Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance

Canadian Journal of Forest Research

Volumn 46, Issue 3, 2015, Pages 323-339

  Freeman, Elizabeth A ^a   Moisen, Gretchen G ^a   Coulston, John W ^b   Wilson, Barry T ^b  

^a ROCKY MOUNTAIN RESEARCH STATION   (United States)

^b USDA FOREST SERVICE   (United States)

Author keywords

Classification and regression trees; Predictive mapping; Random forest; Stochastic gradient boosting; Tree canopy cover

Indexed keywords

DECISION TREES; FORESTRY; MEAN SQUARE ERROR; STOCHASTIC MODELS;

CLASSIFICATION AND REGRESSION TREE; PREDICTIVE MAPPING; RANDOM FORESTS; STOCHASTIC GRADIENT BOOSTING; TREE CANOPY COVERS;

STOCHASTIC SYSTEMS;

CLASSIFICATION; DATA SET; FOREST CANOPY; FOREST ECOSYSTEM; FORESTRY MODELING; PHOTOGRAPHY; PREDICTION; STOCHASTICITY; TREE;

KANSAS; UNITED STATES;

EID: 84959283543     PISSN: 00455067     EISSN: 12086037     Source Type: Journal    
DOI: 10.1139/cjfr-2014-0562     Document Type: Article

References (53)

