One-Class Classification of Natural Vegetation Using Remote Sensing: A Review

Rapinel, Sébastien; Hubert‐Moy, Laurence

doi:10.3390/rs13101892

Cited by 13 publications

(14 citation statements)

References 154 publications

(318 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our results emphasize that this solution does not fully address this issue. Second, the quality of the binary map (presence/absence) is influenced significantly by the thresholding method used (Rapinel & Hubert‐Moy, 2021), and the under‐detection of heathland habitats among LULC classes in our study could be explained by a higher threshold. Finally, the calibration and prediction time needed (ca.…”

Section: Discussionmentioning

confidence: 79%

“…We used an OCC instead of a multiclass classifier to map heathland habitats without knowing the other habitats present in the landscape (Rapinel & Hubert‐Moy, 2021). Indeed, mapping of some habitats of interest using a multiclass classifier would have required masking areas where those habitats are expected to occur (Agrillo et al., 2021; Rapinel et al., 2021; Schindler et al., 2021).…”

Section: Discussionmentioning

confidence: 99%

“…Recently, the open access of ecological variables derived from satellite RS data and field data provides the opportunity to map the fine‐grained pattern of habitats at a national scale. Moreover, several types of products derived from RS data that characterize climate, soil, topography or vegetation phenology are available in open access at global coverage (Rapinel & Hubert‐Moy, 2021). Specifically, the 10‐m Sentinel‐2 multispectral time series can discriminate among physiognomically similar natural habitats based on their phenological profile (Tarantino et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

“…Compared to multiclassifiers, one‐class classifiers (OCCs) avoid using masks because they can classify a natural habitat regardless of other types of vegetation present in the landscape (Álvarez‐Martínez et al., 2018). OCCs have been widely used to map plant species or LULC types, but rarely to map natural habitats (Rapinel & Hubert‐Moy, 2021). Álvarez‐Martínez et al.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Large‐scale and fine‐grained mapping of heathland habitats using open‐source remote sensing data

Hubert‐Moy

Rozo

Perrin³

et al. 2022

Remote Sens Ecol Conserv

Self Cite

View full text Add to dashboard Cite

Mapping natural habitats remains challenging, especially at a national scale. Although new open-access variables for vegetation and its environment and increased spatial resolution derived from satellite remote sensing data are available at the global scale, the relevance of these new variables for fine-grained mapping of natural habitats at a national scale remains underexplored. This study aimed to map the fine-grained pattern of four heathland habitats throughout France (550 000 km 2 ). Environmental (bioclimatic, soil and topographic) and spectral (vegetation) variables derived from MODerate resolution Imaging Spectroradiometer, Advanced Spaceborne Thermal Emission and Reflection Radiometer, and Sentinel-2 satellite data were analyzed using the MaxEnt classifier. Open-access field databases were used to calibrate and validate the classification, based on the threshold-independent area under the curve (AUC) index and the conventional F1-score. For each heathland habitat, potential and actual areas were mapped using environmental and spectral variables, respectively. The results showed high classification accuracy for potential (AUC 0.92-0.99) and actual (AUC 0.88-0.99) suitability maps of the four heathland habitats. Visual interpretation of maps of the probability of occurrence indicated that the fine-grained distribution of heathland habitat was detected satisfactorily. However, although the accuracy of the crisp map of combined classifications of actual heathland habitats was high (overall accuracy 0.72), estimated producer's accuracies in terms of proportion of area were low (<0.25). This study provides the first fine-grained pattern maps of heathland habitats at a national scale, thus highlighting the value of combining environmental and spectral variables derived from open-remote sensing data and open-source field databases. These suitability maps could support the identification of heathland habitats in the framework of national conservation policies.

show abstract

Section: Discussionmentioning

confidence: 79%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Large‐scale and fine‐grained mapping of heathland habitats using open‐source remote sensing data

Hubert‐Moy

Rozo

Perrin³

et al. 2022

Remote Sens Ecol Conserv

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, the use of soil plots enabled assessing the accuracy of the map of potential wetlands [ 38 ], including crops or urban areas, which have not been considered in national inventories [ 27 , 42 , 44 , 46 ]. Many vegetation databases, such as those of the Global Biodiversity Information Facility [ 55 ] and National Forest Inventory (NFI), have been successfully used for spatial modeling of natural vegetation [ 56 ]. Soil databases have been increasingly available in recent years, especially via the GlobalSoilMap project [ 57 ].…”

Section: Introductionmentioning

confidence: 99%