92
training data sets into boxplots, suitable thresholds are determined. The appropriateness of LCCS here varies with specific sites; for example, slack habitat in sand dune
ecosystems can be accurately mapped from contextual information derived from
slope (calculated using VHR LiDAR data) and can therefore be translated to habitat
from LCCS Level 3. Classifications are therefore translated from land cover to habitat after LCCS Level 3 instead of following the hierarchy to Level 4 and beyond.
Once the broad habitat baseline is mapped, thresholds become restricting as they
set clear straight lines in the feature space when classifying, therefore machine
learning techniques such as random forest and/or support vector machines are more
suitable for determining whether dominant species within broad habitat classes can
be separated and classified accurately. By classifying dominant species, condition
of habitats can be inferred. With accuracies of classifying some habitats higher than
others when implementing EO data into a monitoring system, field surveying can
never be ruled out to attain the knowledge required for the habitats directive.
However, surveying can be applied specifically to those habitats that EO data cannot
sufficiently classify.
Keywords Annex I • Habitat mapping • Land Cover Classification System •
EODHaM system • Machine-learning
Introduction
The heterogeneous nature of habitats, particularly beyond the broad habitat level,
presents complications when classifying from remotely sensed imagery, as these
habitats are often difficult to separate spectrally due to low inter-class separation
and high intra-class variability. Many classification methods are available within the
remote sensing community, which address the complexity of habitat mapping, but
conservation bodies use few of these, as the products produced by Earth Observation
(EO) are often either not detailed or accurate enough for purpose. Therefore, the
chosen methods need to be as automated as possible and readily interpreted with
simple user-defined parameters that can be adjusted easily.
This study aimed to test the ability of remote sensing to map the extents of protected habitats, and mainly those listed as Annex I (of European importance) by the
EC’s Habitat Directive (of Annex I habitats of European importance listed in the EC
Habitat’s Directive). The study site comprises terrestrial coastal habitats. The study
also tested the ability to infer habitat condition from EO data, mainly using the presence of a dominant species as a proxy for condition.
G. Jones et al.
training data sets into boxplots, suitable thresholds are determined. The appropriateness of LCCS here varies with specific sites; for example, slack habitat in sand dune
ecosystems can be accurately mapped from contextual information derived from
slope (calculated using VHR LiDAR data) and can therefore be translated to habitat
from LCCS Level 3. Classifications are therefore translated from land cover to habitat after LCCS Level 3 instead of following the hierarchy to Level 4 and beyond.
Once the broad habitat baseline is mapped, thresholds become restricting as they
set clear straight lines in the feature space when classifying, therefore machine
learning techniques such as random forest and/or support vector machines are more
suitable for determining whether dominant species within broad habitat classes can
be separated and classified accurately. By classifying dominant species, condition
of habitats can be inferred. With accuracies of classifying some habitats higher than
others when implementing EO data into a monitoring system, field surveying can
never be ruled out to attain the knowledge required for the habitats directive.
However, surveying can be applied specifically to those habitats that EO data cannot
sufficiently classify.
Keywords Annex I • Habitat mapping • Land Cover Classification System •
EODHaM system • Machine-learning
Introduction
The heterogeneous nature of habitats, particularly beyond the broad habitat level,
presents complications when classifying from remotely sensed imagery, as these
habitats are often difficult to separate spectrally due to low inter-class separation
and high intra-class variability. Many classification methods are available within the
remote sensing community, which address the complexity of habitat mapping, but
conservation bodies use few of these, as the products produced by Earth Observation
(EO) are often either not detailed or accurate enough for purpose. Therefore, the
chosen methods need to be as automated as possible and readily interpreted with
simple user-defined parameters that can be adjusted easily.
This study aimed to test the ability of remote sensing to map the extents of protected habitats, and mainly those listed as Annex I (of European importance) by the
EC’s Habitat Directive (of Annex I habitats of European importance listed in the EC
Habitat’s Directive). The study site comprises terrestrial coastal habitats. The study
also tested the ability to infer habitat condition from EO data, mainly using the presence of a dominant species as a proxy for condition.
G. Jones et al.