APPLICATION OF SUPPORT VECTOR MACHINES IN COAL DEPOSIT BOUNDARY DECISION

  • G Ertunç Hacettepe University, Beytepe, 06800, Ankara
  • F Atalay Hacettepe University, Beytepe, 06800, Ankara

Abstract

In order to make an accurate assessment of the tonnage and coal quality in coal mining, the boundaries of the coal deposits should clearly be defined. Uncertainty in determining the boundary should be taken into account while it has a vital role in geostatistical estimation and mine planning. In general, this uncertainty is evaluated by calculating probability of presence of coal at the given locations where data is not available. Indicator kriging which is non-linear spatial interpolation technique can be used in estimation of local uncertainty by the process of derivation of a local cumulative distribution function (cdf). Despite the simple theoretical basis for this method, there are limitations of indicator kriging such as variogram modelling which requires good command on geostatistics, order relations of results and their correction. In this study, support vector machines (SVM) are introduced as an alternative approach to indicator kriging estimation for defining the coal deposit boundary. The data in the field is converted into binary data and grid of unknown locations is estimated by the Gaussian Radial Basis Function kernel based classification SVM code which is implemented by the authors. The theoretical and practical bases for considerations and limitations of indicator kriging is discussed, along with proposed alternative through a case study. 

References

[1] Cressie, N.A.C., Statistics for Spatial Data. 1991: J. Wiley.

[2] Deutsch, C.V.A.G.J., GSLIB - Geostatistical Software Library and User's Guide. 1998: Oxford University Press.

[3] Goovaerts, P., Geostatistics for natural resources evaluation. Applied geostatistics series. 1997, New York: Oxford University Press. xiv, 483 p.

[4] Journel, A.G., Nonparametric estimation of spatial distributions. Journal of the International Association for Mathematical Geology, 1983. 15(3): p. 445-468.

[5] Tolosana-Delgado, R., V. Pawlowsky-Glahn, and J.-J. Egozcue, Indicator Kriging without Order Relation Violations. Mathematical Geosciences, 2008. 40(3): p. 327-347

[6] Kecman, V., Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. 2001: MIT Press. 608.

[7] Vapnik, V.N., The nature of statistical learning theory. 1995: Springer-Verlag New York, Inc. 188.

[8] Burges, C.J.C., A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 1998. 2(2): p. 121-167.
[9] Vapnik, V., Statistical learning theory 1998: Wiley.

[10] Kanevski, M., et al., Support Vector Machines for Classification and Mapping of Reservoir Data, in Soft Computing for Reservoir Characterization and Modeling, P. Wong, F. Aminzadeh, and M. Nikravesh, Editors. 2002, Physica-Verlag HD: Heidelberg. p. 531-558.

[11] Kanevski, M., Spatial Predictions of Soil Contamination Using General Regression Neural Networks. Int. Journal of Systems Research and Information Systems, 1999. 8(4): p. 15.

[12] Kanevski, M., Pozdnukhov, A., Canu, S. and Maignan, M. , Advanced Spatial Data Analysis and Modelling with Support Vector Machines. 2000a, IDIAP Research Report.

[13] Kanevski, M., Canu, S., Spatial Data Mapping with Support Vector Regression and Geostatistics. 2000b, IDIAP Research Report.

[14] Tartakovsky, D.M. and B.E. Wohlberg, Delineation of geologic facies with statistical learning theory. Geophysical Research Letters, 2004. 31(18): p. n/a-n/a.

[15] Pozdnoukhov, A. and M. Kanevski, Monitoring network optimisation for spatial data classification using support vector machines. International Journal of Environment and Pollution, 2006. 28(3-4): p. 465-484.

[16] Bahria, S., N. Essoussi, and M. Limam, Hyperspectral data classification using geostatistics and support vector machines. Remote Sensing Letters, 2011. 2(2): p. 99-106.

[17] Isaaks, E.H. and R.M. Srivastava, Applied Geostatistics. 1989: Oxford University Press.

[18] Chilès, J.P. and P. Delfiner, Geostatistics: modeling spatial uncertainty. 1999: Wiley.

[19] Armstrong, M., Basic Linear Geostatistics. 1998: Springer Berlin Heidelberg.
[20] 20. Cortes, C. and V. Vapnik, Support-Vector Networks. Machine Learning, 1995. 20(3): p. 273-297.
[21] 21. Platt, J.C., Fast training of support vector machines using sequential minimal optimization, in Advances in kernel methods, S. Bernhard, et al., Editors. 1999, MIT Press. p. 185-208.
Published
2017-09-16
How to Cite
ERTUNÇ, G; ATALAY, F. APPLICATION OF SUPPORT VECTOR MACHINES IN COAL DEPOSIT BOUNDARY DECISION. International Journal of Scientific Research in Information Systems and Engineering (IJSRISE), [S.l.], v. 3, n. 2, p. 5-10, sep. 2017. ISSN 2380-5579. Available at: <http://ijsrise.com/index.php/IJSRISE/article/view/82>. Date accessed: 21 nov. 2017.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.