Skip to Main Content
Predicting tree species presence and basal area in Utah: A comparison of stochastic gradient boosting, generalized additive models, and tree-based methodsAuthor(s): Gretchen G. Moisen; Elizabeth A. Freeman; Jock A. Blackard; Tracey S. Frescino; Niklaus E. Zimmermann; Thomas C. Edwards
Source: Ecological Modelling. 199: 176-187.
Publication Series: Scientific Journal (JRNL)
Station: Rocky Mountain Research Station
PDF: Download Publication (966.23 KB)
DescriptionMany efforts are underway to produce broad-scale forest attribute maps by modelling forest class and structure variables collected in forest inventories as functions of satellite-based and biophysical information. Typically, variants of classification and regression trees implemented in Rulequest's© See5 and Cubist (for binary and continuous responses, respectively) are the tools of choice in many of these applications. These tools are widely used in large remote sensing applications, but are not easily interpretable, do not have ties with survey estimation methods, and use proprietary unpublished algorithms. Consequently, three alternative modelling techniques were compared for mapping presence and basal area of 13 species located in the mountain ranges of Utah, USA. The modelling techniques compared included the widely used See5/Cubist, generalized additive models (GAMs), and stochastic gradient boosting (SGB). Model performancewas evaluated using independent test data sets. Evaluation criteria for mapping species presence included specificity, sensitivity, Kappa, and area under the curve (AUC). Evaluation criteria for the continuous basal area variables included correlation and relative mean squared error. For predicting species presence (setting thresholds to maximize Kappa), SGB had higher values for the majority of the species for specificity and Kappa, while GAMs had higher values for the majority of the species for sensitivity. In evaluating resultant AUC values, GAM and/or SGB models had significantly better results than the See5 models where significant differences could be detected between models. For nine out of 13 species, basal area prediction results for all modelling techniques were poor (correlations less than 0.5 and relative mean squared errors greater than 0.8), but SGB provided the most stable predictions in these instances. SGB and Cubist performed equally well for modelling basal area for three species with moderate prediction success, while all three modelling tools produced comparably good predictions (correlation of 0.68 and relative mean squared error of 0.56) for one species.
- You may send email to firstname.lastname@example.org to request a hard copy of this publication.
- (Please specify exactly which publication you are requesting and your mailing address.)
- 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.
CitationMoisen, Gretchen G.; Freeman, Elizabeth A.; Blackard, Jock A.; Frescino, Tracey S.; Zimmermann, Niklaus E.; Edwards, Thomas 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. Ecological Modelling. 199: 176-187.
Keywordsspecies presence, predictive mapping, forest inventory, GAMs, classification trees, regression trees See5, Cubist, stochastic gradient boosting
- A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and Kappa
- Factors affecting species distribution predictions: A simulation modeling experiment
- PresenceAbsence: An R package for presence absence analysis
XML: View XML