Can we teach machines geochemical exploration?
Abstract
Geochemical surveys are an important part of exploration for mineral resources and in environmental studies. The samples and chemical analyses are often laborious and difficult to obtain and therefore come at a high cost. As a consequence, these surveys are characterised by datasets with large numbers of variables but relatively few data points when compared to conventional big data problems. With more remote sensing platforms and sensor networks being deployed, large volumes of auxiliary data of the surveyed areas are becoming available. The use of these auxiliary data has the potential to improve the prediction of chemical element concentrations over the whole study area. Established geostatistical methods for the prediction of the spatial distributions of chemical elements in geochemical surveys are well understood but require significant pre-processing of the data. Machine learning algorithms, on the other hand, may require less data pre-processing. However, it is not well understood how these methods perform in a geospatial context. In this presentation we use a case study to compare machine learning algorithms against geostatistical methods to compare their performance in a geospatial context. In particular, we test the hypothesis that using geochemical point data and auxiliary remote sensing data can improve the prediction of the spatial distribution of chemical elements in geochemical surveys.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2016
- Bibcode:
- 2016AGUFMIN11B1623K
- Keywords:
-
- 1914 Data mining;
- INFORMATICSDE: 1932 High-performance computing;
- INFORMATICSDE: 1942 Machine learning;
- INFORMATICSDE: 1980 Spatial analysis and representation;
- INFORMATICS