On the Art of Classification in Spatial Ecology: Fuzziness as an Alternative for Mapping Uncertainty

Fiorentino, Dario; Lecours, Vincent; Brey, Thomas

doi:10.3389/fevo.2018.00231

Cited by 11 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though we provided several different statistical measures describing the accuracy of our predictions, covering the gap between reality and the accuracy assessment of our predicted maps remains a challenge [14]. Combining continuous models into thematic maps, as well as using substrate models to train biological models made techniques such as cross-validation impractical.…”

Section: Technical Applicationsmentioning

confidence: 99%

“…Our maps of Hoburgs Bank are intended to be living rather than static products that can be enhanced as soon as, for instance, more or better training data becomes available. However, even with future improvements (e.g., related to data quality, reduction of human error, and more sophisticated models and techniques), we will always live with some degree of uncertainty due to natural variability that our modeling will not be able to incorporate [14,58].…”

Section: Technical Applicationsmentioning

confidence: 99%

“…For example, as noted by Galparsoro et al, [1] the EUNIS classification needs to include new habitat classes and develop the classifications of less well-represented areas (e.g., deep-sea areas). Regardless of how refined such classification schemes become, they will remain a simplification of nature, for example by neglecting transitional areas, reducing local complexities (and neglecting some important feature at a local scale) and creating artefacts [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

How Do Continuous High-Resolution Models of Patchy Seabed Habitats Enhance Classification Schemes?

et al. 2019

Self Cite

View full text Add to dashboard Cite

Predefined classification schemes and fixed geographic scales are often used to simplify and cost-effectively map the spatial complexity of nature. These simplifications can however limit the usefulness of the mapping effort for users who need information across a different range of thematic and spatial resolutions. We demonstrate how substrate and biological information from point samples and photos, combined with continuous multibeam data, can be modeled to predictively map percentage cover conforming with multiple existing classification schemes (i.e., HELCOM HUB; Natura 2000), while also providing high-resolution (5 m) maps of individual substrate and biological components across a 1344 km2 offshore bank in the Baltic Sea. Data for substrate and epibenthic organisms were obtained from high-resolution photo mosaics, sediment grab samples, legacy data and expert annotations. Environmental variables included pixel and object based metrics at multiple scales (0.5 m–2 km), which improved the accuracy of models. We found that using Boosted Regression Trees (BRTs) to predict continuous models of substrate and biological components provided additional detail for each component without losing accuracy in the classified maps, compared with a thematic model. Results demonstrate the sensitivity of habitat maps to the effects of spatial and thematic resolution and the importance of high-resolution maps to management applications.

show abstract

Section: Technical Applicationsmentioning

confidence: 99%

Section: Technical Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

How Do Continuous High-Resolution Models of Patchy Seabed Habitats Enhance Classification Schemes?

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…In areas of high marsh, for instance, oysters may be partially or entirely obscured in UAS imagery. In cases with integrated habitat patches, fuzzy logic and classifications may be more representative of natural transitional zones than traditional techniques that can oversimplify complex systems by imposing discrete boundaries to habitats [46]. The area that demonstrated the most difficulty in differentiating habitats was the eastern border of the scene, which is composed of marsh habitats.…”

Section: Geobia Classificationmentioning

confidence: 99%

Quantifying Intertidal Habitat Relative Coverage in a Florida Estuary Using UAS Imagery and GEOBIA

et al. 2020

Self Cite

View full text Add to dashboard Cite

Intertidal habitats like oyster reefs and salt marshes provide vital ecosystem services including shoreline erosion control, habitat provision, and water filtration. However, these systems face significant global change as a result of a combination of anthropogenic stressors like coastal development and environmental stressors such as sea-level rise and disease. Traditional intertidal habitat monitoring techniques are cost and time-intensive, thus limiting how frequently resources are mapped in a way that is often insufficient to make informed management decisions. Unoccupied aircraft systems (UASs) have demonstrated the potential to mitigate these costs as they provide a platform to rapidly, safely, and inexpensively collect data in coastal areas. In this study, a UAS was used to survey intertidal habitats along the Gulf of Mexico coastline in Florida, USA. The structure from motion photogrammetry techniques were used to generate an orthomosaic and a digital surface model from the UAS imagery. These products were used in a geographic object-based image analysis (GEOBIA) workflow to classify mudflat, salt marsh, and oyster reef habitats. GEOBIA allows for a more informed classification than traditional techniques by providing textural and geometric context to habitat covers. We developed a ruleset to allow for a repeatable workflow, further decreasing the temporal cost of monitoring. The classification produced an overall accuracy of 79% in classifying habitats in a coastal environment with little spectral and textural separability, indicating that GEOBIA can differentiate intertidal habitats. This method allows for effective monitoring that can inform management and restoration efforts.

show abstract

“…analysed simultaneously), and various implementations of this approach have recently become available (Dunstan, Foster, & Darnell, 2011; Foster, Givens, Dornan, Dunstan, & Darnell, 2013; ter Braak, Hoijtink, Akkermans, & Verdonschot, 2003). Noted advantages of one‐stage methods are the direct ecological interpretation of bioregions and appropriate characterization of uncertainty in the distribution of bioregions (Fiorentino, Lecours, & Brey, 2018; Hill et al., 2017; Lyons et al., 2017).…”

Section: Introductionmentioning

confidence: 99%

Determining marine bioregions: A comparison of quantitative approaches

et al. 2020

View full text Add to dashboard Cite

As human pressures on natural systems increase, understanding and predicting the distribution of biodiversity has become vital for managing marine habitats. One important task is to define coherent and ecologically meaningful spatial units that can aid in planning, evaluating and implementing spatial management options. These spatial units are particularly useful for a diverse range of applications including: designing monitoring efforts, managing human activities (especially in marine protected area designation) and informing the relative scales required for ecosystem based assessments (Baker

show abstract

On the Art of Classification in Spatial Ecology: Fuzziness as an Alternative for Mapping Uncertainty

Cited by 11 publications

References 35 publications

How Do Continuous High-Resolution Models of Patchy Seabed Habitats Enhance Classification Schemes?

How Do Continuous High-Resolution Models of Patchy Seabed Habitats Enhance Classification Schemes?

Quantifying Intertidal Habitat Relative Coverage in a Florida Estuary Using UAS Imagery and GEOBIA

Determining marine bioregions: A comparison of quantitative approaches

Contact Info

Product

Resources

About