The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines

Geophysics

Volumn 78, Issue 3, 2013, Pages WB113-WB126

  Cracknell, Matthew J ^a   Reading, Anya M ^a  

^a UNIVERSITY OF TASMANIA   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION TREES; FORECASTING; GEOPHYSICS; LITHOLOGY; MACHINE LEARNING; SUPERVISED LEARNING; SUPPORT VECTOR MACHINES; UNCERTAINTY ANALYSIS; ALGORITHMS; ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS;

CLASS MEMBERSHIP PROBABILITIES; CLASSIFICATION ACCURACY; INDUCTIVE MACHINE LEARNING; MACHINE LEARNING APPROACHES; METAMORPHIC TERRAINS; PREDICTION UNCERTAINTY; SUPERVISED CLASSIFICATION; UNCERTAINTY MEASURES;

LEARNING ALGORITHMS;

ALGORITHM; CONTACT ZONE; DATA SET; FOREST; LITHOLOGY; SATELLITE DATA; TRANSITION ZONE; UNCERTAINTY ANALYSIS; CLASSIFICATION; COMPLEX TERRAIN; FOLDING; PATTERN RECOGNITION;

EID: 84888028156     PISSN: 00168033     EISSN: 19422156     Source Type: Journal    
DOI: 10.1190/GEO2012-0411.1     Document Type: Article

References (87)

