Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem

Ecological Indicators

Volumn 60, Issue , 2016, Pages 870-878

  Yang, Ren Min ^a,b   Zhang, Gan Lin ^a,b   Liu, Feng ^a   Lu, Yuan Yuan ^a,b   Yang, Fan ^a,b   Yang, Fei ^a,b   Yang, Min ^a,b   Zhao, Yu Guo ^a   Li, De Cheng ^a  

^a INSTITUTE OF GEOLOGY AND GEOPHYSICS   (China)

^b UNIVERSITY OF CHINESE ACADEMY OF SCIENCES   (China)

Author keywords

Boosted regression tree; Digital soil mapping; Environmental variables; Random forest; Soil organic carbon; Tibetan Plateau

Indexed keywords

DECISION TREES; FORESTRY; MAPPING; ORGANIC CARBON; REGRESSION ANALYSIS; REMOTE SENSING; SOIL SURVEYS; SOILS; SPATIAL DISTRIBUTION; VEGETATION;

BOOSTED REGRESSION TREES; DIGITAL SOIL MAPPINGS; ENVIRONMENTAL VARIABLES; RANDOM FORESTS; SOIL ORGANIC CARBON; TIBETAN PLATEAU;

CLIMATE MODELS;

ALPINE ENVIRONMENT; COMPARATIVE STUDY; CONCENTRATION (COMPOSITION); DIGITAL MAPPING; ECOLOGICAL MODELING; ENVIRONMENTAL FACTOR; MODEL VALIDATION; REGRESSION ANALYSIS; SOIL ANALYSIS; SOIL CARBON; SOIL MANAGEMENT; SPATIAL DISTRIBUTION; TOPSOIL;

CLIMATES; ECOSYSTEMS; FORESTS; MAPPING; REGRESSION ANALYSIS;

CHINA; QINGHAI-XIZANG PLATEAU;

EID: 84941312435     PISSN: 1470160X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ecolind.2015.08.036     Document Type: Article

References (65)

