

A workflow for ecological niche models based on "dismo". The package include functions for modelling that helps to seamlessly integrate modelling into a pipeline of data manipulation and visualisation.