An assessment of the effectiveness of decision tree methods for land cover classification

By Mahesh Pal, Paul M. Mather. 2003

1,208 citations recorded by the source corpus.

Subfields: Ecology, Global and Planetary Change, Media Technology

View Paper: https://www.semanticscholar.org/paper/abf35bb32d077832d6cc1ead91a01b68b3628413

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 Global and Planetary Change

In Media Technology

Citations in the corpus

Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines (2015, background): “DTs, along with neural networks, are themost widely usedmachine learning algorithms in geosciences (Friedl and Brodley, 1997; Hansen et al., 1996; Lippitt et al., 2008; Pal and Mather, 2003; Rogan et al., 2003; Wessels et al., 2004).”
A Review: The Role of Remote Sensing in Precision Agriculture (2010, background): “…and are useful for operations such as stress mapping, fertilization and pesticide application and irrigation management (Barnes and Baker, 2000; Barroso et al., 2008; Hinzman et al., 1986; Lelong et al., 1998; Pal and Mather, 2003; Singh et al., 2007; Tilling et al., 2007; Yang et al., 2003).”
Implementation of machine-learning classification in remote sensing: an applied review (2018, background): “Pruning reduces the accuracy of classifying the training data but generally increases the accuracy of dealing with unknowns (Pal and Mather 2003).”
Building Instance Classification Using Street View Images (2018, background): “The classification of land cover from Earth Observation (EO) images in complex urban environments has been a focus in remote sensing over the past decades (Anderson et al., 1976; Pal and Mather, 2003; Yuan et al., 2005; Stefanov et al., 2001; RodriguezGaliano et al., 2012; Albert et al., 2017).”
Random forest classifier for remote sensing classification (2005, methodology): “Studies using boosting (Freund and Schapire 1996) with a decision tree as a base classifier have reported a significant increase in classification accuracy for land cover classification studies (Friedl et al. 1999, Muchoney et al. 2000, Pal and Mather 2003a).”
Fusion of Support Vector Machines for Classification of Multisensor Data (2007, methodology): “Self-learning DTs have been applied successfully to diverse remote sensing imagery [8], [ 9 ], [13], [14].”
Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery (2008, methodology): “As this paper focuses more on ensemble classification, we refer the reader who is interested in more detailed explanation about the construction of decision trees to Pal and Mather (2003), Friedl and Brodley (1997), or Quinlan (1993).”
A relative evaluation of multiclass image classification by support vector machines (2004, background): “Again, the size of the training set can influence classification accuracy, and other studies have shown that the accuracy of DT classification increases with training set size [14].”
Comparative classification analysis of post-harvest growth detection from terrestrial LiDAR point clouds in precision agriculture (2015, methodology): “The approaches were selected based on the similar application of those for surface classification (Alexander et al., 2010; Gerke & Jing, 2014; Pal & Mather, 2003), vegetation detection in airborne (Ducic et al., 2006; Höfle & Hollaus, 2010; Rutzinger et al., 2008; Zlinszky et al., 2012) and in…”
A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory (2009, background): “The fact that DT requires a pruning method is also a factor that strongly influences classification accuracy (Pal and Mather 2003).”