Predicting Habitat Suitability with Machine Learning Models: The Potential Area of Pinus Sylvestris L. in the Iberian Peninsula. Garzón, M. B., Blazek, R., Neteler, M., Dios, R. S., Ollero, H. S., & Furlanello, C. Ecological Modelling, 197(3-4):383–393, August, 2006. doi abstract bibtex 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{garzonPredictingHabitatSuitability2006,
title = {Predicting Habitat Suitability with Machine Learning Models: {{The}} Potential Area of {{Pinus}} Sylvestris {{L}}. in the {{Iberian Peninsula}}},
author = {Garz{\'o}n, Marta B. and Blazek, Radim and Neteler, Markus and Dios, Rut S. and Ollero, Helios S. and Furlanello, Cesare},
year = {2006},
month = aug,
volume = {197},
pages = {383--393},
issn = {0304-3800},
doi = {10.1016/j.ecolmodel.2006.03.015},
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.},
journal = {Ecological Modelling},
keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-608546,~to-add-doi-URL,auc,cart,habitat-suitability,iberian-peninsula,kappa,machine-learning,neural-networks,pinus-sylvestris,random-forest},
lccn = {INRMM-MiD:c-608546},
number = {3-4}
}
Downloads: 0
{"_id":"7JoMCu9QvCyE9ZEZ8","bibbaseid":"garzn-blazek-neteler-dios-ollero-furlanello-predictinghabitatsuitabilitywithmachinelearningmodelsthepotentialareaofpinussylvestrislintheiberianpeninsula-2006","downloads":0,"creationDate":"2016-06-22T10:19:45.964Z","title":"Predicting Habitat Suitability with Machine Learning Models: The Potential Area of Pinus Sylvestris L. in the Iberian Peninsula","author_short":["Garzón, M. B.","Blazek, R.","Neteler, M.","Dios, R. S.","Ollero, H. S.","Furlanello, C."],"year":2006,"bibtype":"article","biburl":"https://sharefast.me/php/download.php?id=zOUKvA&token=29","bibdata":{"bibtype":"article","type":"article","title":"Predicting Habitat Suitability with Machine Learning Models: The Potential Area of Pinus Sylvestris L. in the Iberian Peninsula","author":[{"propositions":[],"lastnames":["Garzón"],"firstnames":["Marta","B."],"suffixes":[]},{"propositions":[],"lastnames":["Blazek"],"firstnames":["Radim"],"suffixes":[]},{"propositions":[],"lastnames":["Neteler"],"firstnames":["Markus"],"suffixes":[]},{"propositions":[],"lastnames":["Dios"],"firstnames":["Rut","S."],"suffixes":[]},{"propositions":[],"lastnames":["Ollero"],"firstnames":["Helios","S."],"suffixes":[]},{"propositions":[],"lastnames":["Furlanello"],"firstnames":["Cesare"],"suffixes":[]}],"year":"2006","month":"August","volume":"197","pages":"383–393","issn":"0304-3800","doi":"10.1016/j.ecolmodel.2006.03.015","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.","journal":"Ecological Modelling","keywords":"*imported-from-citeulike-INRMM,~INRMM-MiD:c-608546,~to-add-doi-URL,auc,cart,habitat-suitability,iberian-peninsula,kappa,machine-learning,neural-networks,pinus-sylvestris,random-forest","lccn":"INRMM-MiD:c-608546","number":"3-4","bibtex":"@article{garzonPredictingHabitatSuitability2006,\n title = {Predicting Habitat Suitability with Machine Learning Models: {{The}} Potential Area of {{Pinus}} Sylvestris {{L}}. in the {{Iberian Peninsula}}},\n author = {Garz{\\'o}n, Marta B. and Blazek, Radim and Neteler, Markus and Dios, Rut S. and Ollero, Helios S. and Furlanello, Cesare},\n year = {2006},\n month = aug,\n volume = {197},\n pages = {383--393},\n issn = {0304-3800},\n doi = {10.1016/j.ecolmodel.2006.03.015},\n 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.},\n journal = {Ecological Modelling},\n keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-608546,~to-add-doi-URL,auc,cart,habitat-suitability,iberian-peninsula,kappa,machine-learning,neural-networks,pinus-sylvestris,random-forest},\n lccn = {INRMM-MiD:c-608546},\n number = {3-4}\n}\n\n","author_short":["Garzón, M. B.","Blazek, R.","Neteler, M.","Dios, R. S.","Ollero, H. S.","Furlanello, C."],"key":"garzonPredictingHabitatSuitability2006","id":"garzonPredictingHabitatSuitability2006","bibbaseid":"garzn-blazek-neteler-dios-ollero-furlanello-predictinghabitatsuitabilitywithmachinelearningmodelsthepotentialareaofpinussylvestrislintheiberianpeninsula-2006","role":"author","urls":{},"keyword":["*imported-from-citeulike-INRMM","~INRMM-MiD:c-608546","~to-add-doi-URL","auc","cart","habitat-suitability","iberian-peninsula","kappa","machine-learning","neural-networks","pinus-sylvestris","random-forest"],"downloads":0},"search_terms":["predicting","habitat","suitability","machine","learning","models","potential","area","pinus","sylvestris","iberian","peninsula","garzón","blazek","neteler","dios","ollero","furlanello"],"keywords":["auc","cart","habitat-suitability","iberian-peninsula","kappa","machine-learning","neural-networks","pinus-sylvestris","random-forest","*imported-from-citeulike-inrmm","~inrmm-mid:c-608546","~to-add-doi-url"],"authorIDs":[],"dataSources":["5S2zj2hKW8TWTkuMq"]}