Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis

By Rick L. Lawrence, A. Bunn, Scott L. Powell, M. Zambon. 2004

332 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/27b0c9dd4cd2477a07611d587e328adbf830dc75

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Media Technology

Citations in the corpus

Predicting tree species presence and basal area in Utah: A comparison of stochastic gradient boosting, generalized additive models, and tree-based methods (2006, background): “Lawrence et al. (2004) illustrate the use of stochastic gradient boosting as a refinement of classification tree analysis in a remote sensing problem.”
Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance (2016, result): “Lawrence et al. (2004) compared SGB and classification tree analysis (CTA) for classification of remotely sensed imagery for use in forestry and found that SGB improved accuracy, although the strength of the improvement was dataset dependent.”
Texture and Scale in Object-Based Analysis of Subdecimeter Resolution Unmanned Aerial Vehicle (UAV) Imagery (2009, background): “Decision trees are commonly used for remote sensing applications and often reduce the classification error [30], [31].”
Estimating forest soil bulk density using boosted regression modelling (2010, methodology): “, 2008), remote sensing (Lawrence et al., 2004), ecology (Leathwick et al.”
Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale (2014, unknown): “BRT was shown to have improved accuracy compared with simple regression trees, thanks to its stochastic gradient boosting procedure aimed at minimizing the risk of overfitting and improving its predictive power (Lawrence et al., 2004).”
Extrapolating regional soil landscapes from an existing soil map: Sampling intensity, validation procedures, and integration of spatial context (2008, methodology): “Classification tree analysis (CTA) is a modelling technique that is being used increasingly (Lawrence et al., 2004).”
Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms (2010, background): “…vector machines and maximum likelihood classification algorithms J.R. Otukei a,b,*, T. Blaschke b a Department of Surveying, Makerere University, P.O. Box 7062, Makerere Hill Road, Kampala, Uganda b Z_GIS Centre for GeoInformatics, University of Salzburg, Hellbrunner Str. 34, 5020 Salzburg, Austria”
Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) (2006, methodology): “Our attempts to classify hyperspectral imagery for our study area using numerous classification methods (spectral angle mapper, logistic regression, classification trees, boosted classification trees with See5 (Quinlan, 1993), and stochastic gradient boosting (Lawrence et al., 2004)) all met with no”