1. D. Arrouays, I. Vion, and J.L. Kicin Spatial analysis and modeling of topsoil carbon storage in temperate forest humic loamy soils of France Soil Sci. 159 1995 191 198
2. N.H. Batjes Total carbon and nitrogen in the soils of the world Eur. J. Soil Sci. 47 1996 151 163
3. P.H. Bellamy, P.J. Loveland, R.I. Bradley, R.M. Lark, and G.J. Kirk Carbon losses from all soils across England and Wales 1978-2003 Nature 437 2005 245 248
4. J. Boehner, R. Koethe, O. Conrad, J. Gross, A. Ringeler, and T. Selige Soil regionalisation by means of terrain analysis and process parameterisation E. Micheli, F. Nachtergaele, L. Montanarella, Soil Classification 2001. Research Report No. 7, EUR 20398 EN 2002 European Soil Bureau Luxembourg 213 222
5. H.L. Bohn Estimate of organic carbon in world soils: II Soil Sci. Soc. Am. J. 46 1982 1118 1119
6. R.A. Bowman, J.D. Reeder, and B.J. Wienhold Quantifying laboratory and field variability to assess potential for carbon sequestration Commun. Soil Sci. Plant Anal. 33 2002 1629 1642
7. L. Breiman Random forests Mach. Learn. 45 2001 5 32
8. E. Bui, B. Henderson, and K. Viergever Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia Global Biogeochem. Cycl. 23 2009 GB4033
9. D.C. Carslaw, and P.J. Taylor Analysis of air pollution data at a mixed source location using boosted regression trees Atmos. Environ. 43 2009 3563 3570
10. T.L. Coleman, P.A. Agbu, and O.L. Montgomery Spectral differentiation of surface soils and soil properties - is it possible from space platforms Soil Sci. 155 1993 283 293
11. Cooperative Research Group on Chinese Soil Taxonomy Keys to Chinese Soil Taxonomy 2001 Press of University of Science and Technology of China Hefei, China (in Chinese)
12. Data Center of the Heihe Project Landsat TM Mosaic Image of the Heihe River Basin in 2010 2011 http://westdc.westgis.ac.cn
13. E.A. Davidson, and I.A. Janssens Temperature sensitivity of soil carbon decomposition and feedbacks to climate change Nature 440 2006 165 173
14. B. Efron, and R. Tibshirani An introduction to the Bootstrap 1993 Chapman & Hall New York
15. J.A.M. Demattê, M.V. Galdos, R.V. Guimaraes, A.M. Genu, M.R. Nanni, and J. Zullo Quantification of tropical soil attributes from ETM+/LANDSAT-7 data Int. J. Remote Sens. 28 2007 3813 3829
16. J. Elith, J.R. Leathwick, and T. Hastie A working guide to boosted regression trees J. Anim. Ecol. 77 2008 802 813
17. J.H. Friedman Greedy function approximation: a gradient boosting machine Ann. Stat. 29 2001 1189 1232
18. J.H. Friedman Stochastic gradient boosting Comput. Stat. Data Anal. 38 2002 367 378
19. J.H. Friedman, and J.J. Meulman Multiple additive regression trees with application in epidemiology Stat. Med. 22 2003 1365 1381
20. J.T. Froeschke, and B.F. Froeschke Spatiooral predictive model based on environmental factors for juvenile spotted seatrout in Texas estuaries using boosted regression trees Fish. Res. 111 2011 131 138
21. A. Gal, T.J. Vyn, E. Micheli, E.J. Kladivko, and W.W. McFee Soil carbon and nitrogen accumulation with long-term no-till versus moldboard plowing overestimated with tilled-zone sampling depths Soil Till. Res. 96 2007 42 51
22. R. Geerken, B. Zaitchik, and J.P. Evans Classifying rangeland vegetation type and coverage from NDVI time series using Fourier Filtered Cycle Similarity Int. J. Remote Sens. 26 2005 5535 5554
23. E. Goidts, B. Van Wesemael, and M. Crucifix Magnitude and sources of uncertainties in soil organic carbon (SOC) stock assessments at various scales Eur. J. Soil Sci. 60 2009 723 739
24. J. Grace Understanding and managing the global carbon cycle J. Ecol. 92 2004 189 202
25. R. Grimm, T. Behrens, M. Märker, and H. Elsenbeer Soil organic carbon concentrations and stocks on Barro Colorado Island-digital soil mapping using Random Forests analysis Geoderma 146 2008 102 113
26. L.B. Guo, and R.M. Gifford Soil carbon stocks and land use change: a meta analysis Global Change Biol. 8 2002 345 360
27. B.L. Henderson, E.N. Bui, C.J. Moran, and D.A.P. Simon Australia-wide predictions of soil properties using decision trees Geoderma 124 2005 383 398
28. S.M. Jaber, and M.I. Al-Qinna Soil organic carbon modeling and mapping in a semi-arid environment using thematic mapper data Photogramm. Eng. Remote Sens. 77 2011 709 719
29. H. Jenny Factors of Soil Formation 1941 McGraw-Hill New York
30. X.M. Jin, L. Wan, Y.K. Zhang, G.C. Hu, M.E. Schaepman, J.G.P.W. Clevers, and Z. Su Quantification of spatial distribution of vegetation in the Qilian Mountain area with MODIS NDVI Int. J. Remote Sens. 30 2009 5751 5766
31. E.G. Jobbágy, and R.B. Jackson The vertical distribution of soil organic carbon and its relation to climate and vegetation Ecol. Appl. 10 2000 423 436
32. P. Krishnan, G. Bourgeon, D. Lo Seen, K.M. Nair, R. Prasanna, S. Srinivas, G. Muthusankar, L. Dufy, and B.R. Ramesh Organic carbon stock map for soils of southern India: a multifactorial approach Curr. Sci. India 93 2007 706 710
33. R. Lawrence, A. Bunn, S. Powell, and M. Zambon Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis Remote Sens. Environ. 90 2004 331 336
34. R.L. Lawrence, S.D. Wood, and R.L. Sheley Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (Random Forest) Remote Sens. Environ. 100 2006 356 362