1. Australian Geological Survey Organisation, 1994, Project 617, Broken Hill NSW 1994, Geoscience Australia.
2. National Aeronautics and Space Administration, 2000, Landsat ETM+ scene ELP096R082_7T20001010, L1G: U. S. Geological Survey.
3. Aster, R. C., B. Borchers, and C. H. Thurber, 2005, Parameter estimation and inverse problems: Elsevier International Geophysics Series.
4. Baddeley, A., and R. Turner, 2005, Spatstat: An R package for analyzing spatial point patterns: Journal of Statistical Software, 12, 1-42.
5. Bivand, R., and C. Rundel, 2012, rgeos: Interface to geometry engine - open source (GEOS), R package version 0.2-7, http://CRAN.R-project.org/package=rgeos.
6. Bivand, R. S., E. J. Pebesma, and V. Gomez-Rubio, 2008, Applied spatial data analysis with R: Springer.
7. Bodin, T., M. Sambridge, H. Tkalcic, P. Arroucau, K. Gallagher, and N. Rawlinson, 2012, Transdimensional inversion of receiver functions and surface wave dispersion: Journal of Geophysical Research Solid Earth: JGR, 117, B02301, doi: 10.1029/2011JB008560.
8. Breiman, L., 1996, Bagging predictors: Machine Learning, 24, no. 2, 123-140.
9. Breiman, L., 2001, Random forests: Machine Learning, 45, 5-32, doi: 10.1023/A:1010933404324.
10. Breiman, L., J. H. Friedman, R. A. Olshen, and C. J. Stone, 1984, Classification and regression trees: Wadsworths & Brooks/Cole Statistics/Probability Series.
11. Brown, D. G., 1998, Classification and boundary vagueness in mapping presettlement forest types: International Journal of Geographical Information Science, 12, 105-129, doi: 10.1080/136588198241914.
12. Buckley, P. M., T. Moriarty, and J. Needham, 2002, Broken Hill geoscience database: Geological Survey of New South Wales.
13. Burl, M. C., L. Asker, P. Smyth, U. Fayyad, P. Perona, L. Crumpler, and J. Aubele, 1998, Learning to recognize volcanoes on Venus: Machine Learning, 30, 165-194, doi: 10.1023/A:1007400206189.
14. Buselli, G., and K. L. Lu, 2001, Groundwater contamination monitoring with multichannel electrical and electromagnetic methods: Journal of Applied Geophysics, 48, 11-23, doi: 10.1016/S0926-9851(01)00055-6.
15. Ceamanos, X., B. Waske, J. Benediktsson, J. Chanussot, and J. Sveinsson, 2009, Ensemble strategies for classifying hyperspectral remote sensing data, in Proceedings of the 8th International Workshop on Multiple Classifier Systems: Springer-Verlag, 62-71.
16. Congalton, R. G., and K. Green, 1998, Assessing the accuracy of remotely sensed data: Principles and practices: Lewis Publications.
17. Denison, D. G. T., C. C. Holmes, B. K. Mallick, and A. F. M. Smith, 2002, Baysian methods for nonlinear classification and regression: John Wiley and Sons Ltd.
18. Draskovits, P., and V. Laszlo, 2005, Indication of groundwater contamination with the induced-polarization (IP) method, in D. K. Butler, ed., Near-surface geophysics: SEG Investigations in Geophysics 13, 551-562.
19. Duro, D. C., S. E. Franklin, and M. G. Dubé, 2012, A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery: Remote Sensing of Environment, 118, 259-272, doi: 10.1016/j.rse.2011.11.020.
20. Emery, X., and K. E. Gonzalez, 2007, Incorporating the uncertainty in geological boundaries into mineral resources evaluation: Journal of the Geological Society of India, 69, 29-38.
21. Eun-Jung, H., M. Dentith, and P. Kovesi, 2008, Towards the automated analysis of regional aeromagnetic data to identify regions prospective for gold deposits: Computers & Geosciences, 34, 1505-1513, doi: 10.1016/j.cageo.2007.08.007.
22. Fisher, P. F., 1999, Models of uncertainty in spatial data, in P. Longley, M. Goodchild, D. Maguire, and D. Rhind, eds., Geographical information systems: Principles, techniques, applications and management: Wiley and Sons, 191-205.
23. Foody, G. M., and A. Mathur, 2004, A relative evaluation of multiclass image classification by support vector machines: IEEE Transactions on Geoscience and Remote Sensing, 42, 1335-1343, doi: 10.1109/TGRS.2004.827257.
24. Gahegan, M., 2000, On the application of inductive machine learning tools to geographical analysis: Geographical Analysis, 32, 113-139.
