I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
2
3
8
1
~
2
3
9
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
3
8
1
-
2
3
9
1
2381
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Im
pro
v
ing
water
qua
lity pa
ra
mete
r predic
tion wi
th
multi
-
lev
el
linea
r re
g
ress
io
n
mo
del and hy
brid
f
ea
tur
e selec
tion
Alee
f
ia
K
hu
rsh
i
d,
Sa
m
rudd
hi K
o
rk
e,
Yudh
ir
K
o
t
ha
ri,
S
hruti
Alo
ne,
K
hu
s
ha
li B
a
is
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
S
h
r
i
R
a
md
e
o
b
a
b
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
N
a
g
p
u
r
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
9
,
2
0
2
4
R
ev
is
ed
Sep
2
5
,
2
0
2
4
Acc
ep
ted
Dec
1
4
,
2
0
2
4
P
re
d
ictin
g
a
n
d
m
o
d
e
li
n
g
th
e
q
u
a
li
ty
o
f
wa
ter i
s e
ss
e
n
ti
a
l
to
g
u
a
ra
n
t
e
e
th
a
t
th
e
wa
ter i
s s
a
fe
to
d
rin
k
.
T
h
e
c
h
lo
ri
n
e
c
o
n
ten
t
in
wa
ter n
e
e
d
s to
b
e
m
o
n
it
o
re
d
in
re
a
l
-
ti
m
e
to
p
ro
v
id
e
a
c
o
n
siste
n
t
su
p
p
ly
o
f
d
ri
n
k
a
b
le
wa
ter.
Ad
d
it
io
n
a
ll
y
,
p
o
tas
siu
m
a
n
d
c
h
lo
r
in
e
h
a
v
e
a
m
a
jo
r
imp
a
c
t
o
n
h
o
w
a
p
p
e
a
li
n
g
t
h
e
wa
ter
is,
a
s
th
e
y
a
re
imp
o
r
tan
t
c
o
m
p
o
n
e
n
ts
th
a
t
in
f
lu
e
n
c
e
tas
te
a
n
d
o
d
o
r
.
T
h
e
re
fo
re
,
to
e
v
a
lu
a
te
th
e
lev
e
ls
o
f
c
h
lo
ri
n
e
a
n
d
p
o
tas
siu
m
,
th
is
w
o
rk
p
re
se
n
ts
a
m
u
lt
iv
a
riab
le
l
in
e
a
r
re
g
re
ss
io
n
a
p
p
ro
a
c
h
b
a
c
k
e
d
b
y
a
h
y
b
r
i
d
fe
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
.
T
o
b
r
id
g
e
t
h
e
g
a
p
b
e
twe
e
n
t
h
e
fil
ter
a
n
d
wra
p
p
e
r
a
p
p
ro
a
c
h
e
s,
a
h
y
b
ri
d
a
p
p
r
o
a
c
h
i
s
u
se
d
to
re
m
o
v
e
u
n
n
e
c
e
ss
a
ry
in
fo
rm
a
ti
o
n
a
n
d
re
d
u
c
e
p
ro
c
e
ss
in
g
ti
m
e
a
n
d
c
o
m
p
lex
it
y
.
He
re
th
e
q
u
a
n
ti
tati
v
e
p
a
ra
m
e
ters
,
in
c
o
n
j
u
n
c
ti
o
n
with
c
a
teg
o
rica
l
p
a
ra
m
e
ters
,
a
re
in
stru
m
e
n
tal
in
e
n
a
b
li
n
g
a
c
c
u
ra
te
p
re
d
ictio
n
o
f
two
wa
ter
q
u
a
li
t
y
p
a
ra
m
e
ters
.
Th
e
two
d
e
v
e
lo
p
e
d
m
u
lt
i
-
lev
e
l
re
g
re
ss
io
n
(M
LR)
m
o
d
e
ls
fo
r
th
e
p
re
d
ictio
n
o
f
p
o
tas
siu
m
a
n
d
c
h
l
o
rid
e
a
re
u
se
f
u
l
w
h
e
n
fa
c
to
rs
a
ffe
c
ti
n
g
wa
ter
p
a
ra
m
e
ters
flu
c
tu
a
te
a
t
th
e
site
lev
e
l
a
s
we
l
l
a
s
o
v
e
r
larg
e
r
sp
a
ti
a
l
o
r
tem
p
o
ra
l
sc
a
le
s
g
iv
i
n
g
c
o
n
s
u
m
e
rs
a
v
is
u
a
l
re
p
re
s
e
n
tatio
n
o
f
h
o
w
e
a
c
h
p
a
ra
m
e
ter
in
flu
e
n
c
e
s
p
re
d
ictio
n
.
Th
e
c
o
n
v
e
rg
e
d
m
o
d
e
l
o
u
tp
e
rfo
rm
s
in
c
o
m
p
a
riso
n
with
o
th
e
r
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
wit
h
a
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
AE
)
o
f
7
.
4
2
e
-
1
5
fo
r
p
o
tas
siu
m
a
n
d
3
.
7
2
e
-
1
4
fo
r
c
h
lo
rid
e
.
K
ey
w
o
r
d
s
:
Drin
k
i
n
g
wa
ter
F
e
a
tu
re
e
x
trac
ti
o
n
M
a
c
h
in
e
lea
rn
i
n
g
M
u
lt
i
v
a
riate
li
n
e
a
r
re
g
re
ss
io
n
Wate
r
q
u
a
li
t
y
m
o
n
it
o
r
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Alee
f
ia
Kh
u
r
s
h
id
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics E
n
g
in
ee
r
in
g
,
Sh
r
i Ram
d
eo
b
a
b
a
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
an
d
M
an
ag
em
en
t
Kato
l Ro
ad
,
Nag
p
u
r
,
Ma
h
ar
as
h
tr
a,
I
n
d
ia
E
m
ail: k
h
u
r
s
h
id
aa
@
r
k
n
ec
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
W
ater
q
u
ality
p
r
eser
v
atio
n
is
p
ar
am
o
u
n
t
as
it
d
ir
ec
tly
im
p
ac
ts
th
e
h
ea
lth
an
d
well
-
b
ein
g
o
f
o
r
g
an
is
m
s
an
d
ec
o
s
y
s
tem
s
,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
t
o
id
e
n
tify
c
o
n
tam
in
an
ts
an
d
p
o
llu
tan
ts
th
at
en
d
an
g
e
r
h
u
m
an
h
ea
lth
a
n
d
th
e
en
v
ir
o
n
m
en
t.
A
cr
itical
asp
ec
t
o
f
wat
er
q
u
ality
r
ev
o
l
v
es
ar
o
u
n
d
m
o
n
ito
r
in
g
p
o
tass
iu
m
(
K)
an
d
ch
lo
r
id
e
(
C
l)
.
Fo
r
g
r
o
u
n
d
wate
r
,
a
r
a
n
g
e
o
f
3
5
–
1
2
5
m
g
/L
is
v
iewe
d
as
ty
p
ical
3
.
T
h
e
wate
r
will
tast
e
s
alty
wh
en
th
e
am
o
u
n
t
o
f
ch
lo
r
id
e
is
h
ig
h
e
r
th
an
2
5
0
–
4
0
0
m
g
/L.
Po
tass
iu
m
is
a
d
ir
ec
t
in
d
icato
r
o
f
co
n
tam
in
atio
n
.
Fo
r
g
r
o
u
n
d
wat
er
,
a
r
a
n
g
e
o
f
3
5
–
1
2
5
m
g
/L
is
r
eg
ar
d
e
d
as
ty
p
ical
[
1
]
.
T
h
e
w
ater
will
tast
e
s
alty
if
th
e
c
h
lo
r
id
e
co
n
ce
n
tr
atio
n
i
s
h
ig
h
er
th
an
2
5
0
–
4
0
0
m
g
/L.
I
n
th
o
s
e
wh
o
ar
e
v
u
ln
e
r
ab
le,
it
co
u
ld
h
av
e
s
o
m
e
n
eg
ativ
e
h
ea
lth
im
p
ac
ts
[
2
]
.
P
o
tass
iu
m
also
s
er
v
es
as
a
v
ital
n
u
tr
ien
t
ess
en
tial
f
o
r
th
e
p
r
o
p
er
f
u
n
ctio
n
in
g
o
f
f
lo
r
a,
f
a
u
n
a,
a
n
d
h
u
m
a
n
s
.
Ho
wev
er
,
elev
ate
d
p
o
tass
iu
m
l
ev
els
in
wate
r
m
ay
s
ig
n
if
y
c
o
n
tam
in
atio
n
f
r
o
m
s
o
u
r
ce
s
lik
e
ag
r
icu
ltu
r
al
r
u
n
o
f
f
o
r
in
d
u
s
tr
ial
waste,
n
ec
ess
i
tatin
g
m
o
n
ito
r
in
g
to
m
ain
tain
wate
r
q
u
ality
an
d
s
af
eg
u
ar
d
a
q
u
atic
life
an
d
p
o
tab
le
wate
r
s
u
p
p
lies
.
Similar
ly
,
ch
lo
r
i
d
e,
o
f
ten
f
o
u
n
d
in
th
e
f
o
r
m
o
f
s
o
d
iu
m
ch
lo
r
id
e
(
s
alt)
,
ca
n
b
e
h
ar
m
l
ess
at
lo
w
co
n
ce
n
tr
atio
n
s
b
u
t
p
o
s
es
r
is
k
s
at
elev
ated
lev
el
s
o
r
ig
in
atin
g
f
r
o
m
wastewate
r
d
is
ch
ar
g
e
o
r
r
o
a
d
s
alt
r
u
n
o
f
f
.
M
o
n
ito
r
in
g
ch
l
o
r
id
e
lev
els
is
cr
u
cial
t
o
p
r
o
t
ec
t
d
r
in
k
i
n
g
wate
r
s
o
u
r
ce
s
an
d
m
itig
ate
a
d
v
er
s
e
im
p
ac
ts
o
n
a
q
u
atic
ec
o
s
y
s
te
m
s
.
I
o
n
-
s
en
s
itiv
e
s
en
s
o
r
s
co
m
m
er
cially
av
ailab
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
8
1
-
2
3
9
1
2382
ar
e
co
s
tly
.
Dev
elo
p
in
g
a
s
o
f
t
s
en
s
o
r
f
o
r
ch
lo
r
id
e
o
r
p
o
tass
iu
m
in
wate
r
is
an
alter
n
ati
v
e
to
c
o
m
m
er
cially
av
ailab
le
s
en
s
o
r
s
an
d
th
er
ef
o
r
e
th
e
s
ig
n
if
ican
ce
o
f
em
p
lo
y
i
n
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ca
n
n
o
t
b
e
r
u
led
o
u
t.
M
o
n
ito
r
in
g
b
o
th
p
o
tass
iu
m
an
d
ch
l
o
r
id
e
ca
n
h
elp
in
u
n
d
er
s
tan
d
in
g
th
e
ef
f
icie
n
cy
a
n
d
im
p
ac
ts
o
f
wate
r
tr
ea
tm
en
t
p
r
o
ce
s
s
es,
s
u
ch
as
s
o
f
ten
in
g
,
d
esalin
atio
n
,
o
r
r
e
v
er
s
e
o
s
m
o
s
is
[
3
]
.
C
o
m
m
o
n
l
y
u
tili
ze
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
wate
r
q
u
ality
p
ar
am
ete
r
ass
ess
m
en
t
in
clu
d
e
d
ec
is
io
n
tr
ee
s
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
,
r
an
d
o
m
f
o
r
ests
,
an
d
s
o
p
h
is
ticated
d
ee
p
lear
n
in
g
m
e
th
o
d
s
lik
e
co
n
v
o
l
u
tio
n
al
n
eu
r
a
l
n
etwo
r
k
s
(
C
NNs
)
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs).
R
iv
er
wate
r
ch
lo
r
id
e
co
n
ce
n
t
r
atio
n
s
lead
to
r
is
in
g
s
alin
ity
,
wh
ich
also
p
o
s
es
a
h
az
ar
d
to
aq
u
atic
h
ab
itats
.
