Geostatistics in R

Workshop Outline

This workshop will give a basic yet practical introduction to:

Compositional data analysis:
Statistical analysis of geological (chemical, mineralogical, isotopic) data is fraught with problems. ‘ordinary’ statistical operations such as averaging, regression and error propagation do not always work as expected when they are applied to strictly positive values that are constrained to a constant sum. We will see how to fix this problem.

‘Big Data’ analysis in sedimentary provenance analysis:
Sedimentary provenance studies increasingly apply multiple chemical, mineralogical and isotopic proxies to many samples. The resulting datasets are often so large (containing thousands of numerical values) and complex (comprising multiple dimensions) that it is warranted to use the internet-era term ‘Big Data’ to describe them. The workshop will introduce simple but effective techniques such as principal component analysis and multidimensional scaling to extract geologically meaningful information from such large datasets.

R Programming:
R is a free and open statistical programming language that is rapidly gaining popularity in the Earth Sciences. The workshop will provide a basic introduction to R and some packages that implement the statistical techniques introduced above.

Workshop Leader:

Dr. Pieter Vermeesch

Dr. Pieter Vermeesch is a Reader in Geochronology at University College London (UCL) and co-director of the London Geochronology Centre (LGC). His research interests include geochronology, thermochronometry, (geo)statistics and aeolian geomorphology using the U-Pb, Ar-Ar, fission track and U-Th-He methods. Dr. Vermeesch develops novel ways to generate and interpret ‘Big Data’ for sedimentary provenance analysis, by combining detrital geochronology with mineralogical and chemical provenance tracers. He has developed a suite of free and user-friendly software to make these tools available to the Geosciences community.