Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula

@article{Benito2006_pred_habitat_pinus, abstract = {We present a modelling framework for predicting forest areas. The framework is obtained by integrating a machine learning software suite within the GRASS Geographical Information System (GIS) and by providing additional methods for predictive habitat modelling. Three machine learning techniques (Tree-Based Classification, Neural Networks and Random Forest) are available in parallel for modelling from climatic and topographic variables. Model evaluation and parameter selection are measured by sensitivity-specificity ROC analysis, while the final presence and absence maps are obtained through maximisation of the kappa statistic. The modelling framework is applied at a resolution of 1 km with Iberian subpopulations of Pinus sylvestris L. forests. For this data set, the most accurate algorithm is Breiman's random forest, an ensemble method which provides automatic combination of tree-classifiers trained on bootstrapped subsamples and randomised variable sets. All models show a potential area of P. sylvestris for the Iberian Peninsula which is larger than the present one, a result corroborated by regional pollen analyses.}, author = {Garzon, Marta B. and Blazek, Radim and Neteler, Markus and Dios, Rut S. and Ollero, Helios S. and Furlanello, Cesare }, citeulike-article-id = {608546}, doi = {10.1016/j.ecolmodel.2006.03.015}, journal = {Ecological Modelling}, keywords = {ecology, gis, machine-learning, presence-absence-models, randomforest, roc}, month = {August}, number = {3-4}, pages = {383--393}, posted-at = {2006-08-03 23:03:54}, priority = {2}, title = {Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula}, url = {http://dx.doi.org/10.1016/j.ecolmodel.2006.03.015}, volume = {197}, year = {2006} }

TY - JOUR ID - Benito2006_pred_habitat_pinus L3 - citeulike-article-id:608546 TI - Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula JF - Ecological Modelling VL - 197 IS - 3-4 SP - 383 EP - 393 N2 - We present a modelling framework for predicting forest areas. The framework is obtained by integrating a machine learning software suite within the GRASS Geographical Information System (GIS) and by providing additional methods for predictive habitat modelling. Three machine learning techniques (Tree-Based Classification, Neural Networks and Random Forest) are available in parallel for modelling from climatic and topographic variables. Model evaluation and parameter selection are measured by sensitivity-specificity ROC analysis, while the final presence and absence maps are obtained through maximisation of the kappa statistic. The modelling framework is applied at a resolution of 1 km with Iberian subpopulations of Pinus sylvestris L. forests. For this data set, the most accurate algorithm is Breiman's random forest, an ensemble method which provides automatic combination of tree-classifiers trained on bootstrapped subsamples and randomised variable sets. All models show a potential area of P. sylvestris for the Iberian Peninsula which is larger than the present one, a result corroborated by regional pollen analyses. KW - ecology KW - gis KW - machine-learning KW - presence-absence-models KW - randomforest KW - roc AU - Garzon, Marta AU - Blazek, Radim AU - Neteler, Markus AU - Dios, Rut AU - Ollero, Helios AU - Furlanello, Cesare PY - 2006/08// UR - http://dx.doi.org/10.1016/j.ecolmodel.2006.03.015 ER -