T
h
e
s
ig
n
if
ica
n
ce
o
f
r
ea
l
-
tim
e
r
iv
er
ch
lo
r
i
d
e
p
r
ed
ict
io
n
f
o
r
m
a
n
ag
in
g
an
d
c
o
n
tr
o
ll
in
g
ch
lo
r
id
e
le
v
els
h
as
d
r
awn
a
lo
t
o
f
atten
tio
n
.
Ho
wev
er
,
i
n
cr
ea
s
ed
v
alu
es
o
f
p
o
tass
iu
m
ca
n
n
o
ticea
b
l
y
af
f
e
ct
th
e
tast
e
in
wate
r
.
T
h
e
s
u
g
g
ested
d
ee
p
lear
n
in
g
m
o
d
el
in
[
4
]
b
ased
o
n
g
r
a
p
h
s
ac
q
u
ir
ed
R
2
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
v
alu
es
o
f
0
.
8
8
an
d
5
1
.
1
6
p
p
b
,
r
esp
ec
tiv
ely
.
C
o
n
d
u
ctiv
ity
,
t
em
p
er
atu
r
e,
d
is
s
o
lv
ed
o
x
y
g
en
,
PH,
an
d
tu
r
b
id
ity
ar
e
am
o
n
g
th
e
d
ep
en
d
en
t
p
ar
am
eter
s
.
Her
e
th
e
co
n
v
o
lu
tio
n
al
lay
er
s
an
d
a
p
o
o
lin
g
lay
e
r
m
ak
e
u
p
th
e
f
ee
d
-
f
o
r
war
d
s
tr
u
ct
u
r
e,
wh
ich
r
esu
l
ts
in
a
co
m
p
u
tatio
n
all
y
d
em
a
n
d
in
g
m
o
d
el
f
o
r
p
r
e
d
ictio
n
o
f
c
h
lo
r
id
e.
C
h
i
n
n
a
p
p
a
n
e
t
a
l
.
[
5
]
p
r
e
s
e
n
t
a
f
u
z
z
y
a
l
g
o
r
i
t
h
m
f
o
r
d
e
t
e
r
m
i
n
i
n
g
c
h
l
o
r
i
n
e
l
e
v
e
l
s
i
n
w
a
t
e
r
,
l
e
v
e
r
a
g
i
n
g
m
e
t
r
i
c
s
s
u
c
h
a
s
r
e
c
a
l
l
,
p
r
e
c
i
s
i
o
n
,
a
n
d
F
-
s
c
o
r
e
f
o
r
e
v
a
l
u
a
t
i
o
n
.
W
i
t
h
a
n
F
-
s
c
o
r
e
o
f
8
9
%
,
a
r
e
c
a
l
l
o
f
9
0
%
,
a
n
d
a
p
r
e
c
i
s
i
o
n
o
f
9
2
%
,
t
h
e
s
u
g
g
e
s
t
e
d
m
e
t
h
o
d
p
e
r
f
o
r
m
s
b
e
t
t
e
r
.
T
h
e
p
r
o
c
e
s
s
u
s
e
s
c
h
l
o
r
i
n
e
l
e
v
e
l
s
a
n
d
o
t
h
e
r
v
a
r
i
a
b
l
e
s
,
s
u
c
h
a
s
t
e
m
p
e
r
a
t
u
r
e
(
T
)
,
p
H
,
a
n
d
o
t
h
e
r
c
h
e
m
i
c
a
l
s
,
t
h
a
t
m
a
y
h
a
v
e
a
n
i
m
p
a
c
t
o
n
c
h
l
o
r
i
n
e
l
e
v
e
l
s
a
s
i
n
p
u
t
.
T
h
i
s
s
t
u
d
y
[
6
]
u
s
e
s
f
o
u
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
t
o
p
r
e
d
i
c
t
s
o
d
i
u
m
a
d
s
o
r
p
t
i
o
n
r
a
t
i
o
(
S
A
R
)
a
n
d
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
b
a
s
e
d
o
n
p
h
y
s
i
c
a
l
p
a
r
a
m
e
t
e
r
s
s
u
c
h
a
s
E
C
,
p
H
,
t
e
m
p
e
r
a
t
u
r
e
,
a
n
d
S
A
R
:
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
A
N
N
)
,
k
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
(k
-
N
N
)
,
a
n
d
s
t
o
c
h
a
s
t
i
c
g
r
a
d
i
e
n
t
d
e
s
c
e
n
t
(
S
G
D
)
.
T
r
a
i
n
e
d
o
n
1
7
6
s
a
m
p
l
e
s
a
n
d
v
a
l
i
d
a
t
e
d
o
n
3
7
s
a
m
p
l
e
s
f
r
o
m
M
o
r
o
c
c
o
'
s
C
h
a
o
u
i
a
c
o
a
s
t
a
l
a
q
u
i
f
e
r
,
t
h
e
m
o
d
e
l
s
d
e
m
o
n
s
t
r
a
t
e
d
a
c
c
e
p
t
a
b
l
e
t
o
g
o
o
d
p
e
r
f
o
r
m
a
n
c
e
s
.
T
h
e
b
e
s
t
c
h
l
o
r
i
d
e
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
e
x
h
i
b
i
t
R
M
S
E
r
a
n
g
i
n
g
f
r
o
m
1
.
7
4
t
o
2
.
6
7
.
T
h
e
A
N
N
a
n
d
S
G
D
m
o
d
e
l
s
,
o
f
f
e
r
i
n
g
t
h
e
h
i
g
h
e
s
t
a
c
c
u
r
a
c
y
a
n
d
s
t
a
b
i
l
i
t
y
,
h
a
d
9
5
%
c
o
n
f
i
d
e
n
c
e
b
a
n
d
s
o
f
e
r
r
o
r
a
t
1
.
3
9
f
o
r
c
h
l
o
r
i
d
e
.
T
o
im
p
r
o
v
e
m
o
d
elin
g
ac
c
u
r
ac
y
,
Z
h
a
n
g
et
a
l.
[
7
]
co
m
b
in
ed
th
e
p
er
ce
p
tr
o
n
m
o
d
el
(
ML
P)
an
d
s
tatis
t
ical
in
f
er
en
ce
m
o
d
el
(
S
C
A)
.
An
h
o
u
r
ly
r
iv
e
r
c
h
lo
r
id
e
p
r
ed
ictio
n
was
c
o
n
d
u
cted
u
s
in
g
th
e
g
r
an
d
r
iv
e
r
in
C
an
ad
a
as
a
ca
s
e
s
tu
d
y
,
an
d
th
e
m
o
d
el
p
e
r
f
o
r
m
ed
well
with
R
MSE
o
f
1
1
.
5
8
m
g
/L,
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
ta
g
e
er
r
o
r
(
MA
PE
)
o
f
2
7
.
5
5
%,
Nash
–
Su
tclif
f
e
ef
f
icien
cy
(
NSE)
o
f
0
.
9
0
,
an
d
R
2
o
f
0
.
9
0
.
T
h
e
p
r
o
v
id
ed
d
ata
to
th
e
m
o
d
el
in
cl
u
d
e
co
n
d
u
ctiv
ity
,
wate
r
tem
p
er
atu
r
e,
r
iv
er
f
lo
w
r
ate,
an
d
r
ain
f
all.
Th
e
s
tu
d
y
[
8
]
d
e
v
elo
p
s
a
n
ANN
m
o
d
el
to
p
r
ed
ict
in
cr
ea
s
ed
ch
lo
r
id
e
lev
els
f
r
o
m
r
o
ad
s
alt
i
n
a
s
u
b
u
r
b
an
wate
r
s
h
ed
u
s
in
g
m
ea
s
u
r
ed
r
ai
n
f
all
v
o
lu
m
e
an
d
f
o
u
r
o
th
e
r
p
ar
am
eter
s
(
n
itra
te,
s
u
s
p
en
d
ed
s
o
lid
s
,
tu
r
b
id
ity
,
an
d
d
is
s
o
lv
ed
o
r
g
an
ic
ca
r
b
o
n
)
.
Usi
n
g
th
r
ee
y
ea
r
s
o
f
d
ata
at
s
ix
s
ites
,
th
e
ANN
m
o
d
el,
tr
ain
ed
with
b
ac
k
p
r
o
p
a
g
atio
n
,
s
h
o
ws
a
9
1
%
f
it
b
etwe
en
o
b
s
er
v
ed
an
d
p
r
ed
icted
d
ata.
S
p
atial
an
aly
s
is
r
ev
ea
ls
h
i
g
h
er
ch
lo
r
id
e
clu
s
ter
in
g
n
ea
r
im
p
er
v
io
u
s
s
u
r
f
ac
es.
T
h
e
s
tu
d
y
s
u
g
g
ests
ANN
m
o
d
elin
g
ca
n
b
e
h
elp
f
u
l f
o
r
wate
r
q
u
ality
p
r
ed
ictio
n
,
p
ar
ticu
lar
ly
f
o
r
ch
lo
r
id
e
in
f
lu
en
ce
d
b
y
r
o
a
d
s
alt.
Go
d
o
-
Pla
et
a
l.
[
9
]
p
r
ed
icted
th
e
p
o
tass
iu
m
p
e
r
m
an
g
an
ate
d
em
an
d
f
o
r
d
r
in
k
in
g
wate
r
,
u
s
i
n
g
a
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
with
f
o
u
r
in
p
u
ts
r
esu
ltin
g
in
an
MA
E
o
f
0
.
1
2
8
m
g
·
L
−
1
.
Ar
tific
ial
n
e
u
r
al
n
etwo
r
k
s
wer
e
ex
p
lo
r
ed
in
[
1
0
]
f
o
r
esti
m
atin
g
ch
lo
r
id
e
io
n
ch
an
g
es
in
u
r
b
an
p
o
n
d
s
.
W
h
en
f
iv
e
wa
ter
q
u
ality
in
d
ices
(
C
OD
-
C
r
,
B
O
D5
,
DO,
W
S,
an
d
NO
2
)
wer
e
u
s
ed
as
in
p
u
ts
,
th
e
ANN
m
o
d
el
p
r
o
d
u
ce
d
r
e
s
u
lts
with
lo
w
er
r
o
r
v
alu
es
an
d
g
o
o
d
p
r
e
d
icted
a
cc
u
r
ac
y
with
MSE
=
4
.
9
4
,
R
M
SE
=
2
.
2
2
,
a
n
d
MA
PE
o
f
ju
s
t
3
.
4
2
%,
d
esp
ite
a
s
lig
h
tly
h
ig
h
e
r
R
2
in
th
e
en
tr
a
n
ce
zo
n
e.
I
n
t
h
is
s
tu
d
y
[
1
1
]
,
s
ev
en
h
ea
v
y
m
etal
p
ar
am
eter
s
(
Mg
,
SO4
,
K,
Na,
T
H,
C
l,
an
d
C
a)
af
f
ec
tin
g
wat
er
q
u
ality
u
s
in
g
d
ee
p
lear
n
in
g
tech
n
iq
u
es
ar
e
p
r
ed
icted
f
o
r
m
ea
s
u
r
in
g
th
e
wate
r
q
u
ality
in
d
ex
.
T
h
e
in
p
u
t
p
a
r
a
m
eter
s
tem
p
er
atu
r
e,
E
C
,
p
H,
an
d
T
DS
wer
e
d
er
iv
ed
f
r
o
m
4
9
1
wells
an
d
th
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
in
d
icate
s
R
MSE
(
tr
ain
)
o
f
8
.
1
2
an
d
R
MSE
(
test
)
o
f
1
1
.
3
6
f
o
r
p
o
tass
iu
m
(
K)
.
T
h
e
ch
l
o
r
id
e
p
r
ed
ictio
n
u
s
in
g
a
d
ee
p
n
e
u
r
al
n
etwo
r
k
(
DNN)
r
esu
lted
in
R
MSE
(
tr
ain
)
o
f
2
4
0
.
0
2
a
n
d
R
MSE
(
test
)
o
f
3
0
0
.
0
2
.
Hag
h
iab
i
et
a
l.
[
1
2
]
d
ev
el
o
p
e
d
th
e
m
o
d
el
u
s
in
g
ANN
an
d
SVM,
u
s
in
g
d
is
tin
ct
tr
an
s
f
er
an
d
k
er
n
el
f
u
n
ctio
n
s
,
r
esp
ec
tiv
ely
.
