Support vector machine for 3D modelling from sparse geological information of various origins

Authors:
Alex Smirnoff;Eric Boisvert;Serge J. Paradis
Affiliations:
Natural Resources Canada, Earth Sciences Sector, 490, de la Couronne Québec, Que., Canada G1K 9A91;Natural Resources Canada, Earth Sciences Sector, 490, de la Couronne Québec, Que., Canada G1K 9A91;Natural Resources Canada, Earth Sciences Sector, 490, de la Couronne Québec, Que., Canada G1K 9A91
Venue:
Computers & Geosciences
Year:
2008

Citing 5
Cited 5

Discrete smooth interpolation

ACM Transactions on Graphics (TOG)
The nature of statistical learning theory

The nature of statistical learning theory
Predicting the in vivo signature of human gene regulatory sequences

Bioinformatics
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Mining subsidence prediction based on 3D stratigraphic model and visualization

Transactions on edutainment VI
Mineral potential targeting and resource assessment based on 3D geological modeling in Luanchuan region, China

Computers & Geosciences
3D exploratory analysis of descriptive lithology records using regular expressions

Computers & Geosciences
Support vector machine for multi-classification of mineral prospectivity areas

Computers & Geosciences
Selection of initial designs for multi-objective optimization using classification and regression tree

Structural and Multidisciplinary Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

Three-dimensional (3D) geological models are a powerful way of visualization, analysis and interpretation of geological information. However, manual modelling with available GIS tools is a challenging and time-consuming task. Here we propose the use of the support vector machine (SVM) in order to automate the creation of such models. We experiment with various input data and hyperparameters in order to demonstrate that the SVM can be efficiently applied in 3D geological reconstructions overcoming some limitations of previously used methods.