Research Methodology - Historical Land Use/Land Cover Classification Using Remote Sensing - page 84

Artificial Water bodies, Snow and Ice; and (8) Natural Water-bodies, Snow and Ice
(Di Gregorio 2005 ).
Five major classes were classified: 1, 2, 5, 6 and 8, since the classes 3, 4 and 7
did not exist in the study area ERB. A dichotomous key was applied at the major
level of classification to identify the major land cover classes (see Fig. 5.13 ).
Three classifiers were used in the dichotomous phase, i.e.: Presence of Vegetation;
Edaphic Condition; and Artificiality of Cover. ''These three classifiers were
hierarchically arranged, although independent of this arrangement, the same eight
major land cover types would be keyed out. The hierarchical arrangement is thus
not important in this phase, but was a guiding principle in the subsequent Modular-
Hierarchical Phase'' (Di Gregorio 2005 ).
This was followed by a subsequent so-called: ''(B) Modular-Hierarchical
Phase, in which land cover classes were created by the combination of sets of pre-
defined classifiers. These classifiers were tailored to each of the eight major land
cover types. The tailoring of classifiers in the second phase allowed the use of the
most appropriate classifiers to define land cover classes derived from the major
land cover types and at the same time, reduced the likelihood of impractical
combinations of classifiers'' (Di Gregorio 2005 ).
The classifiers of the pure land cover can be jointed with so-called attributes for
additional description. There are two kinds of these attributes, which form separate
levels in the classification: (Di Gregorio 2005 ): ''(1) Environmental Attributes:
these attributes (e.g., climate, landform, altitude, soils, lithology and erosion)
influence land cover but are not inherent features of it and should not be confused
with ''pure'' land cover classifiers. These attributes can be combined in any user-
defined order; and (2) Specific Technical Attributes: these attributes refer to the
technical discipline. For Semi- Natural Vegetation, the Floristic Aspect can be
added (the method on how this information was collected as well as a list of
species); for Cultivated Areas, the Crop Type can be added either according to
broad categories commonly used in statistics or by crop species; and for bare soil,
the Soil Type according to the FAO/UNESCO Revised Soil Legend can be added.
These attributes can be added freely to the pure land cover class without any
conditions''.
The LCCS is a wide-ranging, standardized a priori classification system,
designed to meet specific user requirements, and formed for mapping exercises,
free from scale factor or means used to map. Any LULC-feature well-known
overall around the world can be readily contained. The classification uses a set of
diagnostic standards that are independent and that able to allowing a correlation
with presented classifications and legends. The advantages of the classifier or
parametric approach are manifold. The system created is a highly flexible a priori
land cover classification in which each land cover class is clearly and systemati-
cally defined, thus providing internal consistency. The system is truly hierarchical
and applicable at a variety of scales. Re-arrangement of the classes based on re-
grouping of the classifiers used facilitates extensive use of the outputs by a wide
variety of end-users. Accuracy assessment of the end product can be generated by
class or by the individual classifiers forming the class. All land covers can be