A multi-task multi-class learning method for automatic identification of heavy minerals from river sand

Abstract The identification of heavy minerals collected from river sand is an essential work in geology, which has great significance in the sedimentary provenance analysis, tectonic evolution and lithofacies paleogeography. Automatic identification of heavy minerals using classifiers trained by identified minerals has become a topical issue in applying machine learning techniques to geological research. Due to the high cost of manual identification and annotation, the available identified heavy minerals from a single river basin are insufficient for training a classifier with acceptable accuracy. Besides, since there are scores of heavy mineral classes in nature, the common “One vs. One” and “One vs. Rest” strategies used for multi-class classification will cause the problems of class imbalance and time overhead in the case of identifying heavy minerals. In this paper, we propose a Multi-Task Multi-Class learning method (MTMC), which leverages the correlation among heavy minerals collected from multiple river basins, and jointly handles these identification tasks, in order to deal with the problem of insufficient identified heavy minerals from a single river basin while improve the performance of the identification of heavy minerals in all the river basins. MTMC uses softmax as the classifier to handle the multi-class classification of heavy minerals, and formalizes the multi-task learning as a convex optimization problem. The experimental results based on heavy minerals collected from the Yangtse River, Yarlung Zangbo River and PumQu River demonstrate the effectiveness of MTMC, which evidently outperforms current machine learning methods for the identification of heavy minerals.

[1]  I. Dunkl,et al.  Semi-Automated Heavy-Mineral Analysis by Raman Spectroscopy , 2019, Minerals.

[2]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[3]  Michael I. Jordan,et al.  Multi-task feature selection , 2006 .

[4]  Ayhan Demiriz,et al.  Linear Programming Boosting via Column Generation , 2002, Machine Learning.

[5]  R. Khajavi,et al.  Automated mineral identification algorithm using optical properties of crystals , 2015, Comput. Geosci..

[6]  Pei Wang,et al.  Research of moldy tea identification based on RF-RFE-Softmax model and hyperspectra , 2018 .

[7]  Na Li,et al.  A transfer learning method for automatic identification of sandstone microscopic images , 2017, Comput. Geosci..

[8]  Simon J. Kemp,et al.  Heavy mineral analysis by ICP-AES a tool to aid sediment provenancing , 2018 .

[9]  Gunnar Rätsch,et al.  Totally corrective boosting algorithms that maximize the margin , 2006, ICML.

[10]  Martin Chamberland,et al.  Mineral identification in hyperspectral imaging using Sparse-PCA , 2016, SPIE Commercial + Scientific Sensing and Imaging.

[11]  Hossein Izadi,et al.  An intelligent system for mineral identification in thin sections based on a cascade approach , 2017, Comput. Geosci..

[12]  Taghi M. Khoshgoftaar,et al.  RUSBoost: A Hybrid Approach to Alleviating Class Imbalance , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[13]  I. Jolliffe.  Principal Component Analysis , 2005 .

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

[15]  Harun Artuner,et al.  Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM-EDS , 2015, Comput. Geosci..

[16]  Eduardo Garzanti,et al.  Raman spectroscopy in heavy-mineral studies , 2013 .

[17]  J. R. Quinlan.  Induction of decision trees , 2004, Machine Learning.

[18]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[19]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[20]  Andrew C. Morton,et al.  Identifying provenance-specific features of detrital heavy mineral assemblages in sandstones , 1994 .

[21]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[22]  Marilton S. de Aguiar,et al.  Mineral Classification Using Machine Learning and Images of Microscopic Rock Thin Section , 2019, MICAI.

[23]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.

[24]  Jiayu Zhou,et al.  Integrating low-rank and group-sparse structures for robust multi-task learning , 2011, KDD.

[25]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[26]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[27]  Huizhen Hao,et al.  Machine learning application to automatically classify heavy minerals in river sand by using SEM/EDS data , 2019, Minerals Engineering.

[28]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[29]  Marcus Gallagher,et al.  Neural networks and the classification of mineralogical samples using x-ray spectra , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[30]  Jieping Ye,et al.  Robust multi-task feature learning , 2012, KDD.

[31]  Lutfiye Akin,et al.  Identification of Some Zeolite Group Minerals by Application of Artificial Neural Network and Decision Tree Algorithm Based on SEM-EDS Data , 2016 .

[32]  Masakazu Niwa,et al.  Provenance identification based on EPMA analyses of heavy minerals: Case study of the Toki Sand and Gravel Formation, central Japan , 2019, Island Arc.

[33]  Ali Jalali,et al.  A Dirty Model for Multi-task Learning , 2010, NIPS.

[34]  Reza Khajavi,et al.  Automatic mineral identification using color tracking , 2017, Pattern Recognit..

[35]  Jieping Ye,et al.  Learning incoherent sparse and low-rank patterns from multiple tasks , 2010 .