Instance selection and classification tree analysis for large spatial datasets in digital soil mapping

Geoderma

Volumn 146, Issue 1-2, 2008, Pages 138-146

  Schmidt, Karsten ^a   Behrens, Thorsten ^a   Scholten, Thomas ^a  

^a UNIVERSITY OF TÜBINGEN   (Germany)

Author keywords

Classification trees; Digital soil mapping; Grid learning; Instance selection; Pruning; Random sampling; Spatial data mining

Indexed keywords

ARSENIC COMPOUNDS; ARTIFICIAL INTELLIGENCE; CANNING; CONFORMAL MAPPING; DATA HANDLING; DECISION MAKING; DECISION THEORY; DECISION TREES; DIGITAL ARITHMETIC; EDUCATION; FORECASTING; LEARNING SYSTEMS; MAPS; SAMPLING;

CLASS PREDICTION; CLASSIFICATION-TREE ANALYSIS; COMPUTATIONAL COSTS; COMPUTATIONAL PROBLEMS; COVARIATES; DATA SETS; DIGITAL SOIL MAPPING; FREQUENCY DISTRIBUTIONS; GRID SEARCH (GS); GRID-SEARCH METHOD; HIGH-RESOLUTION DATASETS; INSTANCE SELECTION; LIMITED DATA; MACHINE-LEARNING; PARAMETER SETTINGS; PREDICTION ACCURACY; PREPROCESSING METHODS; SAMPLE SIZES; SAMPLING METHODS; SOIL CLASSES; SPATIAL DATASETS; STRATIFIED RANDOM SAMPLING; SURROUNDING AREA;

SOILS;

DATA MINING; DATA SET; DECISION MAKING; DIGITAL MAPPING; LEARNING; PREDICTION; SOIL CLASSIFICATION; SPATIAL RESOLUTION;

EID: 48349108755     PISSN: 00167061     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.geoderma.2008.05.010     Document Type: Article

References (68)