35. A. Liaw, and M. Wiener Classification and regression by random forest R News 2 2002 18 22
36. M. Ließ, B. Glaser, and B. Huwe Uncertainty in the spatial prediction of soil texture: comparison of regression tree and Random Forest models Geoderma 170 2012 70 79
37. L. Lin A concordance correlation coefficient to evaluate reproducibility Biometrics 45 1989 255 268
38. B.P. Malone, A.B. McBratney, B. Minasny, and G.M. Laslett Mapping continuous depth functions of soil carbon storage and available water capacity Geoderma 154 2009 138 152
39. M.P. Martin, M. Wattenbach, P. Smith, J. Meersmans, C. Jolivet, L. Boulonne, and D. Arrouays Spatial distribution of soil organic carbon stocks in France Biogeosciences 8 2011 1053 1065
40. A.B. McBratney, M.L.M. Santos, and B. Minasny On digital soil mapping Geoderma 117 2003 3 52
41. B. Minasny, A.B. McBratney, B.P. Malone, and I. Wheeler Digital mapping of soil carbon D.L. Sparks, Advances in Agronomy 2013 1 47
42. B. Minasny, A.B. McBratney, M.L.M. Santos, I.O.A. Odeh, and B. Guyon Prediction and digital mapping of soil carbon storage in the Lower Namoi Valley Aust. J. Soil Res. 44 2006 233
43. U. Mishra, R. Lal, B. Slater, F. Calhoun, D.S. Liu, and M. Van Meirvenne Predicting soil organic carbon stock using profile depth distribution functions and ordinary Kriging Soil Sci. Soc. Am. J. 73 2009 614 621
44. V. Pala, and X. Pons Incorporation of relief in polynomial-based geometric corrections Photogramm. Eng. Rem. Sens. 61 1995 935 944
45. J. Peters, N. Verhoest, R. Samson, P. Boeckx, and B. De Baets Wetland vegetation distribution modelling for the identification of constraining environmental variables Landsc. Ecol. 23 2008 1049 1065
46. R. Pouteau, S. Rambal, J.-P. Ratte, F. Gogé, R. Joffre, and T. Winkel Downscaling MODIS-derived maps using GIS and boosted regression trees: the case of frost occurrence over the arid Andean highlands of Bolivia Remote Sens. Environ. 115 2011 117 129
47. A.M. Prasad, L.R. Iverson, and A. Liaw Newer classification and regression tree techniques: bagging and random forests for ecological prediction Ecosystems 9 2006 181 199
48. D. Riano, E. Chuvieco, J. Salas, and I. Aguados Assessment of different topographic corrections in Landsat-TM data for mapping vegetation types IEEE Trans. Geosci. Remote 41 2003 1056 1061
49. R Development Core Team R: A Language and Environment for Statistical Computing 2009
50. R.H. Razakamanarivo, C. Grinand, M.A. Razafindrakoto, M. Bernoux, and A. Albrecht Mapping organic carbon stocks in eucalyptus plantations of the central highlands of Madagascar: a multiple regression approach Geoderma 162 2011 335 346
51. W.H. Schlesinger Biogeochemistry: An Analysis of Global Change 1997 Academic Press San Diego, CA
52. Y. Shi, F. Baumann, Y. Ma, C. Song, P. Kühn, T. Scholten, and J.S. He Organic and inorganic carbon in the topsoil of the Mongolian and Tibetan grasslands: pattern, control and implications Biogeosciences 9 2012 2287 2299
53. M. Skurichina, and R.P. Duin Bagging, boosting and the random subspace method for linear classifiers Pattern Anal. Appl. 5 2002 121 135
54. K. Sreenivas, G. Sujatha, K. Sudhir, D.V. Kiran, M. Fyzee, T. Ravisankar, and V. Dadhwal Spatial assessment of soil organic carbon density through random forests based imputation J. Indian Soc. Remote Sen. 42 2014 577 587
55. Soil Survey Staff Keys to Soil Taxonomy 12th ed. 2014 NRCS Washington, DC
56. Y. Wang, C. Yan, and J. Wang Landuse/Landcover data of the Heihe river basin in 2000 Data Center of the Heihe Project 2011 10.3972/heihe.020.2013.db
57. D.G. Sullivan, J.N. Shaw, and D. Rickman IKONOS imagery to estimate surface soil property variability in two Alabama physiographies Soil Sci. Soc. Am. J. 69 2005 1789 1798
58. K. Were, D.T. Bui, O.B. Dick, and B.R. Singh A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape Ecol. Indic. 52 2015 394 403
59. M. Wiesmeier, F. Barthold, B. Blank, and I. Kögel-Knabner Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem Plant Soil 340 2011 7 24
60. M. Wiesmeier, F. Barthold, P. Spörlein, U. Geuß, E. Hangen, A. Reischl, B. Schilling, G. Angst, M. von Lützow, and I. Kögel-Knabner Estimation of total organic carbon storage and its driving factors in soils of Bavaria (southeast Germany) Geoderma Reg. 1 2014 67 78
61. Y.H. Yang, J.Y. Fang, Y.H. Tang, C.J. Ji, C.Y. Zheng, J.S. He, and B. Zhu Storage, patterns and controls of soil organic carbon in the Tibetan grasslands Global Change Biol. 14 2008 1592 1599
62. F. Zhang, C. Li, Z. Wang, and H. Wu Modeling impacts of management alternatives on soil carbon storage of farmland in Northwest China Biogeosciences 3 2006 451 466
63. G.L. Zhang, and Z.T. Gong Soil Survey Laboratory Methods 2012 Science Press Beijing (in Chinese)
64. M.S. Zhao, D.G. Rossiter, D.C. Li, Y.G. Zhao, F. Liu, and G.L. Zhang Mapping soil organic matter in low-relief areas based on land surface diurnal temperature difference and a vegetation index Ecol. Indic. 39 2014 120 133
65. A.X. Zhu, L. Yang, B. Li, C. Qin, E. English, J.E. Burt, and C. Zhou Purposive sampling for digital soil mapping for areas with limited data A.E. Hartemink, Digital Soil Mapping With Limited Data 2008 Springer 33 245