Skip to page content
USDA Forest Service
  
Treesearch

Research & Development Treesearch

 
Treesearch Home
About Treesearch
Contact Us
Research & Development
Forest Products Lab
International Institute of Tropical Forestry
Northern
Pacific Northwest
Pacific Southwest
Rocky Mountain
Southern Research Station
Help
 

Science.gov - We Participate


USA.gov  Government Made Easy


Global Forest Information Service

US Forest Service
P.O. Box 96090
Washington, D.C.
20090-6090

(202) 205-8333

You are here: Home / Search / Publication Information
Bookmark and Share

Publication Information

View PDF (74 KB)

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

Author: Freeman, E.; Moisen, G.; Coulston, J.; Wilson, B.;

Date: 2014

Source: The International Forestry Review. 16(5): 408.

Publication Series: Abstract

Description: Random forests (RF) and stochastic gradient boosting (SGB), both involving an ensemble of classification and regression trees, are compared for modeling tree canopy cover for the 2011 National Land Cover Database (NLCD). The objectives of this study were twofold. First, sensitivity of RF and SGB to choices in tuning parameters was explored. Second, performance of the two final models was compared by assessing the importance of, and interaction between, predictor variables, the global accuracy metrics derived from an independent test set, and the visual quality of the resultant maps of tree canopy cover. Examination of relative variable importance elucidated the differences in how RF and SGB make use of correlated predictor variables. SGB had a tendency to concentrate variable importance in fewer variables, whereas RF tended to spread importance out amongst more variables. The predictive accuracy of RF and SGB was remarkably similar on all four of the pilot regions, by all the accuracy measures examined. RF is simpler to implement than SGB, as RF both has fewer parameters needing tuning, and also was less sensitive to these parameters.

Keywords: random forests (RF), stochastic gradient boosting (SGB), tree canopy cover

Publication Notes:

  • We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
  • This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
  • You may send email to rmrspubrequest@fs.fed.us to request a hard copy of this publication. (Please specify exactly which publication you are requesting and your mailing address.)

XML: View XML

Citation:


Freeman, E.; Moisen, G.; Coulston, J.; Wilson, B. 2014. Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance. The International Forestry Review. 16(5): 408.

 


 [ Get Acrobat ]  Get the latest version of the Adobe Acrobat reader or Acrobat Reader for Windows with Search and Accessibility

USDA logo which links to the department's national site. Forest Service logo which links to the agency's national site.