Volume 21, Issue 6

The management of vegetation classifications with fuzzy clustering

Miquel De Cáceres

Centre Tecnològic Forestal de Catalunya. Ctra. antiga St. Llorenç km 2, 25280, Solsona, Catalonia, Spain.

Search for more papers by this author
Xavier Font

Department of Plant Biology, University of Barcelona, Avda. Diagonal 645, 08028 Barcelona, Catalonia, Spain.

Search for more papers by this author
Francesc Oliva

Department of Biostatistics, University of Barcelona, Avda. Diagonal 645, 08028 Barcelona, Catalonia, Spain.

Search for more papers by this author
First published: 12 August 2010
Citations: 50

De Cáceres, M.: (Corresponding author, miquelcaceres@gmail.com): Centre Tecnològic Forestal de Catalunya. Ctra. antiga St. Llorenç km 2, 25280, Solsona, Catalonia, Spain.
Font, X. (xfont@ub.edu): Department of Plant Biology, University of Barcelona, Avda. Diagonal 645, 08028 Barcelona, Catalonia, Spain.
Oliva, F. (xfont@ub.edu): Department of Biostatistics, University of Barcelona, Avda. Diagonal 645, 08028 Barcelona, Catalonia, Spain.

Co‐ordinating Editor: Dr. János Podani.

Abstract

Questions: Does fuzzy clustering provide an appropriate numerical framework to manage vegetation classifications? What is the best fuzzy clustering method to achieve this?

Material: We used 531 relevés from Catalonia (Spain), belonging to two syntaxonomic alliances of mesophytic and xerophytic montane pastures, and originally classified by experts into nine and 13 associations, respectively.

Methods: We compared the performance of fuzzy C‐means (FCM), noise clustering (NC) and possibilistic C‐means (PCM) on four different management tasks: (1) assigning new relevé data to existing types; (2) updating types incorporating new data; (3) defining new types with unclassified relevés; and (4) reviewing traditional vegetation classifications.

Results: As fuzzy classifiers, FCM fails to indicate when a given relevé does not belong to any of the existing types; NC might leave too many relevés unclassified; and PCM membership values cannot be compared. As unsupervised clustering methods, FCM is more sensitive than NC to transitional relevés and therefore produces fuzzier classifications. PCM looks for dense regions in the space of species composition, but these are scarce when vegetation data contain many transitional relevés.

Conclusions: All three models have advantages and disadvantages, although the NC model may be a good compromise between the restricted FCM model and the robust but impractical PCM model. In our opinion, fuzzy clustering might provide a suitable framework to manage vegetation classifications using a consistent operational definition of vegetation type. Regardless of the framework chosen, national/regional vegetation classification panels should promote methodological standards for classification practices with numerical tools.