I
t
was
f
o
u
n
d
th
at
SVM
h
ad
less
d
at
a
d
is
p
er
s
io
n
th
an
th
e
ANN.
R
MSE
o
f
0
.
2
1
0
a
n
d
R
2
o
f
0
.
9
5
wer
e
o
b
tain
ed
wh
en
test
ed
SVM
f
o
r
p
r
ed
ictio
n
o
f
ch
lo
r
i
n
e.
Usi
n
g
g
r
a
d
ien
t
b
o
o
s
tin
g
m
et
h
o
d
s
t
o
b
u
ild
d
ec
is
io
n
tr
ee
s
an
d
p
r
o
d
u
ce
p
r
ed
ictio
n
s
,
th
e
s
tu
d
y
[
1
3
]
d
ev
elo
p
e
d
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
to
f
o
r
ec
ast
f
r
ee
ch
lo
r
i
n
e
r
esid
u
als.
T
h
e
p
o
s
s
ib
ilit
ies
f
o
r
m
o
n
ito
r
i
n
g
s
u
r
f
ac
e
wate
r
q
u
ality
u
s
in
g
two
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
:
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
m
o
d
els
an
d
ANNs
h
av
e
b
ee
n
ex
p
er
im
e
n
ted
in
[
1
4
]
,
[
1
5
]
.
Ho
wev
er
,
th
e
y
also
co
m
e
with
s
p
ec
if
ic
ch
allen
g
e
s
th
at
n
ee
d
to
b
e
ca
r
ef
u
lly
m
an
ag
ed
w
h
en
ap
p
lied
to
s
u
r
f
ac
e
wate
r
q
u
ality
m
o
n
ito
r
in
g
.
T
h
ese
in
clu
d
e
d
at
a
r
eq
u
ir
em
en
ts
,
tem
p
o
r
al
co
r
r
elatio
n
s
,
m
o
d
el
co
m
p
lex
ity
,
c
o
m
p
u
tatio
n
al
co
s
ts
,
an
d
th
e
a
b
ilit
y
to
g
en
e
r
alize
ac
r
o
s
s
v
ar
y
in
g
c
o
n
d
itio
n
s
.
A
l
d
r
e
e
s
e
t
a
l
.
[
1
6
]
a
r
e
o
f
t
h
e
o
p
i
n
i
o
n
t
h
a
t
t
h
e
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
s
s
h
o
u
l
d
b
e
i
n
t
e
r
p
r
e
ta
b
le
a
n
d
h
a
v
e
p
r
o
p
o
s
e
d
a
n
o
v
e
l
S
h
a
p
l
e
y
a
d
d
it
i
v
e
e
x
p
l
a
n
at
i
o
n
s
(
S
HA
P
)
t
e
c
h
n
i
q
u
e
f
o
r
p
r
e
d
i
c
t
i
n
g
w
a
t
e
r
q
u
ali
t
y
p
a
r
a
m
e
te
r
s
.
T
h
i
s
t
e
c
h
n
i
q
u
e
is
m
o
d
e
l
-
a
g
n
o
s
t
i
c
an
d
h
a
s
a
h
i
g
h
c
o
m
p
u
t
a
t
i
o
n
a
l
co
s
t
.
W
h
i
le
u
t
il
i
z
i
n
g
m
a
c
h
i
n
e
l
ea
r
n
i
n
g
w
i
t
h
b
o
o
s
t
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
mp
r
o
vin
g
w
a
ter q
u
a
lity p
a
r
a
mete
r
p
r
ed
ictio
n
w
ith
mu
lti
-
le
ve
l lin
ea
r
…
(
A
leefia
K
h
u
r
s
h
id
)
2383
t
r
e
e
s
,
Sc
h
ä
f
e
r
e
t
a
l
.
[
1
7
]
w
e
r
e
a
b
l
e
t
o
p
r
e
d
i
c
t
t
h
e
c
h
a
n
g
e
s
i
n
w
a
t
e
r
q
u
a
l
i
t
y
wi
t
h
l
es
s
t
h
a
n
1
%
e
r
r
o
r
u
s
i
n
g
t
w
o
l
o
c
a
l
a
n
d
f
i
v
e
g
l
o
b
al
f
e
at
u
r
e
s
in
c
l
u
d
i
n
g
t
i
m
e
s
t
a
m
p
.
T
h
es
e
m
o
d
e
l
s
r
e
q
u
i
r
e
s
i
g
n
i
f
i
c
a
n
t
m
e
m
o
r
y
,
w
i
t
h
m
a
n
y
t
r
e
es
.
A
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
c
e
s
t
u
d
y
i
n
[
1
8
]
h
i
g
h
l
i
g
h
t
s
t
h
e
s
i
g
n
i
f
i
c
a
n
t
im
p
a
c
t
o
f
s
p
e
ci
f
i
c
v
a
r
i
a
b
l
es
a
n
d
t
h
e
e
f
f
e
c
ti
v
e
n
e
s
s
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
ls
i
n
d
i
f
f
e
r
e
n
t
i
a
t
i
n
g
b
e
tw
e
e
n
v
a
r
i
o
u
s
p
ar
a
m
e
t
e
r
s
r
el
a
t
e
d
t
o
w
a
t
e
r
q
u
a
li
ty
.
I
n
o
r
d
er
to
ca
p
tu
r
e
th
e
co
m
p
le
x
co
r
r
elatio
n
s
am
o
n
g
wate
r
q
u
ality
p
ar
am
eter
s
,
th
e
s
tu
d
y
r
ec
o
m
m
en
d
s
u
s
in
g
th
e
h
ig
h
l
y
ac
cu
r
ate
ex
t
r
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
,
an
d
r
a
n
d
o
m
f
o
r
est
m
o
d
els
-
all
o
f
wh
ich
ar
e
co
m
p
u
tatio
n
ally
e
x
p
en
s
iv
e.
T
h
e
ad
ap
tiv
e
d
if
f
e
r
en
tial
ev
o
lu
tio
n
alg
o
r
ith
m
p
r
o
p
o
s
ed
in
s
t
u
d
y
[
1
9
]
u
s
es
th
e
r
an
k
n
u
m
b
er
s
to
d
eter
m
in
e
th
e
p
o
s
itio
n
s
o
f
v
ec
to
r
s
in
th
e
m
u
tatio
n
o
p
e
r
atio
n
f
o
r
s
o
lv
in
g
v
ar
io
u
s
n
o
n
lin
ea
r
r
eg
r
ess
io
n
p
r
o
b
lem
s
.
T
h
e
m
et
h
o
d
is
s
elf
-
ad
ap
tiv
e
b
u
t
co
m
p
u
tatio
n
in
ten
s
iv
e
T
h
e
Ma
m
d
a
n
i
f
u
zz
y
tech
n
iq
u
e
ex
ce
ls
at
ad
ap
tin
g
to
d
y
n
am
i
c
en
v
ir
o
n
m
en
tal
s
h
if
ts
[
2
0
]
i
n
o
r
d
er
t
o
m
o
n
it
o
r
cr
itical
p
ar
am
eter
s
lik
e
p
H,
tu
r
b
id
ity
,
tem
p
er
atu
r
e,
a
n
d
d
is
s
o
lv
ed
s
o
lid
s
in
s
h
r
im
p
cu
ltiv
atio
n
.
Ho
wev
er
,
im
p
l
em
en
tin
g
c
o
m
p
lex
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
ca
n
b
e
d
if
f
icu
lt,
p
ar
ticu
lar
ly
with
li
m
ited
h
ar
d
war
e
r
eso
u
r
ce
s
.
Pre
v
io
u
s
s
tu
d
ies
in
th
e
f
ield
o
f
wate
r
q
u
ality
r
esear
ch
h
av
e
ex
p
lo
r
ed
th
e
u
s
e
o
f
s
ev
er
al
m
ac
h
in
e
-
lear
n
i
n
g
ap
p
r
o
a
ch
es
to
f
o
r
ec
ast
th
e
wate
r
q
u
ality
in
d
e
x
in
d
icatin
g
th
at
wate
r
q
u
ality
m
ea
s
u
r
em
e
n
ts
ca
n
b
e
m
ad
e
with
m
u
ch
g
r
ea
ter
p
r
ec
is
io
n
d
u
e
to
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
[
2
1
]
–
[
2
4
]
.
Fu
t
u
r
e
s
tu
d
ies,
ac
co
r
d
in
g
to
th
e
r
esear
ch
team
,
s
h
o
u
l
d
lo
o
k
in
to
ex
ten
d
in
g
th
e
ap
p
licab
il
ity
d
o
m
ai
n
to
en
h
an
cin
g
p
r
e
d
ictiv
ity
.
Fro
m
th
e
liter
atu
r
e
r
ev
iew,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
els
ar
e
eith
er
co
m
p
u
tatio
n
ally
ex
p
en
s
iv
e,
d
ep
e
n
d
o
n
th
e
ap
p
r
o
p
r
iate
ch
o
ice
o
f
k
er
n
el,
lack
ac
cu
r
ac
y
an
d
i
n
ter
p
r
etab
ilit
y
,
d
ep
en
d
u
p
o
n
p
r
o
p
er
t
u
n
in
g
o
f
h
y
p
er
p
ar
a
m
eter
s
,
o
r
r
e
q
u
ir
e
m
an
y
in
p
u
t
p
ar
am
ete
r
s
f
o
r
th
e
p
r
ed
i
ctio
n
o
f
ch
lo
r
id
e
an
d
p
o
tass
iu
m
.
Few
p
r
ed
ictiv
e
f
r
am
ewo
r
k
s
tar
g
et
to
p
r
ed
ict
ch
lo
r
id
e
an
d
p
o
tass
iu
m
b
u
t r
e
q
u
ir
e
a
lar
g
e
n
u
m
b
er
o
f
in
p
u
t f
ea
tu
r
es.
I
n
o
r
d
er
to
cl
o
s
e
th
e
r
esear
ch
g
ap
,
th
e
c
u
r
r
e
n
t
wo
r
k
is
f
o
cu
s
ed
o
n
b
u
ild
in
g
a
r
eliab
le
an
d
e
x
p
lain
ab
le
p
r
ed
ictiv
e
m
o
d
el
with
f
ewe
r
i
n
p
u
t
p
ar
am
ete
r
s
th
at
m
itig
ates
th
e
af
o
r
em
en
tio
n
ed
p
r
o
b
lem
s
.
Me
m
o
r
y
u
s
ag
e
is
m
an
ag
ed
with
tech
n
iq
u
es
lik
e
f
ea
tu
r
e
s
u
b
s
am
p
lin
g
an
d
u
s
in
g
r
e
g
r
ess
io
n
tech
n
iq
u
es.
T
h
e
r
o
b
u
s
t
r
eg
r
ess
io
n
tech
n
iq
u
e
em
p
l
o
y
ed
f
o
r
th
e
p
r
esen
ted
wo
r
k
b
u
ild
s
a
m
o
d
el
th
at
ex
p
lain
s
to
u
s
er
s
h
o
w
ea
ch
p
ar
am
eter
in
f
lu
en
ce
s
p
r
ed
ictio
n
.
T
h
e
m
o
d
el
is
co
n
s
tr
u
cte
d
b
ased
o
n
a
s
u
b
s
tan
tial
d
ataset
f
r
o
m
th
e
r
i
v
er
Gan
g
a,
s
o
u
r
ce
d
f
r
o
m
th
e
“
Nam
am
i
Gan
g
a
”
p
r
o
ject,
wh
er
e
wate
r
co
n
tam
in
atio
n
ar
is
es
f
r
o
m
ef
f
lu
e
n
ts
an
d
v
ar
io
u
s
u
r
b
an
ac
tiv
ities
an
d
is
te
s
ted
f
r
o
m
d
ata
ac
q
u
ir
ed
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
.
T
h
e
co
m
b
in
atio
n
o
f
m
u
ltil
ev
el
lin
ea
r
r
eg
r
ess
io
n
m
o
d
els
an
d
h
y
b
r
id
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
en
h
an
ce
s
th
e
p
r
ed
ictio
n
o
f
wate
r
q
u
ality
p
ar
am
eter
s
,
em
p
h
asizin
g
th
e
n
o
v
elty
an
d
ef
f
ec
tiv
en
ess
o
f
th
e
ap
p
r
o
ac
h
.
