European Forest Types: toward an automated classification

Key messageThe outcome of the present study leads to the application of a spatially explicit rule-based expert system (RBES) algorithm aimed at automatically classifying forest areas according to the European Forest Types (EFT) system of nomenclature at pan-European scale level. With the RBES, the EFT system of nomenclature can be now easily implemented for objective, replicable, and automatic classification of field plots for forest inventories or spatial units (pixels or polygons) for thematic mapping.ContextForest Types classification systems are aimed at stratifying forest habitats. Since 2006, a common scheme for classifying European forests into 14 categories and 78 types (European Forest Types, EFT) exists.AimsThis work presents an innovative method and automated classification system that, in an objective and replicable way, can accurately classify a given forest habitat according to the EFT system of nomenclature.MethodsA rule-based expert system (RBES) was adopted as a transparent approach after comparison with the well-known Random Forest (RF) classification system. The experiment was carried out based on the information acquired in the field in 2010 ICP level I plots in 17 European countries. The accuracy of the automated classification is evaluated by comparison with an independent classification of the ICP plots into EFT carried out during the BioSoil project field survey. Finally, the RBES automated classifier was tested also for a pixel-based classification of a pan-European distribution map of beech-dominated forests.ResultsThe RBES successfully classified 94% of the plots, against a 92% obtained with RF. When applied to the mapped domain, the accuracy obtained with the RBES for the beech forest map classification was equal to 95%.ConclusionThe RBES algorithm successfully automatically classified field plots and map pixels on the basis of the EFT system of nomenclature. The EFT system of nomenclature can be now easily and objectively implemented in operative transnational European forest monitoring programs.

[1]  R. Hédl,et al.  Is sampling subjectivity a distorting factor in surveys for vegetation diversity? , 2007, Folia Geobotanica.

[2]  N. Zimmermann,et al.  Predictive mapping of alpine grasslands in Switzerland: Species versus community approach , 1999 .

[3]  Panos Panagos,et al.  European digital archive on soil maps (EuDASM): preserving important soil data for public free access , 2011, Int. J. Digit. Earth.

[4]  Frederick Hayes-Roth,et al.  Rule-based systems , 1985, CACM.

[5]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[6]  Piermaria Corona,et al.  Consolidating new paradigms in large-scale monitoring and assessment of forest ecosystems. , 2016, Environmental research.

[7]  Bing-Yuan Cao,et al.  Ecosystem Assessment and Fuzzy Systems Management , 2014 .

[8]  Antoine Guisan,et al.  Vegetation classification and biogeography of European floodplain forests and alder carrs , 2016 .

[9]  Piermaria Corona,et al.  European Mixed Forests: definition and research perspectives , 2014 .

[10]  Don Faber-Langendoen,et al.  EcoVeg: a new approach to vegetation description and classification , 2014 .

[11]  A. Lanz,et al.  State of Europe\'s forests 2015 , 2015 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Markus Lier,et al.  State of Europe\'s forests, 2011: status & trends in sustainable forest management in Europe , 2011 .

[14]  Adriana Gamazo,et al.  EURYDICE (2013): Key data on teachers and school leaders in Europe. 2013 edition Eurydice report (Luxembourg Publications Office of the European Union) , 2013 .

[15]  J. L. Parra,et al.  Very high resolution interpolated climate surfaces for global land areas , 2005 .

[16]  Simon E. Cook,et al.  A Rule-based System to Map Soil Properties , 1996 .

[17]  Hua Ouyang,et al.  Simulated distribution of vegetation types in response to climate change on the Tibetan Plateau , 2005 .

[18]  Milan Chytrý,et al.  Stratified resampling of phytosociological databases: some strategies for obtaining more representative data sets for classification studies , 2005 .

[19]  Milan Chytrý,et al.  Vegetation of the Czech Republic: diversity, ecology, history and dynamics , 2012 .

[20]  Andrew Martin,et al.  Information Systems Project Redefinition in New Zealand: Will We Ever Learn? , 1996, Aust. Comput. J..

[21]  Richard M. Lucas,et al.  an we predict habitat quality from space ? A multi-indicator ssessment based on an automated knowledge-driven system , 2014 .

[22]  Daniele de Rigo,et al.  European atlas of forest tree species , 2016 .

[23]  Ladislav Mucina,et al.  Classification of vegetation: past, present and future , 1997 .

[24]  G. Nabuurs,et al.  Statistical mapping of tree species over Europe , 2011, European Journal of Forest Research.

[25]  M. Ho,et al.  Connecting differential responses of native and invasive riparian plants to climate change and environmental alteration. , 2015, Ecological applications : a publication of the Ecological Society of America.

[26]  Milan Chytrý,et al.  Determination of diagnostic species with statistical fidelity measures , 2002 .