Number of times cited according to CrossRef: 50

  • Alien flora across European coastal dunes, Applied Vegetation Science, 10.1111/avsc.12490, 23, 3, (317-327), (2020).
  • Reducing the arbitrary: fuzzy detection of microbial ecotones and ecosystems – focus on the pelagic environment, Environmental Microbiome, 10.1186/s40793-020-00363-w, 15, 1, (2020).
  • Vegetation richness and rarity in habitats of European conservation value in Ireland, Ecological Indicators, 10.1016/j.ecolind.2020.106387, 117, (106387), (2020).
  • Weed control in natural grasslands: A case study using a perennial native forb from the South American Campos, Austral Ecology, 10.1111/aec.12904, 0, 0, (2020).
  • Recognition and Characterization of Forest Plant Communities through Remote-Sensing NDVI Time Series, Diversity, 10.3390/d12080313, 12, 8, (313), (2020).
  • A general method for the classification of forest stands using species composition and vertical and horizontal structure, Annals of Forest Science, 10.1007/s13595-019-0824-0, 76, 2, (2019).
  • Vegetation classification at the association level under the China Vegetation Classification System: an example of six Stipa steppe formations in China, Journal of Plant Ecology, 10.1093/jpe/rtz028, 12, 6, (1009-1024), (2019).
  • Silhouette width using generalized mean—A flexible method for assessing clustering efficiency, Ecology and Evolution, 10.1002/ece3.5774, 9, 23, (13231-13243), (2019).
  • Variation in compositional and structural components of community assemblage and its determinants, Journal of Vegetation Science, 10.1111/jvs.12708, 30, 2, (257-268), (2019).
  • GRIMP: A machine‐learning method for improving groups of discriminating species in expert systems for vegetation classification, Journal of Vegetation Science, 10.1111/jvs.12696, 30, 1, (5-17), (2019).
  • Supervised versus un‐supervised classification: A quantitative comparison of plant communities in savanna vegetation, Applied Vegetation Science, 10.1111/avsc.12442, 22, 3, (373-382), (2019).
  • Patterning emergent marsh vegetation assemblages in coastal Louisiana, USA, with unsupervised artificial neural networks, Applied Vegetation Science, 10.1111/avsc.12425, 22, 2, (213-229), (2019).
  • Adapting prescribed burns to future climate change in Mediterranean landscapes, Science of The Total Environment, 10.1016/j.scitotenv.2019.04.348, 677, (68-83), (2019).
  • Temporal dimension of forest vulnerability to fire along successional trajectories, Journal of Environmental Management, 10.1016/j.jenvman.2019.109301, 248, (109301), (2019).
  • Resistance, Resilience or Change: Post-disturbance Dynamics of Boreal Forests After Insect Outbreaks, Ecosystems, 10.1007/s10021-019-00378-6, (2019).
  • Effects of the overstory on the diversity of the herb and shrub layers of Anatolian black pine forests, European Journal of Forest Research, 10.1007/s10342-018-1114-3, 137, 4, (433-445), (2018).
  • Using classification assignment rules to assess land-use change impacts on forest biodiversity at local-to-national scales, Forest Ecosystems, 10.1186/s40663-017-0121-z, 5, 1, (2018).
  • Mapping grassland plant communities using a fuzzy approach to address floristic and spectral uncertainty, Applied Vegetation Science, 10.1111/avsc.12396, 21, 4, (678-693), (2018).
  • Plant Assemblages of Abandoned Ore Mining Heaps: A Case Study from Roşia Montană Mining Area, Romania, Geographical Changes in Vegetation and Plant Functional Types, 10.1007/978-3-319-68738-4_14, (303-332), (2018).
  • Cluster Analysis, Numerical Ecology with R, 10.1007/978-3-319-71404-2_4, (59-150), (2018).
  • Synoptic weather conditions and changing fire regimes in a Mediterranean environment, Agricultural and Forest Meteorology, 10.1016/j.agrformet.2018.02.014, 253-254, (190-202), (2018).
  • A classification of the geothermal vegetation of the Taupō Volcanic Zone, New Zealand, Journal of the Royal Society of New Zealand, 10.1080/03036758.2017.1322619, 48, 1, (21-38), (2017).
  • undefined, 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 10.1109/IDAP.2017.8090183, (1-7), (2017).
  • A review of high‐mountain acidophilous vegetation in the Iberian Peninsula, Applied Vegetation Science, 10.1111/avsc.12314, 20, 3, (513-526), (2017).
  • Determining the factors affecting the distribution of Muscari latifolium, an endemic plant of Turkey, and a mapping species distribution model, Ecology and Evolution, 10.1002/ece3.2766, 7, 4, (1112-1124), (2017).
  • The Pinus halepensis Mill. forests in the central-eastern European Mediterranean basin , Plant Biosystems - An International Journal Dealing with all Aspects of Plant Biology, 10.1080/11263504.2017.1302514, 151, 3, (512-529), (2017).
