Dataset Information

Classifying development stages of primeval European beech forests: is clustering a useful tool?

ABSTRACT: BACKGROUND:Old-growth and primeval forests are passing through a natural development cycle with recurring stages of forest development. Several methods for assigning patches of different structure and size to forest development stages or phases do exist. All currently existing classification methods have in common that a priori assumptions about the characteristics of certain stand structural attributes such as deadwood amount are made. We tested the hypothesis that multivariate datasets of primeval beech forest stand structure possess an inherent, aggregated configuration of data points with individual clusters representing forest development stages. From two completely mapped primeval beech forests in Albania, seven ecologically important stand structural attributes characterizing stand density, regeneration, stem diameter variation and amount of deadwood are derived at 8216 and 9666 virtual sampling points (moving window, focal filtering). K-means clustering is used to detect clusters in the datasets (number of clusters (k) between 2 and 5). The quality of the single clustering solutions is analyzed with average silhouette width as a measure for clustering quality. In a sensitivity analysis, clustering is done with datasets of four different spatial scales of observation (200, 500, 1000 and 1500 m2, circular virtual plot area around sampling points) and with two different kernels (equal weighting of all objects within a plot vs. weighting by distance to the virtual plot center). RESULTS:The clustering solutions succeeded in detecting and mapping areas with homogeneous stand structure. The areas had extensions of more than 200 m2, but differences between clusters were very small with average silhouette widths of less than 0.28. The obtained datasets had a homogeneous configuration with only very weak trends for clustering. CONCLUSIONS:Our results imply that forest development takes place on a continuous scale and that discrimination between development stages in primeval beech forests is splitting continuous datasets at selected thresholds. For the analysis of the forest development cycle, direct quantification of relevant structural features or processes might be more appropriate than classification. If, however, the study design demands classification, our results can justify the application of conventional forest development stage classification schemes rather than clustering.

SUBMITTER: Glatthorn J

PROVIDER: S-EPMC6247681 | biostudies-other | 2018 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Classifying development stages of primeval European beech forests: is clustering a useful tool?

Glatthorn Jonas J Feldmann Eike E Tabaku Vath V Leuschner Christoph C Meyer Peter P

BMC ecology 20181120 1

<h4>Background</h4>Old-growth and primeval forests are passing through a natural development cycle with recurring stages of forest development. Several methods for assigning patches of different structure and size to forest development stages or phases do exist. All currently existing classification methods have in common that a priori assumptions about the characteristics of certain stand structural attributes such as deadwood amount are made. We tested the hypothesis that multivariate datasets ...[more]

PMID: 30458749

Similar Datasets

Project description:With the rapid growth of online property rental and sale platforms, the prevalence of fake real estate listings has become a significant concern. These deceptive listings waste time and effort for buyers and sellers and pose potential risks. Therefore, developing effective methods to distinguish genuine from fake listings is crucial. Accurately identifying fake real estate listings is a critical challenge, and clustering analysis can significantly improve this process. While clustering has been widely used to detect fraud in various fields, its application in the real estate domain has been somewhat limited, primarily focused on auctions and property appraisals. This study aims to fill this gap by using clustering to classify properties into fake and genuine listings based on datasets curated by industry experts. This study developed a K-means model to group properties into clusters, clearly distinguishing between fake and genuine listings. To assure the quality of the training data, data pre-processing procedures were performed on the raw dataset. Several techniques were used to determine the optimal value for each parameter of the K-means model. The clusters are determined using the Silhouette coefficient, the Calinski-Harabasz index, and the Davies-Bouldin index. It was found that the value of cluster 2 is the best and the Camberra technique is the best method when compared to overlapping similarity and Jaccard for distance. The clustering results are assessed using two machine learning algorithms: Random Forest and Decision Tree. The observational results have shown that the optimized K-means significantly improves the accuracy of the Random Forest classification model, boosting it by an impressive 96%. Furthermore, this research demonstrates that clustering helps create a balanced dataset containing fake and genuine clusters. This balanced dataset holds promise for future investigations, particularly for deep learning models that require balanced data to perform optimally. This study presents a practical and effective way to identify fake real estate listings by harnessing the power of clustering analysis, ultimately contributing to a more trustworthy and secure real estate market.

