Typing mineral deposits using their associated rocks, grades and tonnages using a probabilistic neural network
Mathematical Geology
By: D.A. Singer
Links
- More information: Publisher Index Page (via DOI)
- Download citation as: RIS | Dublin Core
Abstract
A probabilistic neural network is employed to classify 1610 mineral deposits into 18 types using tonnage, average Cu, Mo, Ag, Au, Zn, and Pb grades, and six generalized rock types. The purpose is to examine whether neural networks might serve for integrating geoscience information available in large mineral databases to classify sites by deposit type. Successful classifications of 805 deposits not used in training - 87% with grouped porphyry copper deposits - and the nature of misclassifications demonstrate the power of probabilistic neural networks and the value of quantitative mineral-deposit models. The results also suggest that neural networks can classify deposits as well as experienced economic geologists. ?? International Association for Mathematical Geology 2006.
| Publication type | Article |
|---|---|
| Publication Subtype | Journal Article |
| Title | Typing mineral deposits using their associated rocks, grades and tonnages using a probabilistic neural network |
| Series title | Mathematical Geology |
| DOI | 10.1007/s11004-005-9023-7 |
| Volume | 38 |
| Issue | 4 |
| Year Published | 2006 |
| Language | English |
| Larger Work Type | Article |
| Larger Work Subtype | Journal Article |
| Larger Work Title | Mathematical Geology |
| First page | 465 |
| Last page | 474 |
| Google Analytic Metrics | Metrics page |