To access all pages and datasets consider registering first. Already registered? Login here. Forgot your password?

Change Font Size

Change Screen

Change Profile

Change Layouts

Change Menu Styles



Stay informed on our latest news!

Syndicate content

GEOSTAT tutorials

GEOSTAT software

Software iconList of FOSS software used in this course and installation instructions. Follow these instructions to prepare and customize the software before the beginning of the course.

Literature used

ASDAR bookList of books / lecture notes used in this course. See also: CRAN Task View: Analysis of Spatial Data.


« February 2017 »

Statistical geocomputing combining R and SAGA GIS

Objective: To introduce the RSAGA package to execute SAGA GIS geoprocessing tools and apply local and focal functions to rasters; to provide an overview of state-of-the-art statistical and machine-learning classification techniques; to introduce error measures and error estimation procedures for the assessment of spatial classification rules; to apply these methods using R

General description: This module introduces statistical geocomputing as the art and science of using and integrating statistical and GIS tools in applied spatial modeling. The focus is on classification problems, which occur in a wide range of fields such as remote sensing (land cover classification), applied geomorphology (landslide susceptibility), or ecology (habitat modeling). A broad overview of modern classification techniques and their qualitative and statistical aspects is given, and different error measures and error estimation techniques are discussed, depending on the time available. In the lab class, we will use the RSAGA and sperrorest packages to model landslide susceptibility with the generalized additive model (GAM), classification trees, and random forests.

Required back-ground knowledge:  Basic understanding of GIS operations and data types, general understanding of regression and/or classification methods
Software / R packages required: RSAGA, sperrorest, gam, rpart, randomForest, ROCR


  • Brenning, A., 2008. Statistical geocomputing combining R and SAGA: The example of landslide susceptibility analysis with generalized additive models. In: J. Boehner, T. Blaschke \&{} L. Montanarella (eds.), SAGA - Seconds Out (= Hamburger Beitraege zur Physischen Geographie und Landschaftsoekologie, 19), 23-32.
  • Brenning, A., 2012. Spatial cross-validation and bootstrap for the assessment of prediction rules in remote sensing: the R package 'sperrorest'. 2012 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 23-27 July 2012, pp. 5372-5375
  • Brenning A, Long S, Fieguth P, 2012. Detecting rock glacier flow structures using Gabor filters and IKONOS imagery. Remote Sensing of Environment, 125: 227-237.
  • Brenning, A., 2005. Spatial prediction models for landslide hazards: review, comparison and evaluation. Natural Hazards and Earth System Sciences, 5: 853-862
  • Russ, G. & A. Brenning, 2010a. Data mining in precision agriculture: Management of spatial information. Lecture Notes in Computer Science, 6178 LNAI: 350-359
  • Russ, G. & A. Brenning, 2010b. Spatial variable importance assessment for yield prediction in Precision Agriculture. Lecture Notes in Computer Science, 6065 LNCS: 184-195.
GEOSTAT2013_RSAGA.pdf360.56 KB
GEOSTAT2013_Classification.pdf936.57 KB
GEOSTAT2013_RSAGA_sperrorest_lab.zip976.54 KB
GEOSTAT2013_Geostatistics_1.pdf560.89 KB
GEOSTAT2013_Geostatistics_2.pdf271.93 KB
Your rating: None