Classification trees: An alternative non‐parametric approach for predicting species distributions

By M. Vayssières, Richard E. Plant, B. Allen-Diaz. 2000

365 citations recorded by the source corpus.

Subfields: Ecological Modeling, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/fc0175d7eabccc1d658403f4b08563bfede1598f

How researchers see this paper

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

In Ecological Modeling

In Nature and Landscape Conservation

Citations in the corpus

Nonparametric Multiplicative Regression for Habitat Modeling (2011, methodology): “Classification trees have been used as habitat models, using presence-absence as a binary response variable (e.g. Austin et al. 1994, Franklin 1998; Vayssières et al. 2000).”
Predicting species distributions in poorly-studied landscapes (2008, result): “This result is consistent with what one would expect from a classification method, which partitions the environment into multiple nodes allowing the model to effectively account for variations in habitat selection by spatially isolated populations (Vayssières et al. 2000).”
Ecological niche modelling of two cryptic bat species calls for a reassessment of their conservation status (2007, methodology): “We used Geographical Information Systems (GIS) and Ecological Niche Factor Analysis (ENFA) to prepare species-specific optimal habitat profiles, to compare respective ecological niche parameters and to predict habitat suitability on a nation-wide scale (Buckland & Elston 1993; Manel et al . 1999; V”
Consumers’ Intention to Purchase Electric Vehicles: Influences of User Attitude and Perception (2021, methodology): “The classification tree approach is helpful because of its ability to reveal data structures with complex interactions among variables, while not requiring a specific functional form [30].”
The performance of state-of-the-art modelling techniques depends on geographical distribution of species. (2009, methodology): “CTA is used frequently for biogeographical and environmental studies (De’Ath and Fabricius, 2000; Vayssière et al., 2000; Franklin, 2002; Thuiller et al., 2004a,b).”
Modeling the distribution of four vegetation alliances using generalized linear models and classification trees with spatial dependence (2002, neutral): “…including vegetation modeling (Moore et al., 1991a; Lees and Ritman, 1991; Lenihan and Neilson, 1993; Michaelsen et al., 1994; Franklin, 1998; Franklin et al., 2000; Guisan et al., 1998; Vayssières et al., 2000; Meentemeyer et al., 2001*/reviewed by Franklin, 1995; Guisan and Zimmermann, 2000).”
Soil nutritional factors improve models of plant species distribution: an illustration with Acer campestre (L.) in France (2006, methodology): “Many statistical techniques have been developed to model the response of species to environmental conditions (Yee & Mitchell, 1991; Huisman et al., 1993; Elith, 2000; Vayssières et al., 2000; Gelfand et al., 2003; Robertson et al.,”
Generalized models vs. classification tree analysis: Predicting spatial distributions of plant species at different scales (2003, methodology): “These provide an alternative to regression techniques (e.g. Vayssières et al. 2000; Thuiller et al. 2003).”
Assessing long‐term fire risk at local scale by means of decision tree technique (2006, methodology): “Being a nonparametric tool, CART analysis has been shown to outperform LR [Vayssieres et al., 2000]; its capability to estimate continuous response variable (regression feature)”
Spatial prediction of demersal fish distributions: enhancing our understanding of species–environment relationships (2009, methodology): “Although valuable in examining species-environment relationships, AdjD2 is not an unbiased and independent method of comparing approaches (Franklin 1998, Vayssières et al. 2000).”
An evaluation of methods for modelling species distributions (2004, methodology): “As for spatial distributions, the same trend was observed for environmental distributions: (1) lower measures of performance and stability of DOMAIN and BIOMAP were more evident for species of group 1; (2) highest performances of NNETW were more evident for species of groups 3 and 4; (3) AGAM showed”
Commercially Important Trees as Invasive Aliens – Towards Spatially Explicit Risk Assessment at a National Scale (2002, methodology): “Recursive partitioning is an attractive statistical technique for analysing large datasets, and yields more accurate predictions than standard linear models (Hawkins 1995; De’ath and Fabricius 2000; Vayssieres et al. 2000 ).”