BIOMOD - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change. Thuiller, W. 9(10):1353–1362. ![BIOMOD - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.
@article{thuillerBIOMODOptimizingPredictions2003,
title = {{{BIOMOD}} - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change},
author = {Thuiller, Wilfried},
date = {2003-10},
journaltitle = {Global Change Biology},
volume = {9},
pages = {1353--1362},
issn = {1354-1013},
doi = {10.1046/j.1365-2486.2003.00666.x},
url = {https://doi.org/10.1046/j.1365-2486.2003.00666.x},
abstract = {A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.},
keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-164719,~to-add-doi-URL,artificial-neural-networks,climate-change,future-climatic-envelopes,generalized-additive-models,generalized-linear-models,regression-tree-analysis},
number = {10}
}
Downloads: 0
{"_id":"dajbypXG6EQ8DeMic","bibbaseid":"thuiller-biomodoptimizingpredictionsofspeciesdistributionsandprojectingpotentialfutureshiftsunderglobalchange","authorIDs":[],"author_short":["Thuiller, W."],"bibdata":{"bibtype":"article","type":"article","title":"BIOMOD - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change","author":[{"propositions":[],"lastnames":["Thuiller"],"firstnames":["Wilfried"],"suffixes":[]}],"date":"2003-10","journaltitle":"Global Change Biology","volume":"9","pages":"1353–1362","issn":"1354-1013","doi":"10.1046/j.1365-2486.2003.00666.x","url":"https://doi.org/10.1046/j.1365-2486.2003.00666.x","abstract":"A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.","keywords":"*imported-from-citeulike-INRMM,~INRMM-MiD:c-164719,~to-add-doi-URL,artificial-neural-networks,climate-change,future-climatic-envelopes,generalized-additive-models,generalized-linear-models,regression-tree-analysis","number":"10","bibtex":"@article{thuillerBIOMODOptimizingPredictions2003,\n title = {{{BIOMOD}} - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change},\n author = {Thuiller, Wilfried},\n date = {2003-10},\n journaltitle = {Global Change Biology},\n volume = {9},\n pages = {1353--1362},\n issn = {1354-1013},\n doi = {10.1046/j.1365-2486.2003.00666.x},\n url = {https://doi.org/10.1046/j.1365-2486.2003.00666.x},\n abstract = {A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.},\n keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-164719,~to-add-doi-URL,artificial-neural-networks,climate-change,future-climatic-envelopes,generalized-additive-models,generalized-linear-models,regression-tree-analysis},\n number = {10}\n}\n\n","author_short":["Thuiller, W."],"key":"thuillerBIOMODOptimizingPredictions2003","id":"thuillerBIOMODOptimizingPredictions2003","bibbaseid":"thuiller-biomodoptimizingpredictionsofspeciesdistributionsandprojectingpotentialfutureshiftsunderglobalchange","role":"author","urls":{"Paper":"https://doi.org/10.1046/j.1365-2486.2003.00666.x"},"keyword":["*imported-from-citeulike-INRMM","~INRMM-MiD:c-164719","~to-add-doi-URL","artificial-neural-networks","climate-change","future-climatic-envelopes","generalized-additive-models","generalized-linear-models","regression-tree-analysis"],"downloads":0},"bibtype":"article","biburl":"https://tmpfiles.org/dl/58794/INRMM.bib","creationDate":"2020-07-02T22:41:31.078Z","downloads":0,"keywords":["*imported-from-citeulike-inrmm","~inrmm-mid:c-164719","~to-add-doi-url","artificial-neural-networks","climate-change","future-climatic-envelopes","generalized-additive-models","generalized-linear-models","regression-tree-analysis"],"search_terms":["biomod","optimizing","predictions","species","distributions","projecting","potential","future","shifts","under","global","change","thuiller"],"title":"BIOMOD - Optimizing Predictions of Species Distributions and Projecting Potential Future Shifts under Global Change","year":null,"dataSources":["DXuKbcZTirdigFKPF"]}