Predictive soil parent material mapping at a regional-scale: A Random Forest approach

Geoderma

Volumn 214-215, Issue , 2014, Pages 141-154

  Heung, Brandon ^a   Bulmer, Chuck E ^b   Schmidt, Margaret G ^a  

^a SIMON FRASER UNIVERSITY   (Canada)

^b BC Ministry of Forests Lands and Natural Resource Operations   (Canada)

Author keywords

Digital soil mapping; Environmental correlation; Knowledge discovery; Machine learning; Random forest; Soil parent material

Indexed keywords

BRITISH COLUMBIA; DIGITAL ELEVATION MODEL; DIGITAL SOIL MAPPINGS; ENVIRONMENTAL CORRELATIONS; PARENT MATERIALS; RANDOM FORESTS; TOPOGRAPHIC INDEX; VARIABLE REDUCTIONS;

DATA MINING; DECISION TREES; FORECASTING; FORESTRY; GEOMETRY; LEARNING SYSTEMS; OPTIMIZATION; SOIL SURVEYS; SOILS; SURVEYING;

MATERIALS;

CORRELATION; DATA MINING; DIGITAL ELEVATION MODEL; HIERARCHICAL SYSTEM; LEARNING; PREDICTION; SOIL SURVEY;

CORRELATION; DATA PROCESSING; DECISION MAKING; FORESTS; GEOMETRY; MAPPING; OPTIMIZATION; SOIL;

BRITISH COLUMBIA; CANADA;

EID: 84888203732     PISSN: 00167061     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.geoderma.2013.09.016     Document Type: Article

References (81)

