Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit

ZHANG Xunan; SONG Shiji; LI Jiabiao; WU Cheng

doi:10.1007/s13131-013-0337-x

Article Contents

Article Navigation > Acta Oceanologica Sinica > 2013 > 32(8): 16-25

ZHANG Xunan, SONG Shiji, LI Jiabiao, WU Cheng. Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit[J]. Acta Oceanologica Sinica, 2013, 32(8): 16-25. doi: 10.1007/s13131-013-0337-x

Citation:

ZHANG Xunan, SONG Shiji, LI Jiabiao, WU Cheng. Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit[J]. Acta Oceanologica Sinica, 2013, 32(8): 16-25. doi: 10.1007/s13131-013-0337-x

Citation:

PDF( 1174 KB)

Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit

doi: 10.1007/s13131-013-0337-x

1.
Department of Automation, Tsinghua University, Beijing 100084, China
2.
Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China

Received Date: 2012-02-21
Rev Recd Date: 2012-12-24

Abstract

Abstract

Due to the geological complexities of ore body formation and limited borehole sampling, this paper proposes a robust weighted least square support vectormachine (LS-SVM) regression model to solve the ore grade estimation for a seafloor hydrothermal sulphide deposit in Solwara 1, which consists of a large proportion of incomplete samples without ore types and grade values. The standard LS-SVM classification model is applied to identify the ore type for each in complete sample. Then, a weighted K-nearest neighbor (WKNN) algorithm is proposed to interpolate the missing values. Prior to modeling, the particle swarm optimization (PSO) algorithm is used to obtain an appropriate splitting for the training and test data sets so as to eliminate the large discrepancies caused by randomdivision. Coupled simulated annealing (CSA) and grid search using 10-fold cross validation techniques are adopted to determine the optimal tuning parameters in the LS-SVM models. The effectiveness of the proposed model by comparing with other well-known techniques such as inverse distance weight (IDW), ordinary kriging (OK), and back propagation (BP) neural network is demonstrated. The experimental results show that the robust weighted LS-SVM outperforms the othermethods, and has strong predictive and generalization ability.
- weighted LS-SVM,
- grade estimation,
- incomplete samples,
- data division

FullText(HTML)

References(23)

References

Chatterjee S, Bandopadhyay S, Rai P. 2008. Genetic algorithm-based neural network learning parameter selection for ore grade evaluation of limestone deposit. Mining Technology, 117(4): 178-190

Garcia-Laencina P J, Sancho-Gomez J L, Figueiras-Vidal A R. 2010.Pattern classification with missing data: a review. Neural Computing & Applications, 19(2): 263-282

Gencoglu M T, Uyar M. 2009. Prediction of flashover voltage of insulators using least squares support vector machines. Expert Systems with Applications, 36(7): 10789-10798

Herzig P M, Hannington M D. 1995. Polymetallic massive sulfides at themodern seafloor: a review. Ore Geology Reviews, 10: 95-115

Huang W B. 2011. Using tuned LS-SVR to derive normal height from GPS height. Proceedings of the 2011 IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM2011). NJ, USA: Piscataway, 511-514

Jerez J M, Molina I, Garcia-Laencina P J, et al. 2010. Missing data imputation using statistical andmachine learningmethods in a real breast cancer problem. Artificial Intelligence in Medicine, 50(2): 105-115

Kanevski M, Pozdnoukhov A, Timonin V. 2009. Machine learning for spatial environmental data theory, application and software. Lausanne, Switzerland: EPFL Press

Kennedy J E, Eberhart R C. 1995. Particle swarm optimization. Proceedings of IEEE International Conference on Neural Networks. NJ, USA: Piscataway, 1942-1948

Kennedy J E, Eberhart R C. 1997. A discrete binary version of the particle swarm optimization. IEEE International Conference on Systems, Man, and Cybernetics, 5: 4104-4105

Little R J A, Rubin D B. 2002. Statistical Analysis with Missing Data. Hoboken, New Jersey: JohnWiley & Sons Inc

Lipton I. 2008. Mineral resource estimate Solwara 1 project Bismarck Sea Papua New Guinea for Nautilus Minerals Inc, Canadian NI43-101 form F1. http://www.nautilusminerals.com/i/pdf /2008-02-01?Solwara1?43-101.pdf/2008-02-01/2011-06-15

Mahmoudabadi H, Izadi M, Menhaj M B. 2009. A hybrid method for grade estimation using genetic algorithm and neural networks. Computational Geosciences, 13(1): 91-101

Samanta B. 2010. Radial basis function network for ore grade estimation. Natural Resources Research, 19(2): 91-102

Samanta B, Bandopadhyay S. 2009. Construction of a radial basis function network using an evolutionary algorithm for grade estimation in a placer gold deposit. Computers & Geosciences, 35(8): 1592-1602

Samanta B, Bandopadhyay S, Ganguli R, et al. 2002. Data segmentation and genetic algorithms for sparse data division in nome placer gold grade estimation using neural network and geostatistics. Mining Explor Geol, 11(1-4): 69-76

Suykens J A K, De Brabanter J, Lukas L, et al. 2002. Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing, Special issue on fundamental and information processing aspects of neurocomputing, 48(1- 4): 85-105

Suykens J A K, Lukas L, Van Dooren P, et al. 1999. Least squares support vector machine classifiers: a large scale algorithm. Proc European Conf on Circuit Theroy and Design (ECCTD'99). Torino, Italy: Politecnico di Torino, 839-842

Suykens J A K, Lukas L, Vandewalle J. 2000. Sparse approximation using least squares support vector machines. IEEE International Symposium on Circuits and Systems ISCAS'2000. Lausanne, Switzerland: Presses Polytechniques et Universitaires Romandes, 757-760

Suykens J A K, Vandewalle J. 1999. Least squares support vector machine classifiers. Neural Processing Letters, 9(3): 293-300

Van Gestel T, Suykens J A K, Baesens B, et al. 2004. Benchmarking least squares support vector machine classifiers. Machine Learning, 54(1): 5-32

Van Gestel T, Suykens J A K, Lanckriet G, et al. 2002. Multiclass LSSVMs: moderated outputs and coding-decoding schemes. Neural Processing Letters, 15(1): 45-58

Vapnik V N. 1998. Statistical Learning Theory. New York: John Wiley Xavier de Souza S, Suykens J A K. 2010. Coupled simulated annealing. IEEE transactions on Systems, Man, and Cybernetics, Part B, 40(2): 320-335

Yama B R, Lineberry G T. 1999. Artificial neural network application for a predictive task inmining. Mining Eng, 51(2): 59-64

Relative Articles

Supplements(0)

Cited By

Proportional views