1. Baccini, A., Laporte, N., Goetz, S.J., Sun, M., and Dong, H. 2008. A first map of tropical Africa’s above-ground biomass derived from satellite imagery. Environ. Res. Lett. 3(4): 045011. doi:10.1088/1748-9326/3/4/045011.
2. Bailey, R.G. 1995. Description of the ecoregions of the United States. USDA Forest Service Misc. Pub. 1391.
3. Baker, C., Lawrence, R., Montagne, C., and Patten, D. 2006. Mapping wetlands and riparian areas using Landsat ETM+ imagery and decision-tree-based models. Wetlands, 26(2): 465-474. doi:10.1672/0277-5212(2006)26[465:MWARAU]2.0.CO;2.
4. Bechtold, W.A., and Patterson, P.L. (Editors). 2005. The Enhanced Forest Inventory and Analysis Program - national sampling design and estimation procedures. USDA Forest Service, Southern Research Station, Asheville, North Carolina, General Technical Report SRS-80.
5. Breiman, L. 2001. Random forests. Mach. Learn. 45: 5-32. doi:10.1023/A:1010933404324.
6. Breiman, L., Friedman, R.A., Olshen, R.A., and Stone, C.G. 1984. Classification and regression trees. Wadsworth.
7. Chan, J.C.W., and Paelinckx, D. 2008. Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotype mapping using airborne hyperspectral imagery. Remote Sens. Environ. 112(6): 2999-3011. doi:10.1016/j.rse.2008.02.011.
8. Chirici, G., Scotti, R., Montaghi, A., Barbati, A., Cartisano, R., Lopez, G., Marchetti, M., McRoberts, R.E., Olsson, H., and Corona, P. 2013. Stochastic gradient boosting classification trees for forest fuel types mapping through airborne laser scanning and IRS LISS-III imagery. Int. J. Appl. Earth Obs. Geoinf. 25: 87-97. doi:10.1016/j.jag.2013.04.006.
9. Cochran, W.G. 1977. Sampling Techniques. 3rd ed. John Wiley & Sons, New York.
10. Coulston, J.W., Moisen, G.G., Wilson, B.T., Finco, M.V., Cohen, W.B., and Brewer, C.K. 2012. Modeling percent tree canopy cover: a pilot study. Photogramm. Eng. Remote Sens. 78(7): 715-727. doi:10.14358/PERS.78.7.715.
11. De’ath, G. 2007. Boosted trees for ecological modeling and prediction. Ecology, 88(1): 243-251. doi:10.1890/0012-9658(2007)88[243:BTFEMA]2.0.CO;2.
12. De’ath, G., and Fabricius, K.E. 2000. Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology, 81(11): 3178-3192. doi:10.1890/0012-9658(2000)081[3178:CARTAP]2.0.CO;2.
13. Elith, J., Leathwick, J.R., and Hastie, T. 2008. A working guide to boosted regression trees. J. Anim. Ecol. 77: 802-13. doi:10.1111/j.1365-2656.2008.01390.x.
14. Evans, J., and Cushman, S. 2009. Gradient modeling of conifer species using random forests. Landsc. Ecol. 24: 673-683. doi:10.1007/s10980-009-9341-0.
15. Filippi, A.M., Guneralp, İ., and Randall, J. 2014. Hyperspectral remote sensing of aboveground biomass on a river meander bend using multivariate adaptive regression splines and stochastic gradient boosting. Remote Sens. Lett. 5(5): 432-441. doi:10.1080/2150704X.2014.915070.
16. Freeman, E., and Frescino, T. 2009. ModelMap: an R package for modeling and map production using Random Forest and Stochastic Gradient Boosting. USDA Forest Service, Rocky Mountain Research Station, 507 25th street, Ogden, Utah, U.S.A. Available at https://cran.r-project.org/web/packages/ModelMap/vignettes/VModelMap.pdf.
17. Frescino, T.S., and Moisen, G.G. 2012. Comparing alternative tree canopy cover estimates derived from digital aerial photography and field-based assessments. In Proceedings of Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. Edited by W. McWilliams and F.A. Roesch. USDA Forest Service, Southern Research Station, Asheville, North Carolina, e-Gen. Tech. Rep. SRS-157. pp. 237-244.
18. Friedman, J.H. 2001. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5): 1189-1232. doi:10.1214/aos/1013203451.
19. Friedman, J.H. 2002. Stochastic Gradient Boosting. Computational Statistics and Data Analysis, 28: 367-78. doi:10.1016/S0167-9473(01)00065-2.
20. Friedman, J., Hastie, T., and Tibshirani, R. 2000. Additive logistic regression: a statistical view of boosting. Ann. Stat. 28(2): 337-407. doi:10.1214/aos/1016218223.
21. Gislason, P.O., Benediktsson, J.A., and Sveinsson, J.R. 2006. Random Forests for land cover classification. Pattern Recognit. Lett. 27(4): 294-300. doi:10.1016/j.patrec.2005.08.011.
22. Guneralp, İ., Filippi, A.M., and Randall, J. 2014. Estimation of floodplain aboveground biomass using multispectral remote sensing and nonparametric modeling. Int. J. Appl. Earth Obs. Geoinf. 33: 119-126. doi:10.1016/j.jag.2014.05.004.
23. Hastie, T., Tibshirani, R., and Friedman, J. 2009. Model assessment and selection. In The elements of statistical learning. Springer Series in Statistics, Springer, New York. pp. 219-259.
24. Hauke, J., and Kossowski, T. 2011. Comparison of values of Pearson’s and Spear-man’s correlation coefficients on the same sets of data. Quaestiones Geographicae, 30(2): 87-93. doi:10.2478/v10117-011-0021-1.
25. Homer, C., Huang, C., Yang, L., Wylie, B., and Coan, M. 2004. Development of a 2001 National Landcover Database for the United States. Photogramm. Eng. Remote Sens. 70(7): 829-840. doi:10.14358/PERS.70.7.829.
26. Homer, C., Dewitz, J., Fry, J., Coan, M., Hossain, N., Larson, C., Herold, N., McKerrow, A., VanDriel, J.N., and Wickham, J. 2007. Completion of the 2001 National Land Cover Database for the conterminous United States. Photogramm. Eng. Remote Sens. 73(4): 337-341.
27. Jackson, T.A., Moisen, G., Patterson, P.L., and Tipton, J. 2012. Repeatability in photo-interpretation of tree canopy cover and its effect on predictive mapping. In Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. Edited by W. McWilliams and F.A. Roesch. USDA Forest Service, Southern Research Station, Asheville, North Carolina, e-Gen. Tech. Rep. SRS-157. pp. 189-192.
28. Jennings, S.B., Brown, N.D., and Sheil, D. 1999. Assessing forest canopies and understory illumination: canopy closure, canopy cover and other measures. Forestry, 72(1): 59-73. doi:10.1093/forestry/72.1.59.
