Spatial Modeling and Prediction

04-GEO-MET1

Lecturer

Martin Wegmann

ECTS

5 ECTS

 

Aim:

Within this course different methods to analyse point pattern statistically and conduct a spatial prediction are covered. Students will learn how to design such analysis, how to avoid caveats, troubleshoot errors and interpret the results.

 

Content

Different statistical methods will be applied for analysing spatial point patterns, such as vegetation samples or biodiversity related information. These results will be statistically predicted using methods such as GLM, GAM, Random Forest or MaxEnt. Implications of spatial point patterns as well as chosen environmental parameters will be discussed. All methods will be practically applied during the course using the programming language R. The needed pre-requisites are covered in the course “Applied Programming for Remote Sensing and GIS“.

 

Coding

Coding examples and individual project work

Software

Various software programs will be used, but mainly OpenSource software such as R and GRASS.

Techniques

Different techniques will be introduced and practically applied such as randomForest, GAM or MaxEnt

w

Content

The theory and practice of spatial modeling with a focus on ecology and conservation

General Course News and Updates

EAGLE students coding with sweets

Today our EAGLE students applied data munging, pipes, plotting and statistics using colour distribution of sweets. They specifically used the dplyr, ggplot, kableExtra and others to compute derivatives, rearrange the data, plot it and run statistics on colour...

read more

Spatial Python block course

Last week Steven Hill and Thorsten Dahms gave a course that introduced EAGLE students to Python-based spatial data analysis. The advantages and challenges of different python libraries, data sets and methods were covered in hands-on exercises and also discussed...

read more
Share This