Developing a classifier for the Habitats Directive grassland types in Denmark using species lists for prediction

Question It is an old notion that pattern and process are linked in plant communities. Spatial pattern may, therefore, be a valuable indicator of community processes in space and time. Obviously, spatial aggregation may arise as the result of clonal propagation and short‐distance dispersal of seeds, but it is less well known how variation in the spatial aggregation links to plant community processes and to community responses to environmental stresses, such as eutrophication and acidification. We hypothesize that intra‐specific spatial aggregation may prove a useful indicator of structure and function in plant communities and, more specifically, that spatial aggregation in semi‐natural grasslands will increase with increasing eutrophication and acidification. Methods The intra‐specific spatial aggregation at the level of the community was estimated using pin‐point data for all observed species at a site with a single parameter using the PÓlya–Eggenberger distribution. Results Intra‐specific spatial aggregation correlates with biotic and abiotic gradients in the form of pH, vegetation height, species richness and species composition. The results support the hypothesis that eutrophication and acidification not only cause loss of species, but also lead to increasing intra‐specific aggregation of the component species. However, there was no significant effect of N deposition, which suggests that residual nutrients from former cultivation as well as sulphur deposition override the effect of N deposition on pH and productivity in Danish acidic grasslands. Conclusion We suggest that intra‐specific spatial aggregation may be used as an indicator of structure and function in plant communities and as a possible early warning indicator of future species loss.

Section: Vegetation Samplingmentioning

confidence: 99%

Intra‐specific spatial aggregation in acidic grasslands: effects of acidification and nitrogen deposition on spatial patterns of plant communities

Damgaard

Ejrnæs

2012

“…Pot (1997) developed an algorithm, based on the deductive method, which progresses downward from the highest hierarchical level (class) to the lowest (association or sub-association), assigning the relevés to syntaxa at the lowest level where discrimination is possible, given the species compositions of the relevés. Ejrnaes et al (2004) stress the difference between unsupervised and supervised classifications, but these are rarely distinguished in community classifications based on species composition.…”

Section: Introductionmentioning

confidence: 99%

Assignment of relevés to pre‐defined classes by supervised clustering of plant communities using a new composite index

Tongeren¹,

Gremmen²,

Hennekens

2008

Question: How does a newly designed method of supervised clustering perform in the assignment of relevé (species composition) data to a previously established classification. How do the results compare to the assignment by experts and to the assignment using a completely different numerical method? Material: Relevés analysed represent 4186 Czech grassland plots and 4990 plots from a wide variety of vegetation types (359 different associations or basal communities) in The Netherlands. For both data sets we had at our disposal an expert classification, and for the Czech data we also had available a numerical classification as well as a classification based on a neural network method (multi‐layer perceptron). Methods: Two distance indices, one qualitative and one quantitative, are combined into a single index by weighted multiplication. The composite index is a distance index for the dissimilarity between relevés and vegetation types. For both data sets the classifications by the new method were compared with the existing classifications. Results: For the Czech grasslands we correctly classified 81% of the plots to the classes of an expert classification at the alliance level and 71% to the classes of the numerical classification. Correct classification rates for the Dutch relevés were 64, 78 and 83 % for the lowest (subassociation or association), association, and alliance level, respectively. Conclusion: Our method performs well in assigning community composition records to previously established classes. Its performance is comparable to the performance of other methods of supervised clustering. Compared with a multi‐layer perceptron (a type of artificial neural network), fewer parameters have to be estimated. Our method does not need the original relevé data for the types, but uses synoptic tables. Another practical advantage is the provision of directly interpretable information on the contributions of separate species to the result.

“…However, in the existing applications, the Cocktail classifier was essentially created by experts. Fully automated procedures of supervised classification include artificial neural networks, applied to plot-based vegetation classification by Ejrnaes et al (2004) and Cern a & Chytr y (2005), and a broad range of other machine-learning algorithms (Bishop 2006;Basu et al 2009), which rarely have been applied to classify vegetation plots.…”

Section: Introductionmentioning

confidence: 99%

Semi‐supervised classification of vegetation: preserving the good old units and searching for new ones

Tichý

Chytrý

Botta‐Dukát

2014

Aim The unsupervised nature of traditional numerical methods used to classify vegetation hinders the development of comprehensive vegetation classification systems. Each new unsupervised classification yields partitions that are partly inconsistent with previous classifications and change group membership for some sites. In contrast, supervised methods account for previously established vegetation units, but cannot define new ones. Therefore, we introduce the concept of semi‐supervised classification to community ecology and vegetation science. Semi‐supervised classification formally reproduces the existing units in a supervised mode and simultaneously identifies new units among unassigned sites in an unsupervised mode. We discuss the concept of semi‐supervised clustering, introduce semi‐supervised variants of two clustering algorithms that produce groups with crisp boundaries, k‐means and partitioning around medoids (PAM), provide a free software tool to perform these classifications and demonstrate the advantages using example data sets of vegetation plots. Methods Semi‐supervised methods use a priori information about group membership for some sites to define centroids (k‐means) or medoids (PAM) of site groups that represent previously established vegetation units. They identify these groups in a species hyperspace and assign new sites to them. At the same time, they search for a user‐defined number of new groups. We compared the unsupervised, supervised and semi‐supervised methods using an example of a forest vegetation data set that was previously classified using expert knowledge, and assessed how well these methods reproduced vegetation units defined by experts. Then we compared supervised and semi‐supervised methods in a task when a grassland vegetation classification established in one country was extended to two neighbouring countries. Results and conclusions Example analyses of vegetation plot data sets demonstrated that semi‐supervised variants of k‐means and PAM are extremely valuable tools for extending existing vegetation classifications while preserving previously defined vegetation units. They can be used both for identifying so far unrecognized vegetation types in the regions where a vegetation classification already exists and for extending a vegetation classification from a particular region to neighbouring regions with partly identical but partly different vegetation types. Both k‐means and PAM provide site groups with crisp boundaries, which makes them a simpler alternative to fuzzy clustering methods.