A comparison of t-SNE, SOM and SPADE for identifying material type domains in geological data

@article{Balamurali2019ACO,
  title={A comparison of t-SNE, SOM and SPADE for identifying material type domains in geological data},
  author={Mehala Balamurali and Katherine L. Silversides and Arman Melkumyan},
  journal={Comput. Geosci.},
  year={2019},
  volume={125},
  pages={78-89}
}

From Continent to Ocean: Investigating the Multi-Element and Precious Metal Geochemistry of the Paraná-Etendeka Large Igneous Province Using Machine Learning Tools

Large Igneous Provinces, and by extension the mantle plumes that generate them, are frequently associated with platinum-group element (PGE) ore deposits, yet the processes controlling the metal

Quantifying Mineral Resources and Their Uncertainty Using Two Existing Machine Learning Methods

This research proposes the use and comparison of two machine learning methods, multiple linear regression and a multilayer neural network, to generate tonnage curves and their CIs directly from the data, and indicates that there are no significant differences between the ML methods.

Sample Truncation Strategies for Outlier Removal in Geochemical Data: The MCD Robust Distance Approach Versus t-SNE Ensemble Clustering

Two sample truncation strategies which have been devised to reject outliers in multivariate geochemical data are presented and Visual and quantitative analyses show that the proposed methods are superior to the baseline method which rejects samples using chi-square critical values.

Can Agents Model Hydrocarbon Migration for Petroleum System Analysis? A Fast Screening Tool to De-Risk Hydrocarbon Prospects

Understanding subsurface hydrocarbon migration is a crucial task for petroleum geoscientists. Hydrocarbons are released from deeply buried and heated source rocks, such as shales with a high organic

A Comparison of Linear and Non-Linear Machine Learning Techniques (PCA and SOM) for Characterizing Urban Nutrient Runoff

Urban stormwater runoff represents a significant challenge for the practical assessment of diffuse pollution sources on receiving water bodies. Given the high dimensionality of the problem, the main

t-Distributed Stochastic Neighbor Embedding

  • M. Balamurali
  • Computer Science
    Encyclopedia of Mathematical Geosciences
  • 2021

References

SHOWING 1-10 OF 24 REFERENCES

Advanced methodologies for the analysis of databases of mineral deposits and major faults

The effectiveness of some novel software tools used for clustering and classifying multivariate data is tested and used to evaluate mineral exploration criteria by examining a mineral deposit and

t-SNE Based Visualisation and Clustering of Geological Domain

This work compares PCA and some other linear and non-linear methods with a newer method, t-Distributed Stochastic Neighbor Embedding (t-SNE) for the visualization of large geochemical assay datasets and finds significant differences between the nonlinear method t-S NE and the state of the art methods in two dimensional target spaces.

Detection of Outliers in Geochemical Data Using Ensembles of Subsets of Variables

A novel approach for detecting outliers robustly in large multi-dimensional geochemical data that incorporates a feature selection method that automatically seeks the best subset of chemical ratios that, together with the original chemical variables, best represent the inherent characteristics of the data.

A Data Mining Approach to Validating Drill Hole Logging Data in Pilbara Iron Ore Exploration

Logging of exploration drillholes is a routine practice and its accuracy is essential for resource evaluation and planning in the minerals industry. Logged compositions record a set of material types

Data mining of 3D poststack seismic attribute volumes using Kohonen self-organizing maps

For several decades, artificial neural networks have assisted in data reduction processes through classifications applied to a wide spectrum of aspects—from traffic solutions and medicinal purposes

The Genesis of the Hope Downs Iron Ore Deposit, Hamersley Province, Western Australia

The banded iron formation (BIF)-hosted Hope Downs high-grade hematite ore deposits are situated within the Marra Mamba Iron Formation with subsidiary deposits in the Brockman Iron Formation of the

Marra Mamba Iron Formation stratigraphy in the eastern Chichester Range, Western Australia

The Marra Mamba Iron Formation is the basal member of the Hamersley Group in Western Australia and is host to major iron‐ore deposits in its upper Mt Newman Member. Previous studies have suggested

Iron formation-hosted iron ores in the Hamersley Province of Western Australia

Abstract Iron formation-hosted iron ore deposits account for the majority of current world iron ore production and consist of three classes: unenriched primary iron formation with typically 25 to 45

Engineering applications of the self-organizing map

The self-organizing map method, which converts complex, nonlinear statistical relationships between high-dimensional data into simple geometric relationships on a low-dimensional display, can be utilized for many tasks: reduction of the amount of training data, speeding up learning nonlinear interpolation and extrapolation, generalization, and effective compression of information for its transmission.