I
t
is
an
ticip
ated
th
at
th
is
wo
r
k
will
ad
v
an
ce
th
e
f
ield
b
y
c
o
m
p
letin
g
t
h
e
f
o
llo
w
in
g
:
a.
Dev
elo
p
in
g
an
e
x
p
lain
ab
le
m
o
d
el
f
o
r
p
o
tass
iu
m
an
d
ch
l
o
r
id
e
co
n
ce
n
tr
atio
n
th
at
will
en
ab
le
ac
c
u
r
ate
o
u
tco
m
es b
y
u
n
d
er
s
tan
d
in
g
th
e
in
f
lu
en
ce
o
f
ea
ch
p
ar
am
eter
o
n
th
e
p
r
ed
icted
o
u
tp
u
t.
b.
E
m
p
lo
y
in
g
a
h
y
b
r
id
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
o
lo
g
y
to
e
x
a
m
in
e
th
e
s
ig
n
if
ican
ce
o
f
v
ar
i
o
u
s
in
p
u
t
f
ac
to
r
s
f
o
r
p
r
ed
ictio
n
a
n
aly
s
is
.
c.
E
s
tab
lis
h
in
g
a
f
r
am
ewo
r
k
f
o
r
th
e
cr
ea
tio
n
o
f
an
e
f
f
ec
tiv
e
h
a
r
d
war
e
im
p
lem
en
tatio
n
with
p
r
e
-
k
n
o
wled
g
e
o
f
th
e
r
eg
r
ess
io
n
co
e
f
f
icien
ts
.
T
h
e
later
s
ec
tio
n
s
also
p
r
esen
t
a
co
m
p
a
r
is
o
n
b
etwe
en
v
ar
io
u
s
m
ac
h
in
e
-
lea
r
n
in
g
al
g
o
r
ith
m
s
g
iv
en
th
eir
co
m
p
u
tatio
n
al
c
o
s
t a
n
d
ef
f
icien
cy
.
2.
M
E
T
H
O
DO
L
O
G
Y
A
m
u
lti
-
lev
el
r
eg
r
ess
io
n
m
o
d
el
is
u
s
ed
to
u
n
d
er
s
tan
d
f
ac
to
r
s
af
f
ec
tin
g
wate
r
p
ar
am
eter
s
at
s
ite
an
d
s
p
atial
lev
els
with
a
h
y
b
r
id
f
ea
tu
r
e
ex
tr
ac
tio
n
ap
p
r
o
ac
h
t
o
ac
cu
r
ately
p
r
ed
ict
wate
r
q
u
a
lity
p
ar
am
eter
s
lik
e
p
o
tass
iu
m
an
d
ch
lo
r
id
e.
T
h
e
s
tep
b
y
ap
p
r
o
ac
h
is
p
r
esen
te
d
in
Fig
u
r
e
1
.
T
h
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
is
co
m
p
iled
b
y
s
cr
a
p
p
in
g
liv
e
d
ata
f
r
o
m
th
e
“Na
m
am
i
Gan
g
a
”
p
r
o
ject,
co
n
s
is
tin
g
o
f
2
9
,
0
0
7
s
am
p
les
f
r
o
m
4
2
lo
ca
tio
n
s
o
f
r
iv
er
Gan
g
a
an
d
1
2
lo
ca
tio
n
s
in
r
iv
er
Ya
m
u
n
a
o
n
s
ea
s
o
n
al
b
asis
.
T
h
e
d
ataset
co
m
p
r
is
es
s
ev
en
teen
cr
itical
v
ar
ia
b
les,
in
clu
d
in
g
p
H,
d
is
s
o
lv
ed
o
x
y
g
en
(
DO)
,
b
io
lo
g
ical
o
x
y
g
e
n
d
em
a
n
d
(
B
OD)
,
ch
em
ical
o
x
y
g
e
n
d
em
an
d
(
C
OD)
,
tem
p
er
atu
r
e,
co
lo
r
,
to
tal
o
r
g
an
ic
ca
r
b
o
n
(
T
OC
)
,
elec
tr
ical
co
n
d
u
ctiv
ity
(
E
C
)
,
an
d
to
tal
d
is
s
o
lv
ed
s
o
lid
s
(
T
DS)
,
f
o
r
s
ix
m
o
n
th
s
.
ca
p
tu
r
in
g
v
ar
iatio
n
s
r
esu
ltin
g
f
r
o
m
wea
th
er
c
h
an
g
es
.
T
o
en
s
u
r
e
th
e
en
h
an
ce
d
q
u
ali
ty
o
f
d
ata,
p
r
e
-
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
ar
e
im
p
lem
en
te
d
.
T
h
e
p
r
o
ce
s
s
in
v
o
lv
ed
d
ata
clea
n
in
g
an
d
tr
an
s
f
o
r
m
at
io
n
in
Fig
u
r
e
1
,
wh
ich
wer
e
aim
ed
at
im
p
r
o
v
in
g
th
e
in
teg
r
ity
o
f
th
e
d
ataset.
Sp
ec
if
ically
,
th
e
lin
ea
r
s
ca
lin
g
m
eth
o
d
was
em
p
lo
y
ed
to
n
o
r
m
alize
th
e
d
ata,
r
esu
ltin
g
in
a
co
llectio
n
o
f
ap
p
r
o
x
im
ately
2
3
,
0
0
0
clea
n
an
d
tr
an
s
f
o
r
m
ed
s
am
p
les.
T
h
e
s
am
p
le
d
ata
ex
tr
ac
ted
f
r
o
m
th
e
d
atab
ase
is
p
r
esen
ted
in
T
a
b
le
1
.
2
.
1
.
Co
rr
el
a
t
io
n a
na
ly
s
is
a
n
d f
ea
t
ure
s
elec
t
io
n
I
n
ad
d
itio
n
t
o
wate
r
le
v
el,
a
c
o
r
r
elatio
n
h
ea
t
m
a
p
was
u
tili
z
ed
to
e
x
am
in
e
th
e
r
elatio
n
s
h
ip
am
o
n
g
th
e
s
ev
en
teen
p
ar
am
ete
r
s
th
at
wer
e
tak
en
in
t
o
ac
co
u
n
t.
T
o
s
im
u
late
s
ev
er
al
lear
n
in
g
m
o
d
e
ls
,
v
ar
iab
les
with
a
co
r
r
elatio
n
co
e
f
f
icien
t
g
r
ea
ter
th
an
0
.
4
we
r
e
u
s
ed
.
Fig
u
r
e
2
d
is
p
lay
s
th
e
co
r
r
elatio
n
h
ea
t
m
ap
f
o
r
th
e
o
b
tain
e
d
p
ar
am
eter
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
8
1
-
2
3
9
1
2384
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
f
o
r
f
ea
tu
r
e
s
elec
tio
n
an
d
m
o
d
el
d
esig
n
T
ab
le
1
.
Sam
p
le
d
ata
s
et
B
O
D
(
mg
/
l
)
DO
(
mg
/
l
)
C
o
n
d
u
c
t
i
v
i
t
y
(
µ
S
/
c
m)
pH
Te
mp
e
r
a
t
u
r
e
(
°
C
)
P
o
t
a
ssi
u
m
(
mg
/
l
)
C
h
l
o
r
i
d
e
(
mg
/
l
)
C
O
D
(
mg
/
l
)
TSS
(
mg
/
l
)
3
.
4
2
8
.
6
1
1
0
2
6
.
4
1
0
.
4
2
1
0
.
7
1
7
.
3
5
1
3
.
7
7
1
.
5
8
5
.
4
8
1
6
0
8
.
7
4
26
1
0
.
4
2
0
1
4
.
9
7
1
2
0
.
7
3
1
.
8
4
6
.
9
9
2
8
8
7
.
6
5
30
1
0
.
4
2
0
1
3
.
1
5
3
8
.
1
2
1
.
9
9
6
.
8
3
1
9
0
8
.
5
3
2
6
.
7
1
0
.
4
2
0
1
7
.
3
6
1
4
3
.
3
4
1
.
1
8
8
.
0
7
2
3
4
7
.
2
1
2
6
.
9
1
0
.
4
2
0
1
3
.
3
2
1
2
8
.
9
5
1
.
1
6
1
.
9
6
3
6
5
8
.
7
31
9
.
5
4
1
9
.
9
1
2
.
8
6
2
2
.
3
4
4
.
6
4
9
.
0
6
7
2
7
8
.
3
3
1
.
3
5
.
6
4
1
8
.
1
2
5
.
2
1
2
9
.
3
3
3
.
3
4
7
.
4
3
1
8
2
7
.
8
4
2
8
.
5
1
.
8
4
.
2
1
8
.
1
4
2
2
0
.
4
3
2
.
1
4
6
.
7
6
1
9
8
7
.
6
2
9
.
6
3
.
6
4
9
1
4
.
2
1
5
8
.
2
3
T
o
b
r
i
d
g
e
t
h
e
g
a
p
b
etwe
en
th
e
f
ilter
an
d
wr
ap
p
er
a
p
p
r
o
ac
h
es,
a
h
y
b
r
id
a
p
p
r
o
ac
h
is
u
s
ed
to
r
em
o
v
e
u
n
n
ec
ess
ar
y
in
f
o
r
m
atio
n
a
n
d
r
ed
u
ce
p
r
o
ce
s
s
in
g
tim
e
an
d
co
m
p
lex
ity
.
T
h
e
f
ea
tu
r
e
s
et
is
f
ilter
ed
u
s
in
g
a
co
r
r
elatio
n
h
ea
tm
ap
,
a
n
d
t
h
e
r
an
k
in
g
in
f
o
r
m
atio
n
th
at
th
e
f
ilter
m
eth
o
d
p
r
o
v
id
es
is
th
e
n
u
s
ed
to
e
v
alu
ate
t
h
e
f
ea
tu
r
es
u
s
in
g
p
a
r
ticu
lar
m
ac
h
in
e
-
lear
n
in
g
m
eth
o
d
s
in
Fig
u
r
e
1
.
C
o
n
s
id
er
in
g
t
h
e
co
r
r
elatio
n
m
ap
a
n
d
th
e
in
ter
p
lay
am
o
n
g
d
if
f
er
en
t
p
ar
am
eter
s
,
ten
p
a
r
am
eter
s
wh
ich
in
clu
d
e
B
OD,
DO,
C
OD,
p
H,
co
n
d
u
ctiv
ity
,
t
o
tal
s
u
s
p
en
d
ed
s
o
lid
s
(
T
SS
)
,
tem
p
er
atu
r
e,
T
OC
,
c
o
lo
r
an
d
tu
r
b
id
ity
wer
e
f
in
ally
u
tili
ze
d
as
i
n
p
u
ts
to
th
e
m
u
lti
-
lev
el
r
eg
r
ess
io
n
(
ML
R
)
m
o
d
el
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
mp
r
o
vin
g
w
a
ter q
u
a
lity p
a
r
a
mete
r
p
r
ed
ictio
n
w
ith
mu
lti
-
le
ve
l lin
ea
r
…
(
A
leefia
K
h
u
r
s
h
id
)
2385
Fig
u
r
e
2
.
C
o
r
r
elatio
n
h
ea
tm
a
p
2
.
2
.
M
o
del
s
elec
t
io
n a
nd
pa
ra
m
et
er
t
un
ing
Fro
m
th
e
liter
atu
r
e
r
ev
iew,
it
was
d
er
iv
ed
th
at
th
e
r
esear
ch
er
s
h
av
e
u
tili
ze
d
SVM,
ANN,
an
d
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
f
o
r
p
r
ed
i
ctin
g
th
e
wate
r
q
u
ality
p
ar
am
eter
s
.
T
h
eo
r
etica
lly
,
SVMs
ca
n
n
o
t
c
o
n
v
er
g
e
to
a
s
o
lu
tio
n
,
p
a
r
ticu
lar
ly
wh
en
d
ea
lin
g
with
n
o
is
y
d
ata.