Project description:Objective: To develop a nutrient-rich food (NRF) score that captures dietary reference values for older adults and to validate this against a diet index that was specifically designed to assess adherence to dietary guidelines for the older population. Design: A cross-sectional study within the Dutch National Food Consumption Survey (DNFCS, n = 735 men and women aged 70-94 years, enrolled between October 2010 and February 2012) and within the NU-AGE study (n = 250 men and women aged 65-79 years, enrolled between April 2012 and March 2013). Dietary intake was assessed by means of two non-consecutive dietary record assisted 24-h recalls and 7-day food records, respectively. Structured questionnaires collected data on lifestyle and socio-economic information. Anthropometrics were measured by trained dieticians or research assistants. We evaluated Elderly NRF (E-NRF) scores against the NU-AGE index, a measure of adherence to European dietary guidelines for the aging population. The E-NRF scores were composed of nutrients that: (1) have been shown to be of inadequate intake in the aging population (>20%), (2) were defined as nutrients of public health relevance, and (3) were associated with relevant health outcomes. Results: The E-NRF score that best predicted the NU-AGE index included seven nutrients to encourage (protein, dietary fiber, folate, vitamin D, calcium, magnesium, potassium) and three nutrients to limit (saturated fat, sodium and mono- and disaccharides) on a 100-kcal basis, the E-NRF7.3 score (model R2 0.27 in DNFCS and 0.41 in NU-AGE). Food groups contributing the most to the individual E-NRF7.3 scores were vegetables, bread, potatoes and milk and milk products. Conclusion: The E-NRF7.3 score is a useful tool for assessing nutrient density of diets within the older population. No index has previously been developed with the aim of evaluating nutrient density of diets and foods specifically capturing dietary reference values for older adults.

Project description:Tropical dry forests (TDFs) are highly endangered tropical ecosystems being replaced by a complex mosaic of patches of different successional stages, agricultural fields and pasturelands. In this context, it is urgent to understand how taxa playing critical ecosystem roles respond to habitat modification. Because Phyllostomid bats provide important ecosystem services (e.g. facilitate gene flow among plant populations and promote forest regeneration), in this study we aimed to identify potential patterns on their response to TDF transformation in sites representing four different successional stages (initial, early, intermediate and late) in three Neotropical regions: México, Venezuela and Brazil. We evaluated bat occurrence at the species, ensemble (abundance) and assemblage level (species richness and composition, guild composition). We also evaluated how bat occurrence was modulated by the marked seasonality of TDFs. In general, we found high seasonal and regional specificities in phyllostomid occurrence, driven by specificities at species and guild levels. For example, highest frugivore abundance occurred in the early stage of the moistest TDF, while highest nectarivore abundance occurred in the same stage of the driest TDF. The high regional specificity of phyllostomid responses could arise from: (1) the distinctive environmental conditions of each region, (2) the specific behavior and ecological requirements of the regional bat species, (3) the composition, structure and phenological patterns of plant assemblages in the different stages, and (4) the regional landscape composition and configuration. We conclude that, in tropical seasonal environments, it is imperative to perform long-term studies considering seasonal variations in environmental conditions and plant phenology, as well as the role of landscape attributes. This approach will allow us to identify potential patterns in bat responses to habitat modification, which constitute an invaluable tool for not only bat biodiversity conservation but also for the conservation of the key ecological processes they provide.

Dataset Information

Classifying development stages of primeval European beech forests: is clustering a useful tool?

Publications

Classifying development stages of primeval European beech forests: is clustering a useful tool?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets