luke_wp

Hutton property modelling whitepaper

Geostatistical models comprise two elements: a geological prior (trend model) and a geostatistical residual. The prior is developed by interrogating the observed data for evidence of non-stationary effects (trends), defining these with mathematical functions, and subtracting them from the observed data...

READ THE FULL PAPER.

 

firstbreak

First Break - October 2019 issue

The decision-oriented world: effective management of uncertainty in geomodelling workflows

Lucy MacGregor, Michael Stewart, Keegan Benallack and Luke Johnson present a machine learning approach to identify commercially significant models within a large ensemble and characterise the uncertainty in decisions based on these.

ACCESS THE FULL PAPER AT FIRST BREAK

 

epcc

The 5th International Workshop on Data Reduction for Big Scientific Data (DRBSD-5)

Using machine learning to reduce ensembles of geological models for oil and gas exploration

...the result of this work is a series of lessons learnt and techniques that are not only applicable to oil and gas exploration, but also more generally to the HPC community as we as a community are forced to work with reduced data-sets due to the gathering of data growing so rapidly.

FULL PAPER COMING SOON HERE