  • Spatial patterns of the Iberian and Balearic endemic vascular flora, Biodiversity and Conservation, 10.1007/s10531-016-1254-z, 26, 2, (479-508), (2016).
  • Non‐native introductions influence fish body size distributions within a dryland river, Ecosphere, 10.1002/ecs2.1615, 7, 12, (2016).
  • Macrophyte assemblages in the aquatic-terrestrial transitional zone of oxbow lakes in the Danube floodplain (Austria), Folia Geobotanica, 10.1007/s12224-016-9234-3, 51, 3, (251-266), (2016).
  • Model‐based assessment of ecological community classifications, Journal of Vegetation Science, 10.1111/jvs.12400, 27, 4, (704-715), (2016).
  • Floodplain forests of the Iberian Peninsula: Vegetation classification and climatic features, Applied Vegetation Science, 10.1111/avsc.12219, 19, 2, (336-354), (2016).
  • Performance of maximum likelihood mixture models to estimate nursery habitat contributions to fish stocks: a case study on sea bream Sparus aurata , PeerJ, 10.7717/peerj.2415, 4, (e2415), (2016).
  • Vegetation classification and biogeography of European floodplain forests and alder carrs, Applied Vegetation Science, 10.1111/avsc.12201, 19, 1, (147-163), (2015).
  • Disentangling the influences of mean body size and size structure on ecosystem functioning: an example of nutrient recycling by a non‐native crayfish, Ecology and Evolution, 10.1002/ece3.1852, 6, 1, (159-169), (2015).
  • Multi-scale analysis of environmental constraints on macrophyte distribution, floristic groups and plant diversity in the Lower Paraná River floodplain, Aquatic Botany, 10.1016/j.aquabot.2015.01.006, 123, (13-25), (2015).
  • The Influence of Agricultural Abandonment and the Abiotic Environment on the Vegetation Communities of a Suburban Deciduous Forest, Castanea, 10.2179/15-055, 80, 2, (103-121), (2015).
  • A comparative framework for broad‐scale plot‐based vegetation classification, Applied Vegetation Science, 10.1111/avsc.12179, 18, 4, (543-560), (2015).
  • Drivers of contemporary landscape vegetation heterogeneity in the Canadian boreal forest: Integrating disturbances (natural and human) with climate and physical environment, Écoscience, 10.2980/21-(3-4)-3696, 21, 3-4, (340-373), (2015).
  • Modeling of Beta Diversity in Tunisian Waters: Predictions Using Generalized Dissimilarity Modeling and Bioregionalisation Using Fuzzy Clustering, PLOS ONE, 10.1371/journal.pone.0131728, 10, 7, (e0131728), (2015).
  • Semi‐supervised classification of vegetation: preserving the good old units and searching for new ones, Journal of Vegetation Science, 10.1111/jvs.12193, 25, 6, (1504-1512), (2014).
  • How does vegetation sampling in different parts of the growing season influence classification results and analyses of beta diversity?, Applied Vegetation Science, 10.1111/avsc.12087, 17, 3, (556-566), (2014).
  • A re-examination of the contributions of biofacies and geographic range to extinction risk in Ordovician graptolites, GFF, 10.1080/11035897.2013.861864, 136, 1, (38-41), (2014).
  • Recognising fuzzy vegetation pattern: the spatial prediction of floristically defined fuzzy communities using species distribution modelling methods, Journal of Vegetation Science, 10.1111/jvs.12092, 25, 2, (323-337), (2013).
  • Classification of Natural and Semi‐natural Vegetation, Vegetation Ecology, 10.1002/9781118452592, (28-70), (2013).
  • Updating vegetation classifications: an example with New Zealand's woody vegetation, Journal of Vegetation Science, 10.1111/j.1654-1103.2012.01450.x, 24, 1, (80-93), (2012).
  • Integration of fuzzy cluster analysis and kernel density estimation for tracking typhoon trajectories in the Taiwan region, Expert Systems with Applications, 10.1016/j.eswa.2012.02.114, 39, 10, (9451-9457), (2012).
  • Towards consistency in vegetation classification, Journal of Vegetation Science, 10.1111/j.1654-1103.2011.01354.x, 23, 2, (387-393), (2011).
  • Competition, invasion effects versus invasiveness and fuzzy classification, Journal of Vegetation Science, 10.1111/j.1654-1103.2010.01246.x, 22, 1, (1-5), (2011).
  • Surveying Southern Mongolia: application of multivariate classification methods in drylands with low diversity and long floristic gradients, Applied Vegetation Science, 10.1111/j.1654-109X.2011.01148.x, 14, 4, (561-570), (2011).
  • New Zealand's forest and shrubland communities: a quantitative classification based on a nationally representative plot network, Applied Vegetation Science, 10.1111/j.1654-109X.2011.01146.x, 14, 4, (506-523), (2011).

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.