ModelMap: Creates Random Forest and Stochastic Gradient Boosting Models, and applies them to GIS .img files to build detailed prediction maps

This package will create sophisticated models of training data and validate the models with an independent test set, cross validation, or in the case of Random Forest Models, with Out Of Bag (OOB) predictions on the training data. It will create graphs and tables of the model validation results. It will apply these models to GIS .img files of predictors to create detailed prediction surfaces. It will handle large predictor files for map making, by reading in the .img files in chunks, and output to the .txt file the prediction for each data chunk, before reading the next chunk of data.

Version: 3.0.15
Depends: R (≥ 2.13.0), randomForest, raster, gbm, rgdal
Imports: fields, HandTill2001, PresenceAbsence
Published: 2014-04-17
Author: Elizabeth Freeman, Tracey Frescino
Maintainer: Elizabeth Freeman <eafreeman at fs.fed.us>
License: Unlimited
Copyright: see file COPYRIGHTS
NeedsCompilation: no
Citation: ModelMap citation info
Materials: ChangeLog
In views: Spatial
CRAN checks: ModelMap results

Downloads:

Reference manual: ModelMap.pdf
Vignettes: ModelMap: an R package for Model Creation and Map Production
Package source: ModelMap_3.0.15.tar.gz
OS X binary: ModelMap_3.0.15.tgz
Windows binary: ModelMap_3.0.15.zip
Old sources: ModelMap archive