29. Kellndorfer, J.M., Walker, W., LaPoint, E., Hoppus, M., and Westfall, J. 2006. Modeling height, biomass, and carbon in US forests from FIA, SRTM, and ancillary national scale data sets. In Proceedings of the IEEE International Symposium on Geoscience and Remote Sensing (IGARSS), July 31-August 4, 2006, Denver, Colorado. pp. 3591-3594.
30. Lawrence, R., Bunn, A., Powell, S., and Zambon, M. 2004. Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis. Remote Sens. Environ. 9(3): 331-336. doi:10.1016/j.rse.2004.01.007.
31. Lawrence, R.L., Wood, S.D., and Sheley, R.L. 2006. Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (Random Forest). Remote Sens. Environ. 100: 356-362. doi:10.1016/j.rse.2005.10.014.
32. Leathwick, J.R., Elith, J., Francis, M.P., Hastie, T., and Taylor, P. 2006. Variation in demersal fish species richness in the oceans surrounding New Zealand: an analysis using boosted regression trees. Mar. Ecol. Prog. Ser. 321: 267-281. doi:10.3354/meps321267.
33. Liaw, A., and Wiener, M. 2002. Classification and regression by random forest. R News, 2: 18-22. Available from http://CRAN.R-project.org/doc/Rnews/.
34. McRoberts, R.E., Holden, G.R., Nelson, M.D., Liknes, G.C., and Gormanson, D.D. 2005. Using satellite imagery as ancillary data for increasing the precision of estimates for the Forest Inventory and Analysis program of the USDA Forest Service. Can. J. For. Res. 35(12): 2968-2980. doi:10.1139/x05-222.
35. Moisen, G.G. 2008. Classification and regression trees. In Encyclopedia of Ecology. Vol. 1. Edited by S.E. Jorgensen and B.D. Fath. Elsevier. pp. 582-588.
36. Moisen, G.G., and Frescino, T.S. 2002. Comparing five modelling techniques for predicting forest characteristics. Ecol. Model. 157: 209-225. doi:10.1016/S0304-3800(02)00197-7.
37. Moisen, G.G., Freeman, E.A., Blackard, J.A., Frescino, T.S., Zimmermann, N.E., and Edwards, T.C., Jr. 2006. Predicting tree species presence and basal area in Utah: a comparison of stochastic gradient boosting, generalized additive models, and tree-based methods. Ecol. Model. 199: 176-187. doi:10.1016/j.ecolmodel.2006.05.021.
38. Moisen, G.G., Coulston, J.W., Wilson, B.T., Cohen, W.B., and Finco, M.V. 2012. Choosing appropriate subpopulations for modeling tree canopy cover nationwide. In Proceedings of Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. Edited by W. McWilliams and F.A. Roesch. USDA Forest Service, Southern Research Station, Asheville, North Carolina, e-Gen. Tech. Rep. SRS-157. pp. 195-200.
39. Moore, I.D., Grayson, R.B., and Ladson, A.R. 1991. Digital terrain modelling: review of hydrological, geomorphological, and biological applications. Hydrol. Processes, 5: 3-30. doi:10.1002/hyp.3360050103.
40. Nowak, D.J., Crane, D.E., and Stevens, J.C. 2006. Air pollution removal by urban trees and shrubs in the United States. Urban Forestry and Urban Greening, 4(3-4): 115-123. doi:10.1016/j.ufug.2006.01.007.
41. Pittman, S.J., Costa, B.M., and Battista, T.A. 2009. Using Lidar bathymetry and boosted regression trees to predict the diversity and abundance of fish and corals. J. Coastal Res., Spec. Issue, 53: 27-38. doi:10.2112/SI53-004.1.
42. Powell, S.L., Cohen, W.B., Healey, S.P., Kennedy, R.E., Moisen, G.G., Pierce, K.B., and Ohmann, J.L. 2010. Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: a comparison of empirical modeling approaches. Remote Sens. Environ. 114(5): 1053-1068. doi:10.1016/j.rse.2009.12.018.
43. Prasad, A.M., Iverson, L.R., and Liaw, A. 2006. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9: 181-199. doi:10.1007/s10021-005-0054-1.
44. R Development Core Team. 2008. R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Available from http://www.R-project.org.ISBN3-900051-07-0.
45. Ridgeway, G. 2007. Generalized boosted models: a guide to the gbm package. Available from https://cran.r-project.org/web/packages/gbm/index.html.
46. Ridgeway, G., et al. 2013. gbm: Generalized boosted regression models. R package version 2.1. Available from https://cran.r-project.org/web/packages/gbm/index.html.
47. Rollins, M.G., and Frame, C.K. (Editors). 2006. The LANDFIRE Prototype Project: nationally consistent and locally relevant geospatial data for wildland fire management. USDA Forest Service, Rocky Mountain Research Station, Fort Collins, Colorado, General Technical Report RMRS-GTR-175.
48. Sankaran, M., Ratnam, J., and Hanan, N. 2008. Woody cover in African savannas: the role of resources, fire and herbivory. Glob. Ecol. Biogeogr. 17: 236-245. doi:10.1111/j.1466-8238.2007.00360.x.
49. Tipton, J., Moisen, G., Patterson, P., Jackson, T.A., and Coulston, J. 2012. Sampling intensity and normalizations: exploring cost-driving factors in nationwide mapping of tree canopy cover. In Proceedings of Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. Edited by W. McWilliams and F.A. Roesch. USDA Forest Service, Southern Research Station, Asheville, North Carolina, e-Gen. Tech. Rep. SRS-157. pp. 201-208.
50. Toney, C., Liknes, G., Lister, A., and Meneguzzo, D. 2012. Assessing alternative measures of tree canopy cover: photo-interpreted NAIP and ground-based estimates. In Proceedings of Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. Edited by W. McWilliams and F.A. Roesch. USDA Forest Service, Southern Research Station, Asheville, North Carolina, e-Gen. Tech. Rep. SRS-157. pp. 209-215.
51. U.S. Department of Agriculture (USDA). 2009. National Agriculture Imagery Program. USDA Farm Service Agency, Aerial Photography Field Office, Salt Lake City, Utah. Available from http://www.apfo.usda.gov/FSA/apfoapp?area=home&subject=prog&topic=nai [accessed 29 March 2012].
52. Webb, B.W., and Crisp, D.T. 2006. Afforestation and stream temperature in a temperate maritime environment. Hydrol. Processes, 20(1): 51-66. doi:10.1002/hyp.5898.
53. White, D., Kimerling, J., and Overton, S.W. 1992. Cartographic and geometric components of a global sampling design for environmental monitoring. Cartographic and Geographic Information Systems, 19(1): 5-22. doi:10.1559/152304092783786636.