Ad
d
it
io
n
ally
,
b
y
em
p
lo
y
in
g
a
co
ll
ab
o
r
ativ
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
th
at
is
aid
ed
b
y
n
u
m
er
o
u
s
tr
ee
s
o
f
f
er
in
g
th
eir
in
s
ig
h
ts
an
d
p
r
o
d
u
cin
g
ac
c
u
r
ate
an
d
co
n
s
is
ten
t
r
esu
lts
,
n
o
n
-
g
u
ar
an
tee
d
co
n
v
er
g
en
ce
o
f
n
e
u
r
al
n
etwo
r
k
s
ca
n
b
e
a
v
o
id
ed
.
T
h
er
e
f
o
r
e,
r
an
d
o
m
f
o
r
est,
ex
t
r
a
tr
ee
s
,
k
-
m
ea
n
s
clu
s
ter
in
g
,
an
d
d
ec
is
io
n
tr
ee
ar
e
th
e
alg
o
r
ith
m
s
th
at
h
av
e
b
ee
n
ch
o
s
en
in
th
is
co
n
te
x
t
to
p
r
o
v
id
e
r
eliab
le
f
o
r
ec
asts
in
v
ar
io
u
s
en
v
ir
o
n
m
en
ts
an
d
ex
tr
a
ct
ad
d
itio
n
al
p
er
f
o
r
m
an
ce
f
r
o
m
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
s
.
T
h
ese
alg
o
r
ith
m
s
ar
e
ch
o
s
en
b
ased
o
n
f
ac
to
r
s
lik
e
th
e
alg
o
r
ith
m
'
s
in
ter
p
r
etab
ilit
y
,
co
m
p
u
tatio
n
al
ef
f
icien
cy
in
r
eso
u
r
ce
-
c
o
n
s
tr
a
in
ed
en
v
ir
o
n
m
e
n
ts
,
an
d
a
b
ilit
y
to
h
a
n
d
le
m
u
ltiv
ar
iate
d
ata,
an
d
th
e
m
o
d
el
is
d
ev
elo
p
e
d
as
s
h
o
wn
in
Fig
u
r
e
1
.
T
wo
d
is
tin
ct
m
o
d
els
h
av
e
b
ee
n
cr
ea
ted
to
p
r
e
d
ict
K
a
n
d
C
l.
Me
tr
ics
lik
e
F
-
s
co
r
e,
ac
cu
r
ac
y
,
an
d
r
ec
all
ar
e
u
s
ed
to
co
m
p
a
r
e
p
er
f
o
r
m
an
ce
.
T
h
ese
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
o
r
m
ea
n
s
q
u
a
r
ed
e
r
r
o
r
(
MSE
)
,
p
r
o
v
id
e
a
n
u
m
e
r
ical
a
s
s
es
s
m
en
t
o
f
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
ca
n
b
e
ap
p
lied
to
e
v
alu
ate
h
o
w
well
t
h
e
s
u
g
g
ested
m
o
d
el
p
er
f
o
r
m
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
an
d
c
o
m
p
ar
es
th
e
r
esu
lts
an
d
a
n
a
ly
s
is
o
f
th
e
ev
alu
atio
n
s
o
f
t
h
e
v
a
r
io
u
s
p
r
ed
ictio
n
m
o
d
els
with
th
e
m
u
ltil
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
th
at
h
as
b
ee
n
s
u
g
g
ested
.
T
h
e
s
im
u
lated
m
ac
h
in
e
lear
n
in
g
m
o
d
els
ar
e
o
p
tim
ized
f
o
r
in
cr
ea
s
ed
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
em
p
lo
y
eit
h
er
s
u
p
er
v
is
ed
o
r
u
n
s
u
p
er
v
is
ed
lear
n
in
g
f
o
r
p
r
e
d
ictio
n
u
s
in
g
v
ar
i
o
u
s
tr
an
s
f
er
an
d
k
er
n
el
f
u
n
ctio
n
s
.
Ad
d
itio
n
ally
p
r
o
v
i
d
ed
a
r
e
th
e
f
in
d
in
g
s
f
r
o
m
th
e
p
r
e
d
ictio
n
o
f
th
e
in
ter
n
al
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
co
m
p
o
n
e
n
ts
o
f
w
ater
q
u
ality
.
3
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
I
n
th
is
s
tu
d
y
,
d
ec
is
io
n
tr
ee
,
ex
tr
a
tr
ee
,
r
an
d
o
m
f
o
r
est,
ANN,
ML
R
,
m
o
d
els
ar
e
u
s
ed
f
o
r
th
e
esti
m
atio
n
o
f
K
an
d
C
l
in
r
iv
e
r
wate
r
.
T
h
e
d
ata
s
et
was
p
ar
titi
o
n
ed
f
o
r
tr
ain
in
g
an
d
v
alid
ati
o
n
an
d
v
er
if
icatio
n
p
u
r
p
o
s
es.
Mu
ltil
in
ea
r
r
eg
r
ess
io
n
:
I
ts
b
asis
is
th
e
lin
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
in
p
u
ts
an
d
o
u
tp
u
ts
.
T
h
is
ex
tr
ac
ts
th
e
lin
ea
r
co
r
r
elatio
n
s
b
etwe
e
n
th
e
d
ep
en
d
en
t
an
d
in
d
ep
en
d
en
t
v
ar
iab
les
u
s
in
g
a
co
n
s
ta
n
t
r
eg
r
ess
io
n
in
th
e
f
o
r
m
u
la
[
2
5
]
.
T
h
e
e
q
u
atio
n
b
e
lo
w
is
th
e
b
asis
o
f
ML
R
wo
r
k
:
y
=
0
+
1
2
+
⋯
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
8
1
-
2
3
9
1
2386
wh
er
e
is
th
e
in
d
ep
en
d
e
n
t v
ar
i
ab
le
,
is
th
e
r
eg
r
ess
io
n
co
n
s
tan
t
,
is
th
e
th
p
r
ed
icto
r
.
a.
R
an
d
o
m
f
o
r
est
(
R
F)
:
T
h
e
m
ai
n
m
eth
o
d
u
s
ed
in
th
is
ap
p
r
o
ac
h
is
s
u
p
er
v
is
ed
lear
n
i
n
g
.
Fo
r
e
ac
h
tr
ain
in
g
s
et
o
f
d
ata,
t
h
is
alg
o
r
ith
m
will
c
r
ea
te
a
d
ec
is
io
n
tr
ee
.
A
tr
ee
d
o
es
not
n
ee
d
an
y
f
ea
tu
r
es
to
b
e
tak
e
n
in
to
ac
co
u
n
t
b
ec
a
u
s
e
it
is
a
co
n
ce
p
tu
al
co
n
s
tr
u
ct.
As
a
r
esu
lt,
t
h
er
e
is
less
f
ea
tu
r
e
s
p
ac
e.
T
h
e
f
in
al
p
r
e
d
ictio
n
f
o
r
r
e
g
r
ess
io
n
task
s
is
ca
lcu
lated
b
y
a
v
er
ag
in
g
th
e
p
r
ed
ictio
n
s
m
ad
e
b
y
ea
c
h
tr
ee
[
2
6
]
–
[
2
8
]
.
b.
Dec
is
io
n
t
r
ee
(
DT
)
:
I
t
c
o
n
s
is
ts
o
f
a
s
in
g
le
d
ec
is
io
n
tr
ee
th
at
ca
n
b
e
tr
ain
e
d
.
T
h
e
p
r
ed
ict
io
n
is
f
ast
as
it
ad
ap
ts
q
u
ick
ly
t
o
th
e
d
ataset
b
u
t is m
o
r
e
s
u
s
ce
p
tib
le
to
o
u
tlier
s
.
c.
E
x
tr
a
tr
ee
:
I
t
g
en
e
r
ates
a
lar
g
e
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
s
,
b
u
t th
er
e
is
n
o
r
ep
lace
m
e
n
t
in
th
e
r
an
d
o
m
s
am
p
le
f
o
r
ea
ch
tr
ee
.
A
f
ea
t
u
r
e'
s
u
n
iq
u
en
ess
is
d
eter
m
in
ed
b
y
a
r
an
d
o
m
s
elec
tio
n
o
f
its
s
p
litt
in
g
v
alu
e
to
ca
lcu
late
a
lo
ca
lly
o
p
tim
al
v
al
u
e.
T
h
e
tr
ee
s
b
ec
o
m
e
d
iv
e
r
s
e
an
d
u
n
co
r
r
elate
d
as a
r
esu
lt.
d.
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
A
NN)
:
ANNs
ar
e
weig
h
ted
f
e
ed
f
o
r
war
d
lin
k
e
d
n
etwo
r
k
s
o
f
n
eu
r
o
n
s
with
weig
h
ted
co
n
n
ec
tio
n
s
.
T
h
e
n
e
u
r
o
n
s
a
r
e
ar
r
an
g
e
d
in
lay
er
s
,
wh
er
e
an
in
p
u
t
lay
e
r
co
r
r
esp
o
n
d
s
to
a
ce
r
tain
in
p
u
t
d
ata
v
ec
to
r
a
n
d
an
o
u
t
p
u
t
lay
er
y
ield
s
th
e
r
eg
r
ess
io
n
'
s
r
esu
lt.
T
h
e
p
e
r
f
o
r
m
an
ce
an
aly
s
is
f
o
r
t
h
e
ev
alu
atio
n
m
etr
ics
(
MSE
)
o
f
th
e
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
d
is
cu
s
s
ed
ab
o
v
e
f
o
r
p
o
tass
iu
m
(
K)
an
d
ch
lo
r
id
e
(
C
l)
ar
e
s
tated
in
T
ab
le
s
2
an
d
3
.
Fro
m
th
e
T
ab
les
2
an
d
3
,
it
is
ev
id
en
t
th
at
m
u
ltil
in
ea
r
r
eg
r
e
s
s
io
n
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
o
th
er
s
tated
m
o
d
els
with
ten
in
p
u
t
p
ar
am
eter
s
b
o
t
h
f
o
r
K
an
d
C
L
.
T
h
e
o
u
tp
u
t
e
q
u
atio
n
f
o
r
ML
R
with
ten
in
p
u
t
p
ar
am
ete
r
s
is
as
s
tated
in
(
2
)
,
=
ℎ0
+
ℎ1
1
+
ℎ2
2
+
ℎ3
3
+
ℎ4
4
+
ℎ5
5
+
ℎ6
6
+
ℎ7
7
+
ℎ8
8
+
ℎ9
9
+
ℎ10
10
(
2
)
T
ab
le
2
.
Per
f
o
r
m
a
n
ce
o
f
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
f
o
r
p
o
t
ass
iu
m
lev
el
p
r
ed
ictio
n
S
r
.
N
o
I
n
p
u
t
p
a
r
a
me
t
e
r
M
S
E
v
a
l
u
e
A
l
g
o
r
i
t
h
m
1.
B
o
d
,
C
o
d
,
c
o
l
o
r
1
4
.
4
9
R
a
n
d
o
m
f
o
r
e
s
t
2.
B
o
d
,
C
o
d
,
c
o
l
o
r
3
.
2
9
Ex
t
r
a
t
r
e
e
s
3.
B
o
d
,
C
o
d
,
c
o
l
o
r
5
1
.
8
4
D
e
c
i
s
i
o
n
t
r
e
e
w
i
t
h
P
C
A
4.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
p
H
9
9
.
9
1
D
e
c
i
s
i
o
n
t
r
e
e
5.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
7
3
.
6
1
D
e
c
i
s
i
o
n
t
r
e
e
6.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
c
o
n
d
u
c
t
i
v
i
t
y
9
2
.
2
6
D
e
c
i
s
i
o
n
t
r
e
e
7.
B
o
d
,
C
o
d
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
8
2
.
9
7
D
e
c
i
s
i
o
n
t
r
e
e
8.
B
o
d
,
C
o
d
,
c
o
n
d
u
c
t
i
v
i
t
y
,
t
e
m
p
e
r
a
t
u
r
e
5
6
.
9
7
D
e
c
i
s
i
o
n
t
r
e
e
9.
B
o
d
,
C
o
d
,
c
o
n
d
u
c
t
i
v
i
t
y
,
t
e
m
p
e
r
a
t
u
r
e
,
p
H
4
1
.
2
1
D
e
c
i
s
i
o
n
t
r
e
e
1
0
.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
p
H
0
.
