GEOSTAT courses

Location

Overview

Course/workshop organizers:

• Augusto Sanabria, Geospatial & Earth Monitoring Division Geoscience Australia
• Alan Welsh, Centre for Mathematics & Its Applications. Australian National University

Objectives: Introduce participants to open source tools R+OSGeo, give some hands-on training and provide enough resources (literature, examples, datasets) so that participants can continue developing his/her skills independently. At the end of the workshop each participant will be familiar with how to load spatio-temporal data in R, reformat and analyze it, visualize it using Open Source GIS and Google Earth and write results in various formats. We also aim we also aim at getting Australian/NZ scientists more involved in the R+OSGeo activities (both as users and contributors).

Target group: Australian/NZ scientists that use Spatial Data Analysis in their work but are not GIS specialists or spatial statisticians; various backgrounds (economists, engineers, scientists, mathematical modellers, etc.).

Lecturers

Course moderators:

1. Tomislav Hengl (Tom), Senior research, ISRIC - World Soil Information, Wageningen University
2. Dylan E. Beaudette (Dylan), Soil Scientist - Natural Resources Conservation Service, USDA

Guest lectures:

1. John Maindonald, Centre for Mathematics & Its Applications, Australian National University, Canberra
2. Graham Williams, Senior director and Chief Data Miner, Australian Taxation Office, Canberra

Daily programme

Coffee breaks daily at 10:30 and 15:30

DAY1: Introduction and software installation

• 9:30 - 10:30 Welcome note and course overview [PDF] (Hengl & Beaudette)
• 11:00 - 13:00 Introduction, Research Interests, OSGEO Demos [PDF] (Beaudette)
• 14:00 - 15:30 Software installation and first steps (Hengl & Beaudette)
• 16:00 - 18:00 Open Source GIS (OSGEO) [PDF] Demonstrations (Beaudette)
• (optional) 18:00 - 19:30 First steps in R (Hengl)

DAY2: Space-time data formats (field observations)

• 9:00 - 11:00 Working with Spatial and Time-Series Data in R [PDF] (Beaudette)
• 11:00 - 13:00 Visualization of Spatial and Time-Series Data in R (Beaudette)
• 14:00 - 17:00 Exercise: Time-series of meteorological measurements (Hengl)
• 17:00 - 17:30 Discussion block (Hengl, Beaudette)

DAY3: Working with gridded maps

• 9:00 - 11:00 Introduction to spatial db / SQL and PostGIS [PDF] (Beaudette)
• 11:00 - 13:00 GRASS GIS, R+FWTools, SAGA GIS [PDF] (Hengl)
• 14:00 - 15:30 Exercise: Preparation of gridded maps for the HRtemp2008 case study [MODIS images] (Hengl)
• 16:00 - 17:30 Guest lecture by Graham Williams: "FOSS in industry"

DAY4: Spatial prediction

• 9:00 - 11:00 Overview of spatial prediction models [PDF] (Hengl)
• 11:00-13:00 Regression-kriging (Hengl)
• 14:00 - 17:00 Exercise: spatio-temporal interpolation of daily temperatures (Hengl)
• 17:00 - 17:30 Discussion block (Hengl, Beaudette)
• +20:00 Dinner at the Indian restaurant close to ANU

DAY5: Visualization of space-time data using Google Earth (P.A.P. Moran room! building 26b located in map GH32 at grid reference G3)

• 9:00 - 10:30 Guest lecture by John Maindonald: "Linear models in spatial statistics" [PDF] additional materials
• 11:00-13:00 Visualization of space-time data in Google Earth (Beaudette)
• 14:00 - 15:30 Open block
• 16:00 - 17:00 Discussion forum: where do we go from here?

DAY6: Excursion (optional)

Case studies:

1. HRclim2008: Daily temperature measurements (365 x 159 locations)
2. Meuse: Soil samples in the southern Netherlands

Key literature:

• Beaudette, D., 2009. Open Source Software Tools for Soil Scientists [website], University of California at Davis.
• Bivand, R., Pebesma, E., Rubio, V., 2008. Applied Spatial Data Analysis with R. Use R Series, Springer, Heidelberg, 378 p.
• Camara, G., Onsrud, H., 2004. Open Source GIS: Myths and Realities. The National Academic Press, Washington.
• Hengl, T., 2009. A Practical Guide to Geostatistical Mapping, 2nd edition. University of Amsterdam, 291 p. ISBN 978-90-9024981-0 (each participant will receive a free copy)
• Kuhnert, P., Venables, W.N., 2005. An Introduction to R: Software for Statistical Modelling & Computing. CSIRO Canberra, Australia, 362 p.
• Maindonald, J., Braun, J., 2010. Data Analysis and Graphics Using R - An Example-Based Approach. 3rd Ed Cambridge University Press, 
• Neteler, M., Mitasova, H., 2008. Open Source GIS: A GRASS GIS Approach, 3rd Edt. Springer, The International Series in Engineering and Computer Science: Volume 773. 406 p.
• Short, T., 2008. R reference card. EPRI PEAC, 4 p.

Requirements and preparation

Each participant is expected to come with his/her own WLAN-enabled laptop. Each participant is responsible for maintaining and customizing the software. Software to be used at the course (installation in detail):

• Operating system (recommended): Windows 7, 64-Bit; with installation rights and 4GB RAM;
• Statistical computing: R 2.12; installation steps:
  • download and install R from CRAN;
  • copy and replace the Rprofile.site (make sure you have read/write rights for the R directory);
  • install Tinn-R and start R from Tinn-R;
  • install R spatial packages;
• R scripting: Tinn-R and/or RStudio;
• GIS: SAGA GIS 2.0.6 (unzip precompiled binaries under "/library/RSAGA/saga_vc/"), QGIS and GRASS GIS 6.4;
• Geographical data browser: Google Earth;
• Database connections: ODBC driver; RODBC and RPostgreSQL packages;

 How to prepare for this course?

1. Study the recommended literature and web-sources.
2. Install and test using recommended software.
3. Obtain the case studies and try to import and visualize data.