%0 Journal Article %1 Garzon2006 %A Garzón, Marta Benito %A Blazek, Radim %A Neteler, Markus %A Dios, Rut Sánchez de %A Ollero, Helios Sainz %A Furlanello, Cesare %D 2006 %J Ecological Modelling %K %N 3-4 %P 383--393 %T Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula %U http://www.sciencedirect.com/science/article/B6VBS-4JRVBDK-5/2/6b75f12e4a096f17439ecf5c766c94c1 %V 197 %X 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.

@article{Garzon2006, 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.}, added-at = {2023-12-12T19:03:52.000+0100}, author = {Garzón, Marta Benito and Blazek, Radim and Neteler, Markus and Dios, Rut Sánchez de and Ollero, Helios Sainz and Furlanello, Cesare}, biburl = {https://www.bibsonomy.org/bibtex/2cb11d3e35cff46ac426c66a01f41a67d/admin}, file = {:Garzon2006.pdf:PDF}, interhash = {1b3843478a119641ba160ed9b43ee83a}, intrahash = {cb11d3e35cff46ac426c66a01f41a67d}, issn = {0304-3800}, journal = {Ecological Modelling}, keywords = {}, month = {#aug#}, note = {2review}, number = {3-4}, pages = {383--393}, timestamp = {2023-12-12T19:03:52.000+0100}, title = {Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula}, url = {http://www.sciencedirect.com/science/article/B6VBS-4JRVBDK-5/2/6b75f12e4a096f17439ecf5c766c94c1}, volume = 197, year = 2006 }