1. Behrens T., and Scholten T. Digital soil mapping in Germany-a review. Journal of Plant Nutrition and Soil Science 169 (2006) 434-443
2. Behrens T., and Scholten T. A comparison of data-mining techniques in predictive soil mapping. In: Lagacherie P., McBratney A.B., and Voltz M. (Eds). Digital Soil Mapping: An Introductory Perspective. Developments in Soil Science vol. 31 (2006), Elsevier, Amsterdam 353-364
3. Behrens T., Förster H., Scholten T., Steinrücken U., Spies E.-D., and Goldschmitt M. Digital soil mapping using artificial neural networks. Journal of Plant Nutrition and Soil Science 168 (2005) 21-33
4. Behrens, T., Schmidt, K., Scholten, T., in press. An approach to removing uncertainities in nominal environmental covariates and soil class maps. In: Hartemink, A.E., McBratney, A.B., Mendonça-Santos, M.L. (Eds.), Digital Soil Mapping with Limited Data. Springer, 440 pp.
5. Bergez J.E., Garcia F., and Lapasse L. A hierarchical partitioning method for optimizing irrigation strategies. Agriculture Systems 80 (2004) 235-253
6. Breiman L., Friedman J.H., Olshen R.A., and Stone C.J. Classification and Regression trees (1984), Wadsworth
7. Brighton H., and Mellish C. Advances in instance selection for instance-based learning algorithms. Data Mining and Knowledge Discovery 6 (2002) 153-172
8. Brus, D.J., 1993: Incorporating models of spatial variation in sampling strategies for soil. Doctoral thesis. Wageningen. Netherlands.
9. Brus D.J., and de Gruijter J.J. Random sampling or geostatistical modelling? Choosing between design-based and model-based sampling strategies for soil. Geoderma 80 (1997) 1-59
10. Bui E.N. Soil survey as a knowledge system. Geoderma 120 (2004) 17-26
11. Bui E.N., and Moran C.J. A strategy to fill gaps in soil survey over large spatial extents: an example from the Murray-Darlin basin of Australia. Geoderma 111 (2003) 21-44
12. Bui E.N., Loughhead A., and Corner R. Extracting soil-landscape rules from previous soil surveys. Australian Journal of Soil Research 37 (1999) 495-508
13. Burrough P.A., and McDonnell R.A. Principles of Geographical Information System. 2nd ed. (1998), Oxford University Press 356 pp.
14. Carre F., McBratney A.B., and Minasny B. Estimation and potential improvement of the quality of legacy soil samples for digital soil mapping. Geoderma 141 (2007) 1-14
15. Chen C., Liaw A., and Breiman L. Using random forest to learn imbalanced data. Technical Report vol. 666 (2004), Department of Statistics, University of California, Berkely
16. Cochran W.G. Sampling Techniques. 3rd ed. (1977), John Wiley & Sons 428 pp.
17. Debeir O., Latinne P., and van den Steen I. Remote sensing classification of spectral, spatial and contextual data using multiple classifier systems. Proccedings 8th ECS Image Analysis, Bordeaux (2001) 584-589
18. Domburg P., de Gruijter J.J., and van Beek P. Designing efficient soil survey schemes with a knowledge-based system using dynamic programming. Geoderma 75 (1997) 183-201
19. Ensor K.B., and Glynn P.W. Stochastic optimization via grid search. Mathematics of Stochastic Manufacturing Systems (1997), American Mathematical Society 399 pp.
20. Friedl M.A., and Brodley C.E. Decision tree classification of land cover from remotely sensed data. Remote Sensing Environment 61 (1997) 399-409
21. Friedman J.H. Multivariate adaptive regression splines (with discussion). Annals of Statistics 19/1 (1991) 1-82
22. Geissen V., Kampichler C., López-de Llergo-Juárez J.J., and Galindo-Acántara A. Superficial and subterranean soil erosion in Tabasco, tropical Mexico: development of a decision tree modeling approach. Geoderma 139 (2007) 277-287
23. Geng W., Cosman P., Berry C.C., Feng Z., and Schafer W.R. Automatic tracking, feature extraction and classification of C. elegans phenotypes. IEEE Transactions on Biomedical Engineering 10/51 (2004) 1811-1820
24. Giasson E., van Es C., van Wambeke A., and Bryant R.B. Assessing the economic value of soil information using decision analysis techniques. Soil Science 165/12 (2000) 971-978
25. Gilardi N., and Bengio S. Local machine learning models for spatial data analysis. Journal of Geographic Information and Decision Analysis 4/1 (2001) 11-28
26. Gómez-Chova L., Calpe J., Soria E., Camps-Valls G., Martin J.D., and Moreno J. Cart-based feature selection of hyperspectral images for crop cover classification. IEEE International Conference on Image Processing 3 (2003) 589-592
27. Gourieroux Ch., and Monfort A. Statsitcs and Econometric Models: General Concepts, Estimation, Prediction, and Algorithms (1995), Cambridge University Press, Cambridge 504 pp.
28. Grinand C., Arrouays D., Laroche B., and Martin M.P. Extrapolating regional soil landscapes from an existing soil map: sampling intensity, validation procedures, and integration of spatial context. Geoderma 143 (2008) 180-190
29. Gu B., Hu F., and Liu H. Sampling: knowing whole from its part. In: Liu H., and Motoda H. (Eds). Instance Selection and Construction for Data Mining (2001), Kluwer Academic Publishers, Boston 448 pp.
30. Hansen M., Dubayah R., and DeFries R. Classification trees: an alternative to traditional land cover classifiers. International Journal of Remote Sensing 17 (1996) 1075-1081
31. Hastie T., Tibshirani R., and Friedman J.H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2001), Springer, New York 533 pp.
32. He P., Fang K.T., and Xu C.-J. The classification tree combined with SIR and Ist application to classification of mass spectra. Journal of Data Science 1 (2003) 425-445