1. Armstrong J.E. Surficial geology of Vancouver area, British Columbia. Paper 55-40, Geological Survey of Canada, Ottawa 1956.
2. Armstrong J.E. Surficial geology of New Westminster map-area, British Columbia. Paper 57-5 and Map 16 1957, Department of Mines and Technical Surveys, Ottawa.
3. B.C.Ministry of Sustainable Resource Management Gridded Digital Elevation Model Product Specifications 2002, Base Mapping and Geomatics Services Branch Ministry of Sustainable Resource Management, Victoria. 2nd edition.
4. Beckett P.H.T. The cost-effectiveness of soil survey. Outlook Agric. 1971, 6:191-198.
5. Beven K.J., Kirkby M.J. A physically based, variable contributing area model of basin hydrology. Hydrol. Sci. Bull. 1979, 24:43-69.
6. Böhner J., Köthe R., Conrad O., Gross J., Ringeler A., Selige T. Soil regionalization by means of terrain analysis and process parameterization. European Soil Bureau - Research Report 2002, 7:213-222.
7. Breiman L. Random forests. Mach. Learn. 2001, 45:5-32.
8. Breiman L., Friedman J., Stone C.J., Olshen R.A. Classification and Regression Trees 1984, CRC Press LLC, Boca Raton, FL.
9. Bui E.N. Soil survey as a knowledge system. Geoderma 2004, 120:17-26.
10. Bui E.N., Moran C.J. Disaggregation of polygons of surficial geology and soil maps using spatial modeling and legacy data. Geoderma 2001, 103:79-94.
11. Bui E.N., Moran C.J. A strategy to fill gaps in soil survey over large spatial extents: an example from the Murray-Darling basin of Australia. Geoderma 2003, 111:21-44.
12. Bui E.N., Lougheed A., Corner R. Extracting soil-landscape rules from previous soil surveys. Acad. J. Sci. Res. 1999, 37:495-508.
13. Bui E.N., Henderson B.L., Viergever K. Knowledge discovery from models of soil properties developed through data mining. Ecol. Model. 2006, 191:431-446.
14. Bui E.N., Henderson B.L., Viergever K. Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia. Glob. Biogeochem. Cycle 2009, 23:GB4033. 10.1029/2009GB003506.
15. Bureau A., Dupuis J., Hayward B., Falls K., Van Eerdewegh P. Mapping complex traits using Random Forest. BMC Genet. 2003, 4:S64.
16. Cutler R.D., Edwards T.C., Beard K.H., Cutler A., Hess K.T., Gibson J., Lawler J.J. Random forests for classification in ecology. Ecology 2007, 88:2783-2792.
17. Díaz-Uriarte R., Alvarez de Andrés S. Gene selection and classification of microarray data using random forest. BMC Bioinformatics 2006, 7:3-15.
18. Florinsky I.V. Accuracy of local topographic variables derived from digital elevation models. Int. J. Geogr. Inf. Sci. 1998, 12:47-61.
19. Galar M., Fernández A., Barrenechea E., Bustince H., Herrera F. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 2011, 42:463-484.
20. Gallant J.C., Dowling T.I. A multiresolution index of valley bottom flatness for mapping depositional areas. Water Resour. Res. 2003, 39:1347-1359.
21. Geng X., Fraser W., VandenBygaart B., Smith C.A.S., Wadell A., Jiao Y., Patterson G. Towards digital soil mapping in Canada: existing soil survey data and related expert knowledge. Digital Soil Mapping: Bridging Research, Environmental Application, and Operation 2010, 325-337. Springer.
22. Gislason P.O., Benediktsson J.A., Sveinsson J.R. Random forests for land cover classification. Pattern Recognit. Remote Sens. 2006, 27:294-300.
23. Grimm R., Behrens T., Märker M., Elsenbeer H. Soil organic carbon concentrations and stocks on Barro Colorado Island - digital soil mapping using random forests analysis. Geoderma 2008, 146:102-113.
24. Grinand C., Arrouays D., Laroche B., Martin M.P. Extrapolating regional soil landscapes from an existing soil map: sampling intensity, validation procedures, and integration of spatial context. Geoderma 2008, 143:180-190.
25. Häntzschel J., Goldberg V., Bernhofer C. GIS-based regionalization of radiation, temperature and coupling measures in complex terrain for low mountain ranges. Meteorol. Appl. 2005, 12:33-42.
26. Häring T., Dietz E., Osenstetter S., Koschitzki T., Schröder B. Spatial disaggregation of complex soil map units: a decision-tree based approach in Bavarian forest soils. Geoderma 2012, 185-186:37-47.
27. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2009, Springer, New York, NY, (734pp.). 2nd ed.
28. Hectares B.C. Hectares BC Available at, (verified 16 May 2012). http://hectaresbc.org/app/habc/HaBC.html.