[27]  K. Olsen,et al.  The evolution of mapping habitat for northern spotted owls (Strix occidentalis caurina): A comparison of photo-interpreted, Landsat-based, and lidar-based habitat maps , 2015 .

[28]  Durrant Tracy,et al.  Evaluation of BioSoil Demonstration Project: Forest Biodiversity - Analysis of biodiversity module , 2011 .

[29]  Piermaria Corona,et al.  European Forest Types and Forest Europe SFM indicators: Tools for monitoring progress on forest biodiversity conservation , 2014 .

[30]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[31]  Piermaria Corona,et al.  Post-fire forest management in southern Europe: a COST action for gathering and disseminating scientific knowledge , 2010 .

[32]  Helge Bruelheide,et al.  A new measure of fidelity and its application to defining species groups , 2000 .

[33]  J. Dengler,et al.  Species constancy depends on plot size – a problem for vegetation classification and how it can be solved , 2009 .

[34]  Stephen J. Walsh,et al.  GIS and remote sensing applications in biogeography and ecology , 2001 .

[35]  Zoltán Botta-Dukát,et al.  Semi-dry grasslands along a climatic gradient across Central Europe: Vegetation classification with validation , 2007 .

[36]  Piermaria Corona,et al.  Calibration assessment of forest flammability potential in Italy , 2014 .

[37]  Janet L. Ohmann,et al.  Predictive mapping of forest composition and structure with direct gradient analysis and nearest- neighbor imputation in coastal Oregon, U.S.A. , 2002 .

[38]  Ming Chen,et al.  Classification Techniques of Neural Networks Using Improved Genetic Algorithms , 2008, 2008 Second International Conference on Genetic and Evolutionary Computing.

[39]  Piermaria Corona,et al.  Prospects for Harmonized Biodiversity Assessments Using National Forest Inventory Data , 2011 .

[40]  Zoltán Botta-Dukát,et al.  Determination of diagnostic species with statistical fidelity measures , 2002 .

[41]  Gherardo Chirici,et al.  Deadwood distribution in European forests , 2017 .

[42]  J. S. Beard,et al.  The vegetation of Western Australia at the 1:3,000,000 scale. Explanatory memoir. Second edition. , 2014 .

[43]  D. Moss,et al.  The Diversity of European Vegetation: an overview of phytosociological alliances and their relationships to EUNIS habitats , 2002 .

[44]  Stan Openshaw,et al.  Artificial intelligence in geography , 1997 .

[45]  Sabine Grunwald,et al.  Multi-criteria characterization of recent digital soil mapping and modeling approaches , 2009 .

[46]  Thomas Raus,et al.  Karte der natürlichen Vegetation Europas / Map of the Natural Vegetation of Europe - Maßstab / Scale 1:2,500,000 , 2000 .

[47]  A. Barbati,et al.  A forest typology for monitoring sustainable forest management: The case of European Forest Types , 2007 .

[48]  Matthew J. Duveneck,et al.  An imputed forest composition map for New England screened by species range boundaries , 2015 .

[49]  Ying Zhang,et al.  Knowledge-Based Approaches to Accurate Mapping of Mangroves from Satellite Data , 2004 .

[50]  John W. King,et al.  Comparison of methods for integrating biological and physical data for marine habitat mapping and classification , 2010 .

[51]  I. Vogiatzakis,et al.  A GIS-based empirical model for vegetation prediction in Lefka Ori, Crete , 2006, Plant Ecology.

[52]  Ladislav Mucina,et al.  The number of vegetation types in European countries: major determinants and extrapolation to other regions , 2014 .

[53]  María Pérez-Ortiz,et al.  Selecting patterns and features for between- and within- crop-row weed mapping using UAV-imagery , 2016, Expert Syst. Appl..

[54]  Richard M. Lucas,et al.  Combined use of expert knowledge and earth observation data for the land cover mapping of an Italian grassland area: An EODHaM system application , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[55]  M. Villani,et al.  Are the ancient forests of the Eastern Po Plain large enough for a long term conservation of herbaceous nemoral species? , 2012 .

[56]  Durrant Tracy,et al.  European Atlas Forest Tree Species , 2015 .

[57]  Jörg Ewald,et al.  A critique for phytosociology , 2003 .

[58]  Pedro Arsénio,et al.  A methodological approach to potential vegetation modeling using GIS techniques and phytosociological expert-knowledge: application to mainland Portugal , 2007 .

[59]  Hiederer Roland,et al.  Evaluation of BioSoil Demonstration Project - Preliminary Data Analysis , 2010 .

[60]  Kwong-Sak Leung,et al.  Applying fuzzy measures and nonlinear integrals in data mining , 2005, Fuzzy Sets Syst..

[61]  Daniele de Rigo,et al.  Betula pendula, Betula pubescens and other birches in Europe: distribution, habitat, usage and threats , 2016 .