Chapter 14 . Time-Series Prediction of Chlorophyll a in Lakes
279
g
a
C''''
Myponga • same day model
-
Obeerved
~N
- _. Predlcted
l!il
c '"
j ~
lä 0
g.~
~'" Cl.
g 0
~
1985
1987 1988 1989 1990 1991
1992
1993 1994 1995 1996 1997
1===1
b
C'
Myponga • 30 day model
~:i!
1
~~
c
.!!
t!il
.<:
Cl.
~
0
1985
1987 1988 1989 1990 1991
1992 1993 1994 1995 1995 1997
!\l
I=~-=I
c
Soyang • same da model
EJ;!il
:::l
- " ,
tU ~
~
.<: 0
Cl.~
E'
.2
.<: '"
0
0
1985 1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
!\l
1==1
d
Soyang • 30 day model
~lil
~
.a",
tU ~
~o
~~
.2
.<: '"
0
0
1985 1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
Fig. 14.6. Time series of observed and predicted chlorophyll a. a Myponga
same day model. b Myponga 30 day ahead model. c Soyang same day model. d
Soyang 30 day ahead model. All predictions are average model outputs using the 5
hidden node 0 error tolerance ANN structure.