29. Henderson B.L., Bui E.N., Moran C.J., Simon D.A.P. Australia-wide predictions of soil properties using decision trees. Geoderma 2005, 124:383-398.
30. Heung B., Bakker L., Schmidt M.G., Dragićević S. Modelling the dynamics of soil redistribution induced by sheet erosion using the Universal Soil Loss Equation and cellular automata. Geoderma 2013, 202-203:112-125.
31. Hole F.D., Campbell J.B. Soil Landscape Analysis 1985, Rowman and Allanheld, Totowa, NJ.
32. Howes D.E., Kenk E. Terrain Classification System for British Columbia, Version 2 1997, Resource Inventory Branch, Ministry of Environment, Lands and Parks, Victoria, BC.
33. Hua J., Xiong Z., Lowely J., Suh E., Dougherty E.R. Optimal number of features as a function of sample size for various classification rules. Bioinformatics 2005, 21:1509-1515.
34. Jenny H. Factors of Soil Formation: A System of Quantitative Pedology 1941, McGraw-Hill, NY.
35. Kenney E., Frank G. Creating a seamless soil dataset for the Okanagan Basin, British Columbia. Proceedings of the Western Regional Cooperative Soil Survey Conference, Las Vegas, NV. USDA-NRCS 2010, (ftp://ftp-fc.sc.egov.usda.gov/NSSC/NCSS/Conferences/regional/2010/west/kenney.pdf (verified 8 Nov 2012).
36. Koethe R., Lehmeier F. SARA-Systeme Zur Automatischen Relief-Analyse, Benutzerhandbuch 1996, 2. Goettingen University.
37. Kubat M., Matwin S. Addressing the curse of imbalanced training sets: one-sided selection. Proceedings of the 14th Annual International Conference on Machine Learning, Nashville, TN 1997, 179-186.
38. Lacoste M., Lemercier B., Walter C. Regional mapping of soil parent material by machine learning based on point data. Geomorphology 2011, 133:90-99.
39. Lawley R., Smith B. Digital soil mapping at a national scale: a knowledge and GIS based approach to improving parent material and property information. Digital Soil Mapping with Limited Data 2008, 173-182. Springer.
40. le Roux J.J., Newby T.S., Sumner P.D. Monitoring soil erosion in South Africa at a regional scale: review and recommendations. S. Afr. J. Sci. 2007, 103:329-335.
41. Lemercier B., Lacoste M., Loum M., Walter C. Extrapolation at regional scale of local soil knowledge using boosted classification trees: a two-step approach. Geoderma 2012, 171-172:75-84.
42. Li S., MacMillan R.A., Lobb D.A., McConkey B.G., Moulin A., Fraser W.R. Lidar DEM error analyses and topographic depression identification in a hummocky landscape in the prairie region of Canada. Geomorphology 2011, 129:263-275.
43. Liaw A., Wiener M. Classification and Regression by randomForest. R News 2002, 2:18-22.
44. Ließ M., Glaser B., Huwe B. Uncertainty in the spatial prediction of soil texture: comparison of regression tree and Random Forest models. Geoderma 2012, 170:70-79.
45. Lord T.M., Green A.J. Soils of the Tulameen Area of British Columbia. Report No. 13, British Columbia Soil Survey 1974, Research Branch, Canada Department of Agriculture, Ottawa, ON, Canada.
46. Luttmerding H.A. Soils of the Langley-Vancouver Map Area. Report No. 15, British Columbia Soil Survey 1981, BC Ministry of Environment, Kelowna, BC, Canada.
47. MacMillan R.A. A new approach to automated extraction and classification of repeating landform types. Frontiers in Pedometrics 2005, 54. Naples Florida, (http://www.conference.ifas.ufl.edu/pedometrics/Abstract%20Book.pdf (verified 8 Nov 2012)).
48. MacMillan R.A., Martin T.C., Earle T.J., McNabb D.H. Automated analysis and classification of landforms using high-resolution digital elevation data: applications and issues. Can. J. Remote. Sens. 2003, 29:592-606.
49. MacMillan R.A., Moon D.E., Coupé R.A. Automated predictive ecological mapping in a forest region of B.C., 2001-2005. Geoderma 2007, 140:353-373.
50. McBratney A.B., Mendoça Santos M.L., Minasny B. On digital soil mapping. Geoderma 2003, 117:3-52.
51. Moore I.D., Grayson R.B., Ladson A.R. Digital terrain modelling: a review of hydrological, geomorphological, and biological applications. Hydrol. Process. 1991, 5:3-30.
52. Moore I.D., Turner A.K., Wilson J.P., Jenson S.K., Band L.E. GIS and land-surface-subsurface process modeling. Environmental Modeling with GIS 1993, 196-230. Oxford University Press.
