id ftunivsavoie:oai:HAL:halsde-00377980v1
record_format openpolar
spelling ftunivsavoie:oai:HAL:halsde-00377980v1 2024-04-28T08:11:05+00:00 Statistical consensus methods for improving predictive geomorphology maps Marmion, M. Hjort, J. Thuiller, W. Luoto, M. Thule Institute University of Oulu Department of Geography Oulu Department of Geosciences and Geography Helsinki Falculty of Science Helsinki Helsingin yliopisto = Helsingfors universitet = University of Helsinki-Helsingin yliopisto = Helsingfors universitet = University of Helsinki Laboratoire d'Ecologie Alpine (LECA) Université Joseph Fourier - Grenoble 1 (UJF)-Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry )-Centre National de la Recherche Scientifique (CNRS) 2009 https://hal.science/halsde-00377980 https://doi.org/10.1016/j.cageo.2008.02.024 en eng HAL CCSD Elsevier info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cageo.2008.02.024 halsde-00377980 https://hal.science/halsde-00377980 doi:10.1016/j.cageo.2008.02.024 ISSN: 0098-3004 EISSN: 1873-7803 Computers & Geosciences https://hal.science/halsde-00377980 Computers & Geosciences, 2009, 35 (3), pp.615-625. ⟨10.1016/j.cageo.2008.02.024⟩ AUC Uncertainty Landforms Predictive modelling Adaptive regression splines climate-change species distributions terrain parameters finnish lapland models gis classification permafrost europe info:eu-repo/semantics/article Journal articles 2009 ftunivsavoie https://doi.org/10.1016/j.cageo.2008.02.024 2024-04-11T00:32:27Z International audience A variety of predictive models is currently used to map the spatial distribution of earth surface processes and landforms. In this study, we tested statistical consensus methods in order to improve the predictive accuracy of geomorphological models. The distributions of 12 geomorphological formations were recorded at a resolution of 25 ha in a sub-arctic landscape in northern Finland. Nine environmental variables were used to predict probabilities of occurrence of the formations using eight state-of-the-art modelling techniques. The probability values of the models were combined using four different consensus methods. The accuracy of the models was calculated using spatially independent test data by the area under the curve (AUC) of a receiver-operating characteristic (ROC) plot. The mean AUC values of the geomorphological models varied between 0.711 and 0.755 based on single-model techniques, whereas the corresponding values based on consensus methods ranged from 0.752 to 0.782. The weighted average consensus method had the highest predictive performance of all methods. It improved the accuracy of 11 predictions out of 12. The results of this study suggest that the consensus methods have clear advantages over single-model predictions. The simplicity of the consensus methods makes it straightforward to implement them in predictive modelling studies in geomorphology. (C) 2008 Elsevier Ltd. All rights reserved. Article in Journal/Newspaper Arctic Climate change Northern Finland permafrost Lapland Université Savoie Mont Blanc: HAL Computers & Geosciences 35 3 615 625
institution Open Polar
collection Université Savoie Mont Blanc: HAL
op_collection_id ftunivsavoie
language English
topic AUC
Uncertainty
Landforms
Predictive modelling
Adaptive regression splines
climate-change
species distributions
terrain parameters
finnish lapland
models
gis
classification
permafrost
europe
spellingShingle AUC
Uncertainty
Landforms
Predictive modelling
Adaptive regression splines
climate-change
species distributions
terrain parameters
finnish lapland
models
gis
classification
permafrost
europe
Marmion, M.
Hjort, J.
Thuiller, W.
Luoto, M.
Statistical consensus methods for improving predictive geomorphology maps
topic_facet AUC
Uncertainty
Landforms
Predictive modelling
Adaptive regression splines
climate-change
species distributions
terrain parameters
finnish lapland
models
gis
classification
permafrost
europe
description International audience A variety of predictive models is currently used to map the spatial distribution of earth surface processes and landforms. In this study, we tested statistical consensus methods in order to improve the predictive accuracy of geomorphological models. The distributions of 12 geomorphological formations were recorded at a resolution of 25 ha in a sub-arctic landscape in northern Finland. Nine environmental variables were used to predict probabilities of occurrence of the formations using eight state-of-the-art modelling techniques. The probability values of the models were combined using four different consensus methods. The accuracy of the models was calculated using spatially independent test data by the area under the curve (AUC) of a receiver-operating characteristic (ROC) plot. The mean AUC values of the geomorphological models varied between 0.711 and 0.755 based on single-model techniques, whereas the corresponding values based on consensus methods ranged from 0.752 to 0.782. The weighted average consensus method had the highest predictive performance of all methods. It improved the accuracy of 11 predictions out of 12. The results of this study suggest that the consensus methods have clear advantages over single-model predictions. The simplicity of the consensus methods makes it straightforward to implement them in predictive modelling studies in geomorphology. (C) 2008 Elsevier Ltd. All rights reserved.
author2 Thule Institute
University of Oulu
Department of Geography Oulu
Department of Geosciences and Geography Helsinki
Falculty of Science Helsinki
Helsingin yliopisto = Helsingfors universitet = University of Helsinki-Helsingin yliopisto = Helsingfors universitet = University of Helsinki
Laboratoire d'Ecologie Alpine (LECA)
Université Joseph Fourier - Grenoble 1 (UJF)-Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry )-Centre National de la Recherche Scientifique (CNRS)
format Article in Journal/Newspaper
author Marmion, M.
Hjort, J.
Thuiller, W.
Luoto, M.
author_facet Marmion, M.
Hjort, J.
Thuiller, W.
Luoto, M.
author_sort Marmion, M.
title Statistical consensus methods for improving predictive geomorphology maps
title_short Statistical consensus methods for improving predictive geomorphology maps
title_full Statistical consensus methods for improving predictive geomorphology maps
title_fullStr Statistical consensus methods for improving predictive geomorphology maps
title_full_unstemmed Statistical consensus methods for improving predictive geomorphology maps
title_sort statistical consensus methods for improving predictive geomorphology maps
publisher HAL CCSD
publishDate 2009
url https://hal.science/halsde-00377980
https://doi.org/10.1016/j.cageo.2008.02.024
genre Arctic
Climate change
Northern Finland
permafrost
Lapland
genre_facet Arctic
Climate change
Northern Finland
permafrost
Lapland
op_source ISSN: 0098-3004
EISSN: 1873-7803
Computers & Geosciences
https://hal.science/halsde-00377980
Computers & Geosciences, 2009, 35 (3), pp.615-625. ⟨10.1016/j.cageo.2008.02.024⟩
op_relation info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cageo.2008.02.024
halsde-00377980
https://hal.science/halsde-00377980
doi:10.1016/j.cageo.2008.02.024
op_doi https://doi.org/10.1016/j.cageo.2008.02.024
container_title Computers & Geosciences
container_volume 35
container_issue 3
container_start_page 615
op_container_end_page 625
_version_ 1797578652274130944