8
6
0
3
ANN
1
1
.
B
O
D
,
D
O
,
C
o
d
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
,
TS
S
,
t
e
mp
e
r
a
t
u
r
e
,
TO
C
,
c
o
l
o
r
,
t
u
r
b
i
d
i
t
y
7
.
1
3
e
-
29
M
A
E:
7
.
4
2
e
-
15
M
L
R
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
f
o
r
ch
l
o
r
id
e
lev
el
p
r
ed
ictio
n
S
r
.
N
o
I
n
p
u
t
p
a
r
a
me
t
e
r
M
S
E
v
a
l
u
e
A
l
g
o
r
i
t
h
m
1.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
D
o
3
0
.
3
0
R
a
n
d
o
m F
o
r
e
s
t
2.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
D
o
1
8
.
9
4
Ex
t
r
a
Tr
e
e
s
3.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
D
o
6
.
8
8
D
e
c
i
s
i
o
n
Tr
e
e
w
i
t
h
P
C
A
4.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
p
H
1
2
9
7
.
6
3
D
e
c
i
s
i
o
n
Tr
e
e
5.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
1
1
9
9
.
8
8
D
e
c
i
s
i
o
n
Tr
e
e
6.
B
o
d
,
C
o
d
,
c
o
l
o
r
,
c
o
n
d
u
c
t
i
v
i
t
y
1
1
3
1
.
9
1
D
e
c
i
s
i
o
n
t
r
e
e
7.
B
o
d
,
C
o
d
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
1
1
8
2
.
9
7
D
e
c
i
s
i
o
n
Tr
e
e
8.
B
o
d
,
C
o
d
,
c
o
n
d
u
c
t
i
v
i
t
y
,
t
e
m
p
e
r
a
t
u
r
e
1
1
0
9
.
2
7
D
e
c
i
s
i
o
n
t
r
e
e
9.
B
o
d
,
C
o
d
,
c
o
n
d
u
c
t
i
v
i
t
y
,
p
H
1
.
5
0
0
8
ANN
1
0
.
B
O
D
,
D
O
,
C
O
D
,
p
H
,
c
o
n
d
u
c
t
i
v
i
t
y
,
T
S
S
,
Te
mp
e
r
a
t
u
r
e
,
TO
C
,
c
o
l
o
r
,
t
u
r
b
i
d
i
t
y
1
.
5
8
e
-
27
M
A
E:
3
.
7
2
e
-
14
M
L
R
T
h
e
co
ef
f
icien
ts
ar
e
s
tated
in
th
e
T
ab
le
s
4
an
d
5
.
I
t
ca
n
b
e
co
n
clu
d
ed
t
h
at
th
e
co
n
d
u
ctiv
ity
h
as
a
s
tatis
t
ically
s
ig
n
if
ican
t
p
o
s
iti
v
e
ef
f
ec
t
o
n
p
o
tass
iu
m
co
n
c
en
tr
atio
n
in
wate
r
.
T
h
is
alig
n
s
with
th
e
p
h
y
s
ical
u
n
d
er
s
tan
d
i
n
g
th
at
p
o
tass
iu
m
io
n
s
co
n
tr
ib
u
te
to
th
e
o
v
er
all
i
o
n
ic
s
tr
en
g
th
an
d
th
u
s
th
e
co
n
d
u
ctiv
ity
o
f
wate
r
.
Als
o
,
th
e
in
d
ep
en
d
en
t
v
ar
iab
l
es
ar
e
n
o
t
h
ig
h
ly
co
r
r
elate
d
with
ea
ch
o
th
er
in
d
icatin
g
a
s
ta
b
le
m
o
d
el.
Als
o
,
th
e
ch
an
g
es
in
p
H
ar
e
a
s
ig
n
if
ican
t
p
r
ed
icto
r
o
f
ch
an
g
es
in
ch
l
o
r
id
e
co
n
ce
n
tr
atio
n
.
T
h
is
alig
n
s
with
th
e
ch
em
ical
u
n
d
er
s
tan
d
i
n
g
th
at
p
H
ca
n
af
f
ec
t
th
e
s
o
lu
b
ilit
y
an
d
d
is
s
o
ciatio
n
o
f
c
h
lo
r
id
e
-
co
n
tain
in
g
co
m
p
o
u
n
d
s
,
th
er
e
b
y
in
f
lu
en
cin
g
ch
l
o
r
id
e
lev
els in
wate
r
.
T
h
u
s
,
b
y
ex
am
in
in
g
th
e
m
ag
n
itu
d
e
an
d
s
ig
n
o
f
th
e
co
ef
f
icien
ts
,
u
s
er
s
ca
n
d
eter
m
in
e
wh
ich
f
ea
tu
r
es
ar
e
m
o
s
t
im
p
o
r
tan
t
f
o
r
th
e
p
r
ed
i
ctio
n
.
T
h
is
h
elp
s
in
u
n
d
er
s
tan
d
in
g
wh
ich
wate
r
q
u
ality
p
ar
am
ete
r
s
h
av
e
th
e
m
o
s
t sig
n
if
ican
t im
p
ac
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
mp
r
o
vin
g
w
a
ter q
u
a
lity p
a
r
a
mete
r
p
r
ed
ictio
n
w
ith
mu
lti
-
le
ve
l lin
ea
r
…
(
A
leefia
K
h
u
r
s
h
id
)
2387
T
ab
le
4
.
C
o
n
v
er
g
ed
ML
R
co
e
f
f
icien
ts
f
o
r
p
o
tass
iu
m
lev
el
p
r
ed
ictio
n
I
n
t
e
r
c
e
p
t
h0
5
.
8
5
3
8
7
2
5
9
6
B
O
D
(
mg
/
l
)
h1
0
.
2
2
3
6
0
6
0
8
4
D
O
(
mg
/
l
)
h2
0
.
0
1
1
4
4
3
7
8
4
C
O
D
(
mg
/
l
)
h3
0
.
0
6
3
1
1
7
2
8
3
pH
h4
0
.
2
0
0
9
4
6
1
4
9
C
o
n
d
u
c
t
i
v
i
t
y
(
µ
S
/
c
m)
h5
1
.
8
8
8
4
7
E
-
05
TSS
(
mg
/
l
)
h6
-
0
.
0
0
5
2
3
8
8
2
7
Te
mp
e
r
a
t
u
r
e
(
°
C
)
h7
0
.
0
3
2
7
5
8
3
7
6
TO
C
(
m
g
/
l
)
h8
-
0
.
1
0
1
3
0
6
5
5
1
C
o
l
o
r
(
P
t
.
S
c
a
l
e
,
H
z
u
n
i
t
s)
h9
0
.
0
0
8
6
3
7
2
6
1
Tu
r
b
i
d
i
t
y
(
N
TU
)
h
1
0
-
0
.
0
0
6
0
5
5
8
5
8
T
ab
le
5
C
o
n
v
e
r
g
ed
ML
R
co
e
f
f
icien
ts
f
o
r
ch
lo
r
id
e
lev
el
p
r
ed
ictio
n
I
n
t
e
r
c
e
p
t
h0
-
1
8
.
3
2
1
9
5
5
9
1
B
O
D
(
mg
/
l
)
h1
1
.
3
3
8
6
0
2
4
1
9
D
O
(
mg
/
l
)
h2
-
0
.
6
7
0
6
6
5
5
1
5
C
O
D
(
mg
/
l
)
h3
0
.
2
8
6
5
0
9
3
1
2
pH
h4
3
.
2
8
9
3
4
6
0
1
4
C
o
n
d
u
c
t
i
v
i
t
y
(
µ
S
/
c
m)
h5
-
3
.
9
1
1
0
8
E
-
06
TSS
(
mg
/
l
)
h6
-
0
.
0
1
5
8
6
3
5
7
4
Te
mp
e
r
a
t
u
r
e
(
Â
°
C
)
h7
0
.
1
7
9
0
6
3
5
3
TO
C
(
m
g
/
l
)
h8
-
0
.
5
0
8
0
4
6
4
2
1
C
o
l
o
r
(
P
t
.
S
c
a
l
e
,
H
z
u
n
i
t
s)
h9
0
.
0
3
7
1
7
8
4
8
4
Tu
r
b
i
d
i
t
y
(
N
TU
)
h
1
0
0
.
0
1
2
3
8
7
7
5
3
T
h
e
Fig
u
r
e
3
in
d
icate
s
th
e
p
l
o
t
o
f
p
r
ed
icted
a
n
d
ac
tu
al
v
al
u
es
o
f
p
o
tass
iu
m
(
K)
f
o
r
th
e
m
u
ltil
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
in
d
icativ
e
o
f
th
e
g
o
o
d
f
it.
T
h
e
Fig
u
r
e
4
in
d
icate
s
th
e
p
lo
t
o
f
p
r
ed
icted
a
n
d
ac
tu
al
v
alu
es
o
f
ch
lo
r
id
e
(
C
l)
f
o
r
th
e
m
u
ltil
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
wh
ile
t
esti
n
g
.
B
o
th
th
e
m
o
d
els
s
tr
ik
e
a
g
o
o
d
b
alan
ce
b
etwe
en
b
ias
an
d
v
ar
ian
ce
,
av
o
id
in
g
u
n
d
er
f
itti
n
g
an
d
o
v
e
r
f
it
tin
g
.
T
h
e
r
ef
o
r
e,
th
e
in
d
e
p
en
d
e
n
t
v
ar
iab
les
c
h
o
s
en
ar
e
r
elev
an
t
a
n
d
h
a
v
e
a
s
tr
o
n
g
r
elatio
n
s
h
ip
with
th
e
d
ep
en
d
en
t
v
ar
iab
le
in
d
icatin
g
a
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
r
elatio
n
s
h
ip
s
id
en
tifie
d
b
y
th
e
m
o
d
el
a
r
e
s
tatis
ticall
y
s
ig
n
if
ican
t
with
a
p
-
v
alu
e
less
th
an
0
.
0
5
.
T
h
e
T
ab
le
6
p
r
esen
ts
a
co
m
p
ar
is
o
n
o
f
wo
r
k
p
u
b
lis
h
ed
b
y
o
th
er
r
esear
ch
er
s
f
o
r
th
e
p
r
e
d
ictio
n
o
f
h
ea
v
y
m
etals
ch
lo
r
id
e
a
n
d
p
o
tass
iu
m
.
I
t
ca
n
b
e
c
o
n
clu
d
ed
t
h
at
th
e
ML
R
is
h
ig
h
ly
s
u
itab
le
f
o
r
p
r
ed
ictio
n
o
f
K
an
d
C
l
u
tili
zin
g
ten
in
p
u
t v
ar
iab
les.
Fig
u
r
e
3
.
Actu
al
v
s
p
r
ed
icted
p
o
tass
iu
m
co
n
ce
n
tr
atio
n
f
o
r
d
i
f
f
er
en
t sam
p
les u
s
in
g
ML
R
Fig
u
r
e
4
.
Actu
al
v
s
p
r
ed
icted
ch
lo
r
id
e
co
n
ce
n
tr
atio
n
f
o
r
d
if
f
er
en
t sam
p
les u
s
in
g
ML
R
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
8
1
-
2
3
9
1
2388
T
h
e
ex
p
er
im
en
tal
f
in
d
in
g
s
in
d
icate
th
at
s
in
ce
m
u
ltil
ev
el
r
eg
r
ess
io
n
m
o
d
els
ar
e
m
ad
e
to
tak
e
in
to
co
n
s
id
er
atio
n
n
ested
d
ata
s
tr
u
ctu
r
es,
th
e
y
allo
w
f
o
r
r
a
n
d
o
m
ef
f
ec
ts
at
m
an
y
lev
els.
T
h
is
is
b
ec
au
s
e
wate
r
q
u
ality
d
ata
f
r
e
q
u
en
tly
h
av
e
a
h
ier
ar
ch
ical
s
tr
u
ctu
r
e,
s
u
c
h
as
m
ea
s
u
r
em
en
ts
m
ad
e
f
r
o
m
m
u
ltip
le
lo
ca
tio
n
s
o
v
er
d
if
f
e
r
en
t
tim
e
p
er
io
d
s
.