25. Glasziou, P., and J. Hilden, 1989, Test selection measures: Medical Decision Making, 9, 133-141.
26. Goodchild, M. F., L. Chih-Chang, and Y. Leung, 1994, Visualizing fuzzy maps, in H. M. Hearnshaw, and D. J. Unwin, eds., Visualization in GIS: Wiley, 158-167.
27. Goodchild, M. F., and D. A. Quattrochi, 1997, Scale, multiscaling, remote sensing and GIS, in D. A. Quattrochi, and M. F. Goodchild, eds., Scale in remote sensing and GIS: Lewis Publishers, 1-12.
28. Goodchild, M. F., G. Q. Sun, and Y. Shiren, 1992, Development and test of an error model for categorical data: International Journal of Geographical Information Systems, 6, 87-103, doi: 10.1080/02693799208901898.
29. Gotway, C. A., and L. J. Young, 2002, Combining incompatible spatial data: Journal of the American Statistical Association, 97, no. 458, 632-648, doi: 10.1198/016214502760047140.
30. Ham, J., C. Yangchi, M. M. Crawford, and J. Ghosh, 2005, Investigation of the random forest framework for classification of hyperspectral data: IEEE Transactions on Geoscience and Remote Sensing, 43, 492-501, doi: 10.1109/TGRS.2004.842481.
31. Hammer, B., and T. Villmann, 2007, How to process uncertainty in machine learning?, in Proceedings of the European Symposium on Artificial Neural Networks, d-side publications, 79-90.
32. Hastie, T., R. Tibshirani, and J. H. Friedman, 2009, The elements of statistical learning: Data mining, inference and prediction: Springer Series in Statistics.
33. Hijmans, R. J., and J. van Etten, 2012, raster: Geographic analysis and modeling with raster data, R package version 2.0-12, http://CRAN.R-project.org/package=raster.
34. Hsu, C.-W., C.-C. Chang, and C.-J. Lin, 2010, A practical guide to support vector classification, Department of Computer Science, National Taiwan University, 16.
35. Hsu, C.-W., and C.-J. Lin, 2002, A comparison of methods for multiclass support vector machines: IEEE Transactions on Neural Networks, 13, no. 2, 415-425.
36. Jackson, J., 2005, The use of sub-audio magnetics (SAM) in gold exploration- Examples from the Yilgarn Craton, WA: Exploration Geophysics, 36, 163-169, doi: 10.1071/EG05163.
37. Joshi, A. J., F. Porikli, and N. Papanikolopoulos, 2009, Multi-class active learning for image classification: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2372-2379.
38. Kanevski, M., A. Pozdnoukhov, and V. Timonin, 2009, Machine learning for spatial environmental data: Theory, applications and software: CRC Press.
39. Karatzoglou, A., D. Meyer, and K. Hornik, 2006, Support vector machines in R: Journal of Statistical Software, 15, 28.
40. Karatzoglou, A., A. Smola, K. Hornik, and A. Zeileis, 2004, kernlab - An S4 package for kernel methods in R: Journal of Statistical Software, 11, 1-20.
41. Keitt, T. H., R. Bivand, E. J. Pebesma, and B. Rowlingson, 2012, rgdal: Bindings for the geospatial data abstraction library, R package version 0.7-8, http://CRAN.R-project.org/package=rgdal.
42. Kohavi, R., 1995, A study of cross-validation and bootstrap for accuracy estimation and model selection: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, 2, 1137-1143.
43. Kohavi, R., and D. H. Wolpert, 1996, Bias plus variance decomposition for zero-one loss functions, in Proceedings machine learning: Proceedings of the Thirteenth International Machine Learning Conference, Morgan Kaufmann, 275-283.
44. Kotsiantis, S. B., 2007, Supervised machine learning: A review of classification techniques: Informatica, 31, 249-268.
45. Kovacevic, M., B. Bajat, and B. Gajic, 2010, Soil type classification and estimation of soil properties using support vector machines: Geoderma, 154, nos. 3-4, 340-347, doi: 10.1016/j.geoderma.2009.11.005.
46. Kovacevic, M., B. Bajat, B. Trivic, and R. Pavlovic, 2009, Geological units classification of multispectral images by using support vector machines: Proceeding of the IEEE International Conference on Intelligent Networking and Collaborative Systems, 267-272.
47. Kuhn, M., J. Wing, S. Weston, A. Williams, C. Keefer, and A. Engelhardt, 2012, caret: Classifcation and regression training, R package version 5.15-023, http://CRAN.R-project.org/package=caret.