53. Moran C.J., Bui E.N. Spatial data mining for enhanced soil map modeling. Int. J. Geogr. Inf. Syst. 2002, 16:533-549.
54. Natural Resources Canada Canada's National Forest Inventory Photo Plot Guidelines, version. 1.1 2004, Canadian Forest Service, Pacific Forestry Centre, Victoria, BC.
55. Pojar J., Klinka K., Demarchi D. Ecosystems of British Columbia. Br. Columbia Minist. For. Ranges 1991, 95-111.
56. Prasad A.M., Iverson L.R., Liaw A. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 2006, 9:181-199.
57. Qi Y. Random forest for bioinformatics. Ensemble Machine Learning 2012, 307-323. Springer.
58. R Development Core Team R: A language and environment for statistical computing 2012, R Foundation for Statistical Computing, Vienna, Austria, (URL http://www.R-project.org.).
59. Resource Inventory Committee Standards for Terrestrial Ecosystem Mapping in British Columbia 1998, Ecosystem Working Group, Terrestrial Ecosystem Task Force, Resource Inventory Committee, Victoria, BC.
60. Riley S.J., DeGloria S.D., Elliot R. A terrain ruggedness index that quantifies topographic heterogeneity. Intermountain J. Sci. 1999, 5:23-27.
61. Saga Development Team System for Automated Geoscientific Analyses (SAGA) Available at, (verified 12 August, 2012). http://www.saga-gis.org/en/index.html.
62. Schut P., Smith S., Fraser W., Geng X., Kroetsch D. Soil Landscapes of Canada: building a national framework for environmental information. Geomatica 2011, 65:293-309.
63. Scull P., Franklin J., Chadwick O.A. The application of classification tree analysis to soil type prediction in a desert landscape. Ecol. Model. 2005, 181:1-15.
64. Sondheim M., Suttie K. User Manual for the British Columbia Soil Information System 1983, 1. BC Ministry of Forests Publication R28-82053, Victoria, BC.
65. Statnikov A., Wang L., Aliferis C.F. A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification. BMC Bioinformatics 2008, 9:319-329.
66. Svetnik V., Liaw A., Tong C., Culberson C., Sheridan R.P., Feuston B.P. Random Forest: a classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci. 2003, 43:1947-1958.
67. Svetnik V., Liaw A., Tong C., Wang T. Application of Breiman's Random Forest to modeling structure-activity relationships of pharmaceutical molecules. Lecture Notes in Computer Science 2004, vol. 3077:334-343. Springer, Berlin. F. Roli, J. Kittler, T. Windeatt (Eds.).
68. Valentine K.W.G., Sprout P.N., Baker T.E., Lavkulich L.M. The Soil Landscapes of British Columbia 1978, BC Ministry of Environment, Victoria, BC, Canada.
69. Van Hulse J., Khoshgoftaar T. Knowledge discovery from imbalanced and noisy data. Data Knowl. Eng. 2009, 68:1513-1542.
70. th Annual International Conference on Machine Learning (ICML 2007), Corvalis, OR 2007, 935-942.
71. Van Vliet J. Map Comparison Kit 3: User Manual 2003, Research Institute for Knowledge Systems, Maastricht.
72. Visser H., de Nijs T. The map comparison kit. Environ. Model. Software 2006, 21:346-358.
73. Weaver A. The distribution of soil erosion as a function of slope aspect and parent material in Ciskei, Southern Africa. Geojournal 1991, 23:29-34.
74. Webster R., Beckett P.H.T. Quality and usefulness of soil maps. Nature 1968, 219:680-682.
75. Webster R., Wong I.F.T. A numerical procedure for testing soil boundaries interpreted from air photographs. Photogrammetria 1969, 24:59-72.
76. Wiesmeier M., Barthold F., Blank B., Kögel-Knabner I. Digital mapping of soil organic matter stocks using random forest modeling in a semi-arid steppe ecosystem. Plant Soil 2011, 340:7-24.
77. Terrain Analysis: Principles and Applications 2000, John Wiley & Sons, New York, NY. J.P. Wilson, J.C. Gallant (Eds.).
78. Wittneben U. Soils of the Okanagan and SimilkameenValleys. Report No. 52, British Columbia Soil Survey 1986, Survey and Resource Mapping Branch, BC Ministry of Environment, Victoria, BC, Canada.
79. Xiong X., Grunwald S., Myers D.B., Kim J., Harris W.G., Comerford N.B. Which covariates are needed for soil carbon models in Florida. Digital Soil Assessment and Beyond 2012, 109-113. CRC Press.
80. Zevenbergen L.W., Thorne C.R. Quantitative analysis of land surface topography. Earth Surf. Proc. Land. 1987, 12:47-56.
81. Zhu A.X., Band L.E. A knowledge-based approach to data integration for soil mapping. Can. J. Remote. Sens. 1994, 20:408-418.