Modelling and mapping the suitability of European forest formations at 1-km resolution

Stefano Casalegno; Giuseppe Amatulli; Annemarie Bastrup-Birk; Tracy Houston Durrant; Anssi Pekkarinen

doi:10.1007/s10342-011-0480-x

Modelling and mapping the suitability of European forest formations at 1-km resolution

Stefano Casalegno, Giuseppe Amatulli, Annemarie Bastrup-Birk, Tracy Houston Durrant, Anssi Pekkarinen

25 Citations (Scopus)

Abstract

Proactive forest conservation planning requires spatially accurate information about the potential distribution of tree species. The most cost-efficient way to obtain this information is habitat suitability modelling i.e. predicting the potential distribution of biota as a function of environmental factors. Here, we used the bootstrap-aggregating machine-learning ensemble classifier Random Forest (RF) to derive a 1-km resolution European forest formation suitability map. The statistical model use as inputs more than 6,000 field data forest inventory plots and a large set of environmental variables. The field data plots were classified into different forest formations using the forest category classification scheme of the European Environmental Agency. The ten most dominant forest categories excluding plantations were chosen for the analysis. Model results have an overall accuracy of 76%. Between categories scores were unbalanced and Mesophitic deciduous forests were found to be the least correctly classified forest category. The model’s variable ranking scores are used to discuss relationship between forest category/environmental factors and to gain insight into the model’s limits and strengths for map applicability. The European forest suitability map is now available for further applications in forest conservation and climate change issues.

Original language	English
Journal	European Journal of Forest Research
Volume	130
Issue number	6
Pages (from-to)	971-981
Number of pages	11
ISSN	1612-4669
DOIs	https://doi.org/10.1007/s10342-011-0480-x
Publication status	Published - Nov 2011

Access to Document

10.1007/s10342-011-0480-x

Cite this

@article{2fa9a51bc3684cfc8b40116346dc0e84,

title = "Modelling and mapping the suitability of European forest formations at 1-km resolution",

abstract = "Proactive forest conservation planning requires spatially accurate information about the potential distribution of tree species. The most cost-efficient way to obtain this information is habitat suitability modelling i.e. predicting the potential distribution of biota as a function of environmental factors. Here, we used the bootstrap-aggregating machine-learning ensemble classifier Random Forest (RF) to derive a 1-km resolution European forest formation suitability map. The statistical model use as inputs more than 6,000 field data forest inventory plots and a large set of environmental variables. The field data plots were classified into different forest formations using the forest category classification scheme of the European Environmental Agency. The ten most dominant forest categories excluding plantations were chosen for the analysis. Model results have an overall accuracy of 76%. Between categories scores were unbalanced and Mesophitic deciduous forests were found to be the least correctly classified forest category. The model{\textquoteright}s variable ranking scores are used to discuss relationship between forest category/environmental factors and to gain insight into the model{\textquoteright}s limits and strengths for map applicability. The European forest suitability map is now available for further applications in forest conservation and climate change issues.",

author = "Stefano Casalegno and Giuseppe Amatulli and Annemarie Bastrup-Birk and Durrant, {Tracy Houston} and Anssi Pekkarinen",

year = "2011",

month = nov,

doi = "10.1007/s10342-011-0480-x",

language = "English",

volume = "130",

pages = "971--981",

journal = "European Journal of Forest Research",

issn = "1612-4669",

publisher = "Springer",

number = "6",

}

TY - JOUR

T1 - Modelling and mapping the suitability of European forest formations at 1-km resolution

AU - Casalegno, Stefano

AU - Amatulli, Giuseppe

AU - Bastrup-Birk, Annemarie

AU - Durrant, Tracy Houston

AU - Pekkarinen, Anssi

PY - 2011/11

Y1 - 2011/11

N2 - Proactive forest conservation planning requires spatially accurate information about the potential distribution of tree species. The most cost-efficient way to obtain this information is habitat suitability modelling i.e. predicting the potential distribution of biota as a function of environmental factors. Here, we used the bootstrap-aggregating machine-learning ensemble classifier Random Forest (RF) to derive a 1-km resolution European forest formation suitability map. The statistical model use as inputs more than 6,000 field data forest inventory plots and a large set of environmental variables. The field data plots were classified into different forest formations using the forest category classification scheme of the European Environmental Agency. The ten most dominant forest categories excluding plantations were chosen for the analysis. Model results have an overall accuracy of 76%. Between categories scores were unbalanced and Mesophitic deciduous forests were found to be the least correctly classified forest category. The model’s variable ranking scores are used to discuss relationship between forest category/environmental factors and to gain insight into the model’s limits and strengths for map applicability. The European forest suitability map is now available for further applications in forest conservation and climate change issues.

AB - Proactive forest conservation planning requires spatially accurate information about the potential distribution of tree species. The most cost-efficient way to obtain this information is habitat suitability modelling i.e. predicting the potential distribution of biota as a function of environmental factors. Here, we used the bootstrap-aggregating machine-learning ensemble classifier Random Forest (RF) to derive a 1-km resolution European forest formation suitability map. The statistical model use as inputs more than 6,000 field data forest inventory plots and a large set of environmental variables. The field data plots were classified into different forest formations using the forest category classification scheme of the European Environmental Agency. The ten most dominant forest categories excluding plantations were chosen for the analysis. Model results have an overall accuracy of 76%. Between categories scores were unbalanced and Mesophitic deciduous forests were found to be the least correctly classified forest category. The model’s variable ranking scores are used to discuss relationship between forest category/environmental factors and to gain insight into the model’s limits and strengths for map applicability. The European forest suitability map is now available for further applications in forest conservation and climate change issues.

U2 - 10.1007/s10342-011-0480-x

DO - 10.1007/s10342-011-0480-x

M3 - Journal article

SN - 1612-4669

VL - 130

SP - 971

EP - 981

JO - European Journal of Forest Research

JF - European Journal of Forest Research

IS - 6

ER -