Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM-EDS

A mineral is a natural, homogeneous solid with a definite chemical composition and a highly ordered atomic arrangement. Recently, fast and accurate mineral identification/classification became a necessity. Energy Dispersive X-ray Spectrometers integrated with Scanning Electron Microscopes (SEM) are used to obtain rapid and reliable elemental analysis or chemical characterization of a solid. However, mineral identification is challenging since there is wide range of spectral dataset for natural minerals. The more mineralogical data acquired, time required for classification procedures increases. Moreover, applied instrumental conditions on a SEM-EDS differ for various applications, affecting the produced X-ray patterns even for the same mineral. This study aims to test whether C5.0 Decision Tree is a rapid and reliable method algorithm for classification and identification of various natural magmatic minerals.Ten distinct mineral groups (olivine, orthopyroxene, clinopyroxene, apatite, amphibole, plagioclase, K-feldspar, zircon, magnetite, biotite) from different igneous rocks have been analyzed on SEM-EDS. 4601 elemental X-ray intensity data have been collected under various instrumental conditions. 2400 elemental data have been used to train and the remaining 2201 data have been tested to identify the minerals. The vast majority of the test data have been classified accurately. Additionally, high accuracy has been reached on the minerals with similar chemical composition, such as olivine ((Mg,Fe)2SiO4]) and orthopyroxene ((Mg,Fe)2SiO6]). Furthermore, two members from amphibole group (magnesiohastingsite, tschermakite) and two from clinopyroxene group (diopside, hedenbergite) have been accurately identified by the Decision Tree Algorithm. These results demonstrate that C5.0 Decision Tree Algorithm is an efficient method for mineral group classification and the identification of mineral members. C5.0 Algorithm is tested as a method for mineral identification using EDS data.Selected minerals have been classified accurately using C5.0 Algorithm.Effects of instrumental conditions have been minimized by applied methods.C5.0 Decision Tree stands as an effective tool for mineral classification using EDS.

[1]  Philip J. Potts,et al.  Electron Microprobe Analysis and Scanning Electron Microscopy in Geology , 1997, Mineralogical Magazine.

[2]  R. Howie,et al.  An Introduction to the Rock-Forming Minerals , 1966 .

[3]  J. Ross Quinlan,et al.  Bagging, Boosting, and C4.5 , 1996, AAAI/IAAI, Vol. 1.

[4]  John Mingers,et al.  An Empirical Comparison of Pruning Methods for Decision Tree Induction , 1989, Machine Learning.

[5]  J. D. Grice,et al.  Nomenclature of amphiboles: additions and revisions to the International Mineralogical Associations amphibole nomenclature , 2004, Mineralogical Magazine.

[6]  Small Ja,et al.  The Analysis of Particles at Low Accelerating Voltages (≤ 10 kV) With Energy Dispersive X-Ray Spectroscopy (EDS). , 2002 .

[7]  J. Seibert.  X-ray imaging physics for nuclear medicine technologists. Part 1: Basic principles of x-ray production. , 2004, Journal of nuclear medicine technology.

[8]  David C. Joy,et al.  Scanning Electron Microscopy and X-Ray Microanalysis , 2017 .

[9]  J. Blundy,et al.  Magma Evolution and Open System Processes at Shiveluch Volcano: Insights From Phenocryst Zoning and Melt Inclusions , 2005 .

[10]  Alan H. Strahler,et al.  Maximizing land cover classification accuracies produced by decision trees at continental to global scales , 1999, IEEE Trans. Geosci. Remote. Sens..

[11]  Ulrike Goldschmidt,et al.  A Practical Guide To Rock Microstructure , 2016 .

[12]  F. Fueten,et al.  Mineral identification using artificial neural networks and the rotating polarizer stage , 2001 .

[13]  Paul M. Mather,et al.  An assessment of the effectiveness of decision tree methods for land cover classification , 2003 .

[14]  Carla E. Brodley,et al.  Identifying Mislabeled Training Data , 1999, J. Artif. Intell. Res..

[15]  Casimir A. Kulikowski,et al.  Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[16]  S. Reed.  Electron Microprobe Analysis and Scanning Electron Microscopy in Geology , 1996 .

[17]  Nobuo Morimoto,et al.  Nomenclature of Pyroxenes , 1988, Mineralogical Magazine.

[18]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[19]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

[20]  J. A. Small.  The Analysis of Particles at Low Accelerating Voltages (≤ 10 kV) With Energy Dispersive X-Ray Spectroscopy (EDS) , 2002, Journal of research of the National Institute of Standards and Technology.

[21]  M. Sabsabi,et al.  Laser-induced breakdown spectroscopy with artificial neural network processing for material identification , 2010 .

[22]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[23]  Sun-Jong Lim,et al.  Analysis of probe current in scanning electron microscopy , 2008, 2008 International Conference on Control, Automation and Systems.

[24]  Martin J. Streck,et al.  Mineral Textures and Zoning as Evidence for Open System Processes , 2008 .

[25]  Melissa Fittipaldo,et al.  ELECTRON MICROPROBE ANALYSIS AND SCANNING ELECTRON MICROSCOPY IN GEOLOGY (2nd ed.): by S.J.B. Reed, Cambridge University Press, August 2005. 206 pages, $70.00 , 2006 .

[26]  Ying Gu.  Automated Scanning Electron Microscope Based Mineral Liberation Analysis An Introduction to JKMRC/FEI Mineral Liberation Analyser , 2003 .

[27]  C. Klein,et al.  Manual of mineralogy , 1864 .

[28]  Nurdan Akhan Baykan,et al.  Mineral identification using color spaces and artificial neural networks , 2010, Comput. Geosci..

[29]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[30]  E Brown de Colstoun,et al.  National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier , 2003 .

[31]  N G Ware,et al.  Background corrections for quantitative electron microprobe analysis using a lithium drifted silicon X-ray detector , 1973 .

[32]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[33]  V. Smolej,et al.  Classification of Energy Dispersion X-ray Spectra of Mineralogical Samples by Artificial Neural Networks , 1996, J. Chem. Inf. Comput. Sci..

[34]  Peter J. Statham,et al.  Limitations to Accuracy in Extracting Characteristic Line Intensities From X-Ray Spectra , 2002, Journal of research of the National Institute of Standards and Technology.

[35]  Erkan Aydar,et al.  WDS versus silicon drift detector EDS: a case report for the comparison of quantitative chemical analyses of natural silicate minerals. , 2008, Micron.

[36]  Brian J. Ross,et al.  Machine Vision and Applications Automatic Mineral Identification Using Genetic Programming , 2022 .