48. Kusky, T. M., and T. M. Ramadan, 2002, Structural controls on Neoproterozoic mineralization in the south eastern desert, Egypt: An integrated field, Landsat TM, and SIR-C/X SAR approach: Journal of African Earth Sciences, 35, no. 1, 107-121.
49. Lewin-Koh, J. N., R. Bivand, E. J. Pebesma, E. Archer, A. Baddeley, H.-J. Bibiko, S. Dray, D. Forrest, M. Friendly, P. Giraudoux, D. Golicher, V. G. R. P. Hausmann, K. O. Hufthammer, T. Jagger, S. P. Luque, D. MacQueen, A. Niccolai, T. Short, B. Stabler, and R. Turner, 2012, maptools: Tools for reading and handling spatial objects, R package version 0.8-16, http://CRAN.R-project.org/package=maptools.
50. Liaw, A., and M. Wiener, 2002, Classification and regression by random- Forest: R News, 2, 18-22.
51. Malinverno, A., 2002, Parsimonious Bayesian Markov chain Monte Carlo inversion in a nonlinear geophysical problem: Geophysical Journal International, 151, 675-688, doi: 10.1046/j.1365-246X.2002.01847.x.
52. Marsland, S., 2009, Machine learning: An algorithmic perspective: Chapman & Hall/CRC.
53. Metelka, V., L. Baratoux, S. Naba, and M.W. Jessell, 2011, A geophysically constrained litho-structural analysis of the eburnean greenstone belts and associated granitoid domains, Burkina Faso, West Africa: Precambrian Research, 190, nos. 1-4, 48-69, doi: 10.1016/j.precamres.2011.08.002.
54. Mosegaard, K., and A. Tarantola, 1995, Monte Carlo sampling of solutions to inverse problems: Journal of Geophysical Research, 100, 12431-12431, doi: 10.1029/94JB03097.
55. Oommen, T., D. Misra, N. K. C. Twarakavi, A. Prakash, B. Sahoo, and S. Bandopadhyay, 2008, An objective analysis of support vector machine based classification for remote sensing: Mathematical Geosciences, 40, 409-424, doi: 10.1007/s11004-008-9156-6.
56. Page, R. W., C. H. H. Conor, B. P. J. Stevens, G. M. Gibson, W. V. Preiss, and P. N. Southgate, 2005a, Correlation of Olary and Broken Hill Domains, Curnamona Province: Possible relationship to Mount Isa and other North Australian Pb-Zn-Ag-bearing successions: Economic Geology, 100, 663-676.
57. Page, R. W., B. P. J. Stevens, and G. M. Gibson, 2005b, Geochronology of the sequence hosting the Broken Hill Pb-Zn-Ag orebody, Australia: Economic Geology, 100, 633-661.
58. Pal, M., 2005, Random forest classifier for remote sensing classification: International Journal of Remote Sensing, 26, 217-222, doi: 10.1080/01431160412331269698.
59. Pebesma, E. J., and R. S. Bivand, 2005, Classes and methods for spatial data in R: R News, 5, 9-13.
60. Price, D., S. Knerr, L. Personnaz, and G. Dreyfus, 1995, Pairwise neural network classifiers with probabilistic outputs, in G. Tesauro, D. Touretzky, and T. Leen, eds., Neural information processing systems: The MIT Press, 7, 1109-1116.
61. Provost, F., and T. Fawcett, 1997, Analysis and visualization of classifier performance: Comparison under imprecise class and cost distributions: Proceedings of the Third International Conference on Knowledge Discovery and Data Mining, American Association for Artificial Intelligence, 43-48.
62. Ramli, M. F., N. Yusof, M. K. Yusoff, H. Juahir, and H. Z. M. Shafri, 2010, Lineament mapping and its application in landslide hazard assessment: A review: Bulletin of Engineering Geology and the Environment, 69, 215-233, doi: 10.1007/s10064-009-0255-5.
63. Sabatakakis, N., G. Koukis, E. Vassiliades, and S. Lainas, 2012, Landslide susceptibility zonation in Greece: Natural Hazards, 1-21.
64. Sambridge, M., 1999a, Geophysical inversion with a neighbourhood algorithm - I. Searching a parameter space: Geophysical Journal International, 138, 479-494, doi: 10.1046/j.1365-246X.1999.00876.x.
65. Sambridge, M., 1999b, Geophysical inversion with a neighbourhood algorithm - II. Appraising the ensemble: Geophysical Journal International, 138, 727-746, doi: 10.1046/j.1365-246x.1999.00900.x.
66. Scales, A. J., and R. Snieder, 1998, What is noise?: Geophysics, 63, 1122-1124, doi: 10.1190/1.1444411.
67. Sen, M. K., and P. L. Stoffa, 1992, Rapid sampling of model space using genetic algorithms - Examples from seismic waveform inversion: Geophysical Journal International, 108, 281-292, doi: 10.1111/j.1365-246X.1992.tb00857.x.
68. Slavinski, H., B. Morris, H. Ugalde, B. Spicer, T. Skulski, and N. Rogers, 2010, Integration of lithological, geophysical, and remote sensing information: A basis for remote predictive geological mapping of the Baie Verte Peninsula, Newfoundland: Canadian Journal of Remote Sensing, 36, 99-118, doi: 10.5589/m10-031.
69. Spencer, C., and D. Gubbins, 1980, Travel-time inversion for simultaneous earthquake location and velocity structure determination in laterally varying media: Geophysical Journal of the Royal Astronomical Society, 63, 95-116, doi: 10.1111/gji.1980.63.issue-1.
70. Stevens, B. P. J., 1986, Post-depositional history of the Willyama Supergroup in the Broken Hill Block, NSW: Australian Journal of Earth Sciences, 33, 73-98.
71. Stevens, B. P. J., I. L. Willis, R. E. Brown, andW. J. Stroud, 1983, The Early Proterozoic Willyama Supergroup: Definitions of stratigraphic units from the Broken Hill Block, New SouthWales: Records of the Geological Survey of New South Wales, 21, 407-442.
72. Stumpf, A., and N. Kerle, 2011, Object-oriented mapping of landslides using Random forests: Remote Sensing of Environment, 115, 2564-2577, doi: 10.1016/j.rse.2011.05.013.
73. Tangestani, M. H., 2004, Landslide susceptibility mapping using the fuzzy gamma approach in a GIS, Kakan catchment area, southwest Iran: Australian Journal of Earth Sciences, 51, 439-450.
74. Taye, W., 2011, Lithology boundary detection using multi-sensor remote sensing imagery for geological interpretation: M.S. Thesis, University of Twente.
75. van der Wel, F. J. M., L. C. van der Gaag, and B. G. H. Gorte, 1998, Visual exploration of uncertainty in remote-sensing classification: Computers & Geosciences, 24, 335-343, doi: 10.1016/S0098-3004(97)00120-9.
76. Vapnik, V. N., 1995, The nature of statistical learning theory: Springer- Verlag New York, Inc.
77. Vapnik, V. N., 1998, Statistical learning theory: John Wiley & Sons, Inc.
78. Waske, B., J. A. Benediktsson, K. Árnason, and J. R. Sveinsson, 2009, Mapping of hyperspectral AVIRIS data using machine learning algorithms: Canadian Journal of Remote Sensing, 35, S106-S116, doi: 10.5589/m09-018.
79. Waske, B., and M. Braun, 2009, Classifier ensembles for land cover mapping using multitemporal SAR imagery: ISPRS Journal of Photogrammetry and Remote Sensing, 64, 450-457, doi: 10.1016/j.isprsjprs.2009.01.003.
80. Waske, B., S. Van Der Linden, J. A. Benediktsson, A. Rabe, and P. Hostert, 2010, Sensitivity of support vector machines to random feature selection in classification of hyperspectral data: IEEE Transactions on Geoscience and Remote Sensing, 48, 2880-2889, doi: 10.1109/TGRS.2010.2041784.
81. Webster, A. E., 2004, The structural evolution of the Broken Hill Pb-Zn-Ag deposit, New South Wales, Australia: PhD Thesis, University of Tasmania.
82. Williams, D., 2009, Landsat 7 science data user's handbook: National Aeronautics and Space Administration (NASA).
83. Willis, I. L., R. E. Brown, W. J. Stroud, and B. P. J. Stevens, 1983, The early ProterozoicWillyama Supergroup: Stratigraphic subdivision and interpretation of high to low-grade metamorphic rocks in the Broken Hill Block, New South Wales: Journal of the Geological Society of Australia, 30, nos. 1-2, 195-224.
84. Witten, I. H., and E. Frank, 2005, Data mining: Practical machine learning tools and techniques: Elsevier/Morgan Kaufman, Morgan Kaufmann series in data management systems.
85. Wu, T.-F., C.-J. Lin, and R. C. Weng, 2004, Probability estimates for multiclass classification by pairwise coupling: Journal of Machine Learning Research, 5, 975-1005.
86. Ya, X., L. Xuejun, L. Carin, and B. Krishnapuram, 2007, Multi-task learning for classification with Dirichlet process priors: Journal of Machine Learning Research, 8, 35-63.
87. Zhu, A. X., 1997, Measuring uncertainty in class assignment for natural resource maps under fuzzy logic: Photogrammetric Engineering and Remote Sensing, 63, 1195-1202.