Traditional kriging versus modern Gaussian processes for large‐scale mining data
- 21 July 2023
- journal article
- research article
- Published by Wiley in Statistical Analysis and Data Mining: An ASA Data Science Journal
- Vol. 16 (5) , 488-506
Abstract
The canonical technique for nonlinear modeling of spatial/point‐referenced data is known as kriging in geostatistics, and as Gaussian Process (GP) regression for surrogate modeling and statistical learning. This article reviews many similarities shared between kriging and GPs, but also highlights some important differences. One is that GPs impose a process that can be used to automate kernel/variogram inference, thus removing the human from the loop. The GP framework also suggests a probabilistically valid means of scaling to handle a large corpus of training data, that is, an alternative to ordinary kriging. Finally, recent GP implementations are tailored to make the most of modern computing architectures, such as multi‐core workstations and multi‐node supercomputers. We argue that such distinctions are important even in classically geostatistical settings. To back that up, we present out‐of‐sample validation exercises using two, real, large‐scale borehole data sets acquired in the mining of gold and other minerals. We compare classic kriging with several variations of modern GPs and conclude that the latter is more economical (fewer human and compute resources), more accurate and offers better uncertainty quantification. We go on to show how the fully generative modeling apparatus provided by GPs can gracefully accommodate left‐censoring of small measurements, as commonly occurs in mining data and other borehole assays.Keywords
All Related Versions
Funding Information
- National Science Foundation of Sri Lanka (1822108, 1822146)
This publication has 40 references indexed in Scilit:
- Gaussian Process Single-Index Models as Emulators for Computer ExperimentsTechnometrics, 2012
- Strictly Proper Scoring Rules, Prediction, and EstimationJournal of the American Statistical Association, 2007
- Approximating Likelihoods for Large Spatial Data SetsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2004
- Generalized Accept-Reject sampling schemes2004
- Neural Network Exploration Using Optimal Experiment DesignNeural Networks, 1996
- Fisher's Method of ScoringInternational Statistical Review, 1992
- Minimax and maximin distance designsJournal of Statistical Planning and Inference, 1990
- Design and Analysis of Computer ExperimentsStatistical Science, 1989
- Fitting variogram models by weighted least squaresMathematical Geology, 1985
- Principles of geostatisticsEconomic Geology, 1963