33. Hole F.D. An approach to landscape analysis with emphasis on soils. Geoderma 21/1 (1978) 1-23
34. Ishioka T. Evaluation of criteria for information retrieval. IEEE/WIC International Conference on Web Intelligence WI 2003, Sponsored by IEEE Computer Society and Web Intelligence Consortium, Halifax, Canada (2003) 425-431
35. IUSS Working Group. World reference base for soil resources 2006. World Soil Resources Reports No. 103. 2nd ed. (2006), FAO, Rome
36. Jenny H. Factors of Soil Formation: A System of Quantitative Pedology (1941), McGraw-Hill, New York 281 pp.
37. Jin Y. Multi-Objective Machine Learning (2006), Springer Verlag 660 pp.
38. John G.H., Kohavi R., and Pfleger K. Irrelevant features and the subset selection problem. Proceedings of the 11th International Conference on Machine Learning (1994) 121-129
39. Kim H., and Loh W.-Y. Classification trees with unbiased multiway splits. Journal of the American Statistical Association 96 (2001) 589-604
40. Kohonen T., Hynninen J., Kangas J., and Laaksonen J. The learning vector quantization program package; version 3.1. Online Puplication (1995). http://www.cis.hut.fi/research
41. Lagacherie P., and Holmes S. Addressing geographical data errors in a classification tree for soil unit prediction. International Journal of Geographical Information Science 11 (1997) 183-198
42. Lagacherie P., Robbez-Masson J.M., Nguyen-The N., and Barthes J.P. Mapping of reference area representativity using a mathematical soilscape distance. Geoderma 101 (2001) 105-118
43. Liu H., and Motoda H. Feature Selection for Knowledge Discovery and Data Mining (1998), Kluwer Academic Publishers, Boston 214 pp.
44. Liu H., and Motoda H. Data reduction via instance selection. In: Liu H., and Motoda H. (Eds). Instance Selection and Construction for Data mining (2001), Kluwer Academic Publishers, Boston 448 pp.
45. Liu H., and Motoda H. On issues of instance selection. Data Mining and Knowledge Discovery vol. 6 (2002), Kluwer Academic Publishers 115-130
46. Loh W.Y., and Shih Y.S. Split selection methods for classification trees. Statistica Sinica 7 (1997) 815-840
47. Loh W.Y., and Vanichsetakul N. Tree-structured classification via generalized discriminant analysis. Journal of the American Statistical Association 83 (1988) 715-728
48. Manning C.D., and Schütze H. Foundations of Statistical Natural Language Processing (1999), MIT Press Cambridge, London 620 pp.
49. McBratney A.B., Odeh I.O.A., Bishop T.F.A., Dunbar M.S., and Shatar T.M. An overview of pedometrics techniques for use in soil survey. Geoderma 97 (2000) 293-327
50. McBratney A.B., Mendonça Santos M.L., and Minasny B. On digital soil mapping. Geoderma 117 (2003) 3-52
51. McKenzie N.J., and Ryan P.J. Spatial prediction of soil properties using environmental correlation. Geoderma 89 (1999) 67-94
52. Mitchell T.M. Machine Learning. Singapore (1997) 414 pp.
53. Mitchie D., Spiegelhalter D.J., and Taylor C.C. Machine Learning, Neural and Statistical Classification (1994), Ellis Horwood, New York 298 pp.
54. Moran J.C., and Bui E.N. Spatial data mining for enhanced soil map modeling. International Journal of Geographical Information Science 16/6 (2002) 533-549
55. Munoz J., and Felicisimo A.M. Comparison of statistical methods commonly used in predictive modelling. Journal of Vegetation Science 15 (2004) 285-292
56. Pal N.R., and Jain L. Advanced Techniques in Knowledge Discovery and Data Mining (2005), Springer Verlag, London 264 pp.
57. Qi F. Knowledge discovery from area-class resource maps: data preprocessing for noise reduction. Transactions in GIS 8/3 (2004) 297-308
58. Qu P., and Loh W.Y. Application of Box-Cox transformations to discrimination for the two-class problem. Communications in Statistics. Theory and Methods 21 (1992) 2757-2774
59. Raghavan V., Bollmann P., and Jung G.S. A critical investigation of recall and precision as measures of retrieval system performance. ACM Transactions on Information Systems 7 (1989) 205-229
60. Schafer J. Analysis of Incomplete Multivariate Data (1997), Chapman & Hall, London 430 pp.
61. Scull P., Franklin J., and Chadwick O.A. The application of classification tree analysis to soil type prediction in a dessert landscape. Ecological Modelling 181 (2005) 1-15
62. Shrestha D.P., Zinck J.A., and Van Ranst E. Modelling land degradation in the Nepalese Himalaya. Catena (2004) 135-156
63. Van Rijsbergen C.J. Information Retrieval (1979), Butterworths 153 pp.
64. Wai L., Keung C.-K., and Ling C.X. Learning via prototype generation and filtering. In: Liu H., and Motoda H. (Eds). Instance Selection and Construction for Data Mining (2001), Kluwer Academic Publishers, Boston 448 pp.
65. Wilson D.L. Asymptotic properties of nearest neighbour rules using edited data. IEEE Transactions on Systems, Man, and Cybernetics 2 (1972) 408-420
66. Zhang J., Guo D., and Wan Q. Geospatial data mining and knowledge discovery using decision tree algorithm-a case study of soil data set of the Yellow River Delta.-Geoinformatics and Socioinformatics. Proceedings of Geoinformatics'99 Conference, Ann Arbor, Michigan (1999) 1-8
67. Zhou B., Zhang X., and Wang R. Automated soil resources mapping based on decision tree and Bayesian predictive modeling. Journal of Zhejiang University Science 5 (2004) 782-795
68. Zhu A.X. Mapping soil landscape as spatial continua: the neural network approach. Water Resources Research 36/3 (2000) 663-677