W
h
en
f
ac
to
r
s
af
f
ec
tin
g
wate
r
p
a
r
am
eter
s
f
lu
ctu
ate
at
th
e
s
ite
l
ev
el
as
well
as
o
v
er
lar
g
er
s
p
atial
o
r
tem
p
o
r
al
s
ca
les,
th
is
ca
n
b
e
h
elp
f
u
l
i
n
s
tu
d
i
es
o
n
wate
r
q
u
ality
.
Simp
ler
e
x
p
lan
atio
n
s
o
f
th
e
co
r
r
elatio
n
s
b
etwe
en
th
e
p
r
e
d
icto
r
s
an
d
th
e
r
esp
o
n
s
e
v
ar
ia
b
le
ar
e
o
f
f
er
ed
b
y
m
u
ltil
ev
el
r
eg
r
ess
io
n
m
o
d
els
s
u
b
s
tan
tiatin
g
th
e
o
b
jectiv
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
.
I
n
c
o
n
tr
as
t
to
th
e
i
n
tr
icate
,
n
o
n
-
lin
ea
r
in
ter
ac
tio
n
s
f
o
u
n
d
i
n
d
ec
is
io
n
tr
ee
s
o
r
r
an
d
o
m
f
o
r
e
s
ts
,
th
e
co
ef
f
icien
ts
in
a
r
eg
r
ess
io
n
m
o
d
el
s
h
o
w
th
e
d
ir
ec
t
in
f
lu
en
ce
o
f
ea
ch
p
r
ed
icto
r
,
wh
ic
h
is
f
r
eq
u
en
tly
ea
s
ier
to
u
n
d
er
s
tan
d
.
Fig
u
r
e
s
5
an
d
6
p
r
esen
ts
a
p
lo
t
o
f
ac
tu
al
v
s
p
r
ed
icted
p
o
tass
iu
m
an
d
ch
lo
r
i
d
e
c
o
n
c
en
tr
atio
n
wh
e
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
test
ed
f
o
r
o
u
t
o
f
b
ag
s
am
p
les
f
r
o
m
d
if
f
er
en
t lo
ca
tio
n
s
.
T
ab
le
6
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
with
r
ep
o
r
ted
wo
r
k
Y
e
a
r
o
f
p
u
b
l
i
c
a
t
i
o
n
/
R
e
f
e
r
e
n
c
e
N
o
.
I
n
p
u
t
p
a
r
a
me
t
e
r
s
P
e
r
f
o
r
ma
n
c
e
me
t
r
i
c
A
l
g
o
r
i
t
h
m
2
0
2
3
[
5
]
T,
p
H
,
w
a
t
e
r
f
l
o
w
C
l
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
r
e
c
a
l
l
:
9
0
%
,
p
r
e
c
i
si
o
n
:
9
2
%
,
F
-
sc
o
r
e
:
8
9
%
D
e
c
i
s
i
o
n
t
r
e
e
2
0
2
0
[
8
]
R
a
i
n
f
a
l
l
v
o
l
u
m
e
,
t
u
r
b
i
d
i
t
y
,
t
o
t
a
l
s
u
s
p
e
n
d
e
d
so
l
i
d
s
(
TSS
)
,
d
i
ss
o
l
v
e
d
o
r
g
a
n
i
c
c
a
r
b
o
n
(
D
O
C
)
,
so
d
i
u
m,
c
h
l
o
r
i
d
e
,
a
n
d
t
o
t
a
l
n
i
t
r
a
t
e
c
o
n
c
e
n
t
r
a
t
i
o
n
s
C
l
l
e
v
e
l
;
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
-
9
1
%
R
M
S
E
:
3
.
0
9
(
a
v
e
r
a
g
e
d
o
v
e
r
s
i
x
d
i
f
f
e
r
e
n
t
si
t
e
s
d
a
t
a
)
ANN
2
0
2
1
[
6
]
EC
,
T,
pH
C
l
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
R
M
S
E
:
0
.
0
1
(ANN),
0
.
1
3
(SGD)
7
.
1
7
(
K
N
N
)
,
1
0
.
5
3
(
S
V
M
)
S
G
D
,
A
N
N
,
k
-
N
N
,
a
n
d
S
V
M
2
0
1
2
[
7
]
EC
,
T,
r
i
v
e
r
f
l
o
w
r
a
t
e
,
a
n
d
r
a
i
n
f
a
l
l
C
l
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
R
2
:
0
.
9
R
M
S
E
:
1
1
.
7
8
S
t
e
p
w
i
se
c
l
u
s
t
e
r
a
n
a
l
y
si
s
w
i
t
h
M
LP
2
0
1
9
[
9
]
U
V
2
5
4
,
t
u
r
b
i
d
i
t
y
,
T,
i
n
f
l
o
w
F
o
r
K
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
M
A
E:
0
.
1
2
8
ANN
2
0
2
3
[
1
2
]
T,
p
H
,
E
C
,
a
n
d
TD
S
C
l
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
R
M
S
E
:
3
0
0
.
4
2
R
2
:
0
.
9
8
K
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
R
M
S
E
:
1
1
.
3
6
R2
:
o
.
9
2
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
P
r
o
p
o
se
d
M
L
R
mo
d
e
l
B
O
D
,
D
O
,
C
o
d
,
p
H
,
E
C
,
TSS
,
T
,
TO
C
,
c
o
l
o
r
,
t
u
r
b
i
d
i
t
y
K
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
M
S
E:
7
.
1
3
e
-
29
M
A
E:
7
.
4
2
e
-
15
C
l
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
:
M
S
E:
1
.
5
8
e
-
27
M
A
E
:
3
.
7
2
e
-
14
M
L
R
Fig
u
r
e
5
.
Scatter
p
l
o
t w
ith
th
e
f
o
r
ec
asted
an
d
m
ea
s
u
r
ed
p
o
tas
s
iu
m
co
n
ce
n
tr
atio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
mp
r
o
vin
g
w
a
ter q
u
a
lity p
a
r
a
mete
r
p
r
ed
ictio
n
w
ith
mu
lti
-
le
ve
l lin
ea
r
…
(
A
leefia
K
h
u
r
s
h
id
)
2389
Fig
u
r
e
6
.
Scatter
p
l
o
t w
ith
th
e
f
o
r
ec
asted
an
d
m
ea
s
u
r
ed
c
h
lo
r
id
e
co
n
ce
n
tr
atio
n
s
4.
CO
NCLU
SI
O
N
T
h
e
an
al
y
s
is
o
f
wate
r
q
u
ality
en
co
m
p
ass
es
th
e
e
x
am
in
atio
n
o
f
p
o
tass
iu
m
(
K)
an
d
ch
lo
r
id
e
(
C
l)
,
b
o
th
o
f
wh
ich
p
lay
cr
u
cial
r
o
les
in
en
v
ir
o
n
m
en
tal
an
d
h
u
m
an
h
e
alth
.
I
n
th
e
r
ea
lm
o
f
p
r
ed
ictiv
e
an
aly
s
is
,
v
ar
io
u
s
in
tellig
en
t
alg
o
r
ith
m
s
ar
e
em
p
lo
y
ed
to
f
o
r
ec
ast
wate
r
q
u
a
lity
p
ar
am
eter
s
.
Ho
wev
er
,
u
p
o
n
co
m
p
ar
in
g
th
e
ac
cu
r
ac
y
o
f
ML
R
f
r
o
m
th
e
li
ter
atu
r
e
with
t
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
o
u
r
ex
p
er
im
en
tal
i
m
p
lem
en
tatio
n
,
it
is
ev
id
en
t
th
at
ML
R
ex
h
ib
ited
s
u
p
er
io
r
ac
c
u
r
ac
y
an
d
y
iel
d
ed
th
e
b
est
-
f
it
r
esu
lts
.
T
h
i
s
u
n
d
er
s
co
r
es
th
e
r
o
b
u
s
tn
ess
an
d
e
f
f
icac
y
o
f
th
e
ML
R
m
o
d
el
in
p
r
ed
ictin
g
wa
ter
q
u
ality
p
ar
am
eter
s
g
iv
i
n
g
co
n
s
u
m
er
s
a
v
is
u
al
r
ep
r
esen
tatio
n
o
f
h
o
w
ea
ch
p
a
r
am
eter
in
f
lu
e
n
ce
s
p
r
ed
ictio
n
.
B
y
co
m
b
in
in
g
th
e
b
r
o
ad
e
f
f
icien
cy
o
f
f
ilter
m
eth
o
d
s
with
th
e
s
p
ec
if
ic
ac
cu
r
ac
y
o
f
wr
ap
p
e
r
m
eth
o
d
s
,
th
is
h
y
b
r
id
a
p
p
r
o
ac
h
en
h
an
ce
s
co
m
p
u
tatio
n
al
f
ea
s
ib
ilit
y
,
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
a
n
d
r
o
b
u
s
tn
ess
,
m
ak
in
g
it
a
v
alu
ab
le
s
tr
ateg
y
i
n
m
ac
h
i
n
e
lear
n
in
g
.
W
h
ile
th
e
liter
atu
r
e
r
ev
iew
d
id
n
o
t
th
o
r
o
u
g
h
ly
a
d
d
r
ess
th
e
im
p
lem
en
tatio
n
o
f
ML
R
,
th
e
p
o
ten
tial
f
o
r
in
teg
r
atin
g
th
is
s
o
f
twar
e
m
eth
o
d
o
lo
g
y
o
n
to
lo
w
-
co
s
t,
lo
w
-
p
o
wer
ed
h
ar
d
war
e
f
o
r
r
ea
l
-
tim
e
wate
r
q
u
ality
m
o
n
ito
r
in
g
p
r
esen
ts
an
in
tr
ig
u
in
g
p
r
o
s
p
ec
t.
T
h
is
a
v
en
u
e
s
u
g
g
ests
th
e
p
o
s
s
ib
ilit
y
o
f
a
p
p
ly
in
g
a
d
v
an
ce
d
an
aly
tical
tech
n
iq
u
es
to
p
r
ac
tical,
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
p
av
in
g
th
e
way
f
o
r
co
s
t
-
ef
f
ec
tiv
e,
r
ea
l
-
tim
e
m
o
n
it
o
r
in
g
s
o
lu
tio
n
s
.
I
n
f
u
tu
r
e
r
esid
u
al
an
aly
s
is
ca
n
b
e
ca
r
r
ied
o
u
t
to
s
u
g
g
est
o
th
e
r
f
ac
to
r
s
in
f
lu
e
n
cin
g
th
e
d
ep
en
d
en
t
v
ar
iab
le,
if
a
n
y
.
Als
o
,
th
e
w
o
r
k
ca
n
b
e
d
ir
ec
ted
f
o
r
r
ea
l
-
tim
e
im
p
lem
en
tatio
n
o
f
th
e
co
n
v
er
g
ed
m
o
d
el.
T
h
e
p
r
o
v
id
e
d
co
n
clu
s
io
n
in
teg
r
ates
th
e
s
ig
n
if
ic
an
ce
o
f
p
o
tass
iu
m
an
d
ch
lo
r
id
e
io
n
s
in
wate
r
q
u
a
lity
,
th
e
p
r
o
wess
o
f
th
e
ML
R
m
o
d
el,
an
d
th
e
p
o
ten
tial
f
o
r
r
e
al
-
tim
e
m
o
n
ito
r
in
g
s
o
lu
tio
n
s
to
s
u
p
p
o
r
t p
u
b
lic
h
ea
lth
b
y
en
s
u
r
i
n
g
s
af
e
d
r
in
k
in
g
wate
r
aid
in
g
en
v
ir
o
n
m
en
tal
m
an
ag
em
en
t
RE
F
E
R
E
NC
E
S
[
1
]
C
P
C
B
,
“
C
P
C
B
’
s
t
e
c
h
n
i
c
a
l
g
u
i
d
e
l
i
n
e
s,”
C
e
n
t
r
a
l
Po
l
l
u
t
i
o
n
C
o
n
t
r
o
l
Bo
a
rd
.
h
t
t
p
s
:
/
/
c
p
c
b
.
n
i
c
.
i
n
/
c
p
c
b
-
t
e
c
h
n
i
c
a
l
-
g
u
i
d
e
l
i
n
e
s
-
so
p
s
/
(
a
c
c
e
s
se
d
M
a
y
2
9
,
2
0
2
4
)
.
