94
P. Goethals . A. Dedecker . W. Gabriels . N. De Pauw
Table 6.1. Monitored variables in the Zwalm river basin.
Variables
pR
Temperature
Dissolved oxygen
Conductivity
Suspended solids
Waterlevel
Fraction of pebbles
Shadow
Water plants
Width
Flow velocity
Meandering
Rollow river beds
PoolslRiffles
Artificial embankment
structures
Units
°C
mgll
/lS/cm
mgll
cm
%
%
2 classes: 0 = absent; 1 = present
cm
mls
6 classes
(l = weil developed to 6 = absent)
6 classes
(l = weil developed to 6 = absent)
6 classes
(l = weil developed to 6 = absent)
3 classes
(0 = absent; 1 = moderate; 2 = intensive)
Macroinvertebrates were collected by means of a standard handnet (NBN 1984)
during five minute kick sampling. The objective of the sampling consists in
collecting the most representive diversity of the macroinvertebrates within the
examined site (De Pauw and Vanhooren 1983). The absence or presence of
macroinvertebrate taxa was respectively represented by 0 or 1 for use in the
different models. In total, 60 sites were monitored in the Zwalm river basin.
6.2.3
Classification Trees
Classification trees (Breiman et al. 1984), often referred to as decision trees
(Quinlan 1986) predict the value of a discrete dependent variable with a finite set
of values (called class) from the values of a set of independent variables (called
attributes), which may be either continuous or discrete. Data describing areal
system, represented in the form of a table, can be used to learn or automatically
construct adecision tree.
The common way to induce decision trees is the so-called 'Top-Down
Induction of Decision Trees' (TDIDT, Quinlan 1986). Tree construction proceeds
recursively starting with the entire set of training examples. At each step, the most
informative attribute is selected as the root of the (sub )tree and the current training
set is split into subsets according to the values of the selected attribute. For
discrete attributes, a branch of the tree is typically created for each possible value
of the attribute. For continuous attributes, a threshold is selected and two branches
P. Goethals . A. Dedecker . W. Gabriels . N. De Pauw
Table 6.1. Monitored variables in the Zwalm river basin.
Variables
pR
Temperature
Dissolved oxygen
Conductivity
Suspended solids
Waterlevel
Fraction of pebbles
Shadow
Water plants
Width
Flow velocity
Meandering
Rollow river beds
PoolslRiffles
Artificial embankment
structures
Units
°C
mgll
/lS/cm
mgll
cm
%
%
2 classes: 0 = absent; 1 = present
cm
mls
6 classes
(l = weil developed to 6 = absent)
6 classes
(l = weil developed to 6 = absent)
6 classes
(l = weil developed to 6 = absent)
3 classes
(0 = absent; 1 = moderate; 2 = intensive)
Macroinvertebrates were collected by means of a standard handnet (NBN 1984)
during five minute kick sampling. The objective of the sampling consists in
collecting the most representive diversity of the macroinvertebrates within the
examined site (De Pauw and Vanhooren 1983). The absence or presence of
macroinvertebrate taxa was respectively represented by 0 or 1 for use in the
different models. In total, 60 sites were monitored in the Zwalm river basin.
6.2.3
Classification Trees
Classification trees (Breiman et al. 1984), often referred to as decision trees
(Quinlan 1986) predict the value of a discrete dependent variable with a finite set
of values (called class) from the values of a set of independent variables (called
attributes), which may be either continuous or discrete. Data describing areal
system, represented in the form of a table, can be used to learn or automatically
construct adecision tree.
The common way to induce decision trees is the so-called 'Top-Down
Induction of Decision Trees' (TDIDT, Quinlan 1986). Tree construction proceeds
recursively starting with the entire set of training examples. At each step, the most
informative attribute is selected as the root of the (sub )tree and the current training
set is split into subsets according to the values of the selected attribute. For
discrete attributes, a branch of the tree is typically created for each possible value
of the attribute. For continuous attributes, a threshold is selected and two branches