[
2
]
B
I
S
,
“
D
r
i
n
k
i
n
g
w
a
t
e
r
-
sp
e
c
i
f
i
c
a
t
i
o
n
,
”
B
u
r
e
a
u
o
f
I
n
d
i
a
n
S
t
a
n
d
a
r
d
s,
N
e
w
D
e
l
h
i
,
2
0
1
2
.
[
3
]
M
.
K
u
mar
a
n
d
A
.
P
u
r
i
,
“
A
r
e
v
i
e
w
o
f
p
e
r
m
i
ssi
b
l
e
l
i
m
i
t
s
o
f
d
r
i
n
k
i
n
g
w
a
t
e
r
,
”
I
n
d
i
a
n
J
o
u
rn
a
l
o
f
O
c
c
u
p
a
t
i
o
n
a
l
a
n
d
E
n
v
i
ro
n
m
e
n
t
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
1
6
,
n
o
.
1
,
p
.
4
0
,
2
0
1
2
,
d
o
i
:
1
0
.
4
1
0
3
/
0
0
1
9
-
5
2
7
8
.
9
9
6
9
6
.
[
4
]
V
.
O
l
i
v
e
i
r
a
S
a
n
t
o
s,
P
.
A
.
C
o
st
a
R
o
c
h
a
,
J
.
V
.
G
.
Th
é
,
a
n
d
B
.
G
h
a
r
a
b
a
g
h
i
,
“
G
r
a
p
h
-
b
a
s
e
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
f
o
r
e
c
a
st
i
n
g
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
i
n
u
r
b
a
n
st
r
e
a
ms
t
o
p
r
o
t
e
c
t
s
a
l
t
-
v
u
l
n
e
r
a
b
l
e
a
r
e
a
,
”
E
n
v
i
r
o
n
m
e
n
t
s
-
MDPI
,
v
o
l
.
1
0
,
n
o
.
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
v
i
r
o
n
m
e
n
t
s
1
0
0
9
0
1
5
7
.
[
5
]
C
.
V
.
C
h
i
n
n
a
p
p
a
n
e
t
a
l
.
,
“
I
o
T
-
e
n
a
b
l
e
d
c
h
l
o
r
i
n
e
l
e
v
e
l
a
ss
e
ssm
e
n
t
a
n
d
p
r
e
d
i
c
t
i
o
n
i
n
w
a
t
e
r
m
o
n
i
t
o
r
i
n
g
sy
s
t
e
m
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
El
e
c
t
ro
n
i
c
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
0
6
1
4
5
8
.
[
6
]
A
.
El
B
i
l
a
l
i
,
A
.
Ta
l
e
b
,
A
.
N
a
f
i
i
,
B
.
A
l
a
b
j
a
h
,
a
n
d
N
.
M
a
z
i
g
h
,
“
P
r
e
d
i
c
t
i
o
n
o
f
so
d
i
u
m a
d
s
o
r
p
t
i
o
n
r
a
t
i
o
a
n
d
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
i
n
a
c
o
a
st
a
l
a
q
u
i
f
e
r
u
n
d
e
r
sea
w
a
t
e
r
i
n
t
r
u
s
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
En
v
i
r
o
n
m
e
n
t
a
l
T
e
c
h
n
o
l
o
g
y
a
n
d
I
n
n
o
v
a
t
i
o
n
,
v
o
l
.
2
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
t
i
.
2
0
2
1
.
1
0
1
6
4
1
.
[
7
]
Q
.
Z
h
a
n
g
e
t
a
l
.
,
“
R
e
a
l
-
t
i
me
p
r
e
d
i
c
t
i
o
n
o
f
r
i
v
e
r
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
u
si
n
g
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
,
”
E
n
v
i
ro
n
m
e
n
t
a
l
P
o
l
l
u
t
i
o
n
,
v
o
l
.
2
9
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
v
p
o
l
.
2
0
2
1
.
1
1
8
1
1
6
.
[
8
]
K
.
Ja
h
a
n
a
n
d
S
.
M
.
P
r
a
d
h
a
n
a
n
g
,
“
P
r
e
d
i
c
t
i
n
g
R
u
n
o
f
f
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
s
i
n
s
u
b
u
r
b
a
n
w
a
t
e
r
sh
e
d
s
u
si
n
g
a
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
A
N
N
)
,
”
H
y
d
r
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
1
–
1
7
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
h
y
d
r
o
l
o
g
y
7
0
4
0
0
8
0
.
[
9
]
L.
G
o
d
o
-
P
l
a
,
P
.
E
mi
l
i
a
n
o
,
F
.
V
a
l
e
r
o
,
M
.
P
o
c
h
,
G
.
S
i
n
,
a
n
d
H
.
M
o
n
c
l
ú
s,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
o
x
i
d
a
n
t
d
e
ma
n
d
i
n
f
u
l
l
-
sca
l
e
d
r
i
n
k
i
n
g
w
a
t
e
r
t
r
e
a
t
me
n
t
u
s
i
n
g
a
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
:
U
n
c
e
r
t
a
i
n
t
y
a
n
d
se
n
s
i
t
i
v
i
t
y
a
n
a
l
y
si
s,
”
Pr
o
c
e
ss
S
a
f
e
t
y
a
n
d
En
v
i
r
o
n
m
e
n
t
a
l
Pro
t
e
c
t
i
o
n
,
v
o
l
.
1
2
5
,
p
p
.
3
1
7
–
3
2
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
se
p
.
2
0
1
9
.
0
3
.
0
1
7
.
[
1
0
]
T.
M
i
l
l
e
r
a
n
d
G
.
P
o
l
e
s
z
c
z
u
k
,
“
P
r
e
d
i
c
t
i
o
n
o
f
t
h
e
se
a
s
o
n
a
l
c
h
a
n
g
e
s
o
f
t
h
e
c
h
l
o
r
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
s
i
n
u
r
b
a
n
w
a
t
e
r
r
e
s
e
r
v
o
i
r
,
”
Ec
o
l
o
g
i
c
a
l
C
h
e
m
i
s
t
ry
a
n
d
E
n
g
i
n
e
e
ri
n
g
S
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
5
9
5
–
6
1
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
5
1
5
/
e
c
e
s
-
2
0
1
7
-
0
0
3
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
8
1
-
2
3
9
1
2390
[
1
1
]
H
.
M
o
e
i
n
z
a
d
e
h
,
P
.
J
e
g
a
k
u
m
a
r
a
n
,
K
.
T
.
Y
o
n
g
,
a
n
d
A
.
W
i
t
h
a
n
a
,
“
E
f
f
i
c
i
e
n
t
w
a
t
e
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
b
y
s
y
n
t
h
e
s
i
z
i
n
g
s
e
v
e
n
h
e
a
v
y
m
e
t
a
l
p
a
r
a
m
e
t
e
r
s
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
r
n
a
l
o
f
W
a
t
e
r
P
r
o
c
e
s
s
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
w
p
e
.
2
0
2
3
.
1
0
4
3
4
9
.
[
1
2
]
A
.
H
.
H
a
g
h
i
a
b
i
,
A
.
H
.
N
a
sr
o
l
a
h
i
,
a
n
d
A
.
P
a
r
sai
e
,
“
W
a
t
e
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
Wa
t
e
r
Q
u
a
l
i
t
y
Re
se
a
rc
h
J
o
u
r
n
a
l
,
v
o
l
.
5
3
,
n
o
.
1
,
p
p
.
3
–
1
3
,
2
0
1
8
,
d
o
i
:
1
0
.
2
1
6
6
/
w
q
r
j
.
2
0
1
8
.
0
2
5
.
[
1
3
]
N
S
F
,
“
I
n
e
x
p
e
n
si
v
e
mo
n
i
t
o
r
i
n
g
p
r
o
c
e
ss
p
o
w
e
r
e
d
b
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
o
u
l
d
a
i
d
i
n
w
a
t
e
r
t
r
e
a
t
m
e
n
t
,
”
U
.
S
.
N
a
t
i
o
n
a
l
S
c
i
e
n
c
e
Fo
u
n
d
a
t
i
o
n
.
h
t
t
p
s:
/
/
n
e
w
.
n
sf
.
g
o
v
/
n
e
w
s
/
i
n
e
x
p
e
n
s
i
v
e
-
m
o
n
i
t
o
r
i
n
g
-
p
r
o
c
e
ss
-
p
o
w
e
r
e
d
-
m
a
c
h
i
n
e
(
a
c
c
e
ss
e
d
M
a
y
2
9
,
2
0
2
4
)
.
[
1
4
]
R
.
R
a
n
a
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
f
o
r
s
u
r
f
a
c
e
w
a
t
e
r
q
u
a
l
i
t
y
e
v
a
l
u
a
t
i
o
n
,
mo
n
i
t
o
r
i
n
g
a
n
d
a
ssessm
e
n
t
,
”
Wa
t
e
r
(
S
w
i
t
ze
rl
a
n
d
)
,
v
o
l
.
1
5
,
n
o
.
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
w
1
5
2
2
3
9
1
9
.
[
1
5
]
T.
Y
.
W
e
i
,
E.
S
.
Ti
n
d
i
k
,
C
.
F
.
F
u
i
,
H
a
v
i
l
u
d
d
i
n
,
a
n
d
M
.
H
.
A
.
H
i
j
a
z
i
,
“
A
u
t
o
ma
t
e
d
w
a
t
e
r
q
u
a
l
i
t
y
m
o
n
i
t
o
r
i
n
g
a
n
d
r
e
g
r
e
ssi
o
n
-
b
a
s
e
d
f
o
r
e
c
a
st
i
n
g
s
y
s
t
e
m
f
o
r
a
q
u
a
c
u
l
t
u
r
e
,
”
Bu
l
l
e
t
i
n
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
B
EEI)
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
5
7
0
–
5
7
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
2
i
1
.
4
4
6
4
.
[
1
6
]
A
.
A
l
d
r
e
e
s
,
M
.
K
h
a
n
,
A
.
T
.
B
.
T
a
h
a
,
a
n
d
M
.
A
l
i
,
“
E
v
a
l
u
a
t
i
o
n
o
f
w
a
t
e
r
q
u
a
l
i
t
y
i
n
d
e
x
e
s
w
i
t
h
n
o
v
e
l
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
s
h
a
p
l
e
y
a
d
d
i
t
i
v
e
e
x
p
l
a
n
a
t
i
o
n
(
S
H
A
P
)
a
p
p
r
o
a
c
h
e
s
,
”
J
o
u
r
n
a
l
o
f
W
a
t
e
r
P
r
o
c
e
s
s
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
5
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
w
p
e
.
2
0
2
4
.
1
0
4
7
8
9
.
[
1
7
]
B
.
S
c
h
ä
f
e
r
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
e
x
p
l
a
i
n
i
n
g
w
a
t
e
r
q
u
a
l
i
t
y
d
y
n
a
mi
c
s
i
n
a
n
u
r
b
a
n
i
s
e
d
r
i
v
e
r
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
2
-
1
6
3
4
2
-
9.
[
1
8
]
F
.
A
b
b
a
s
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
w
a
t
e
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
:
a
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
si
s
a
n
d
u
n
c
e
r
t
a
i
n
t
y
a
sse
ssm
e
n
t
i
n
M
i
r
p
u
r
k
h
a
s,
S
i
n
d
h
,
P
a
k
i
s
t
a
n
,
”
W
a
t
e
r
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
6
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
w
1
6
0
7
0
9
4
1
.
[
1
9
]
W
.
W
o
n
g
s
a
,
P
.
P
u
p
h
a
su
k
,
a
n
d
J
.
W
e
t
w
e
e
r
a
p
o
n
g
,
“
D
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
w
i
t
h
a
d
a
p
t
i
v
e
mu
t
a
t
i
o
n
a
n
d
c
r
o
ss
o
v
e
r
st
r
a
t
e
g
i
e
s
f
o
r
n
o
n
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
p
r
o
b
l
e
ms,
”
Bu
l
l
e
t
i
n
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
B
EEI)
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
3
5
0
3
–
3
5
1
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
3
i
5
.
6
4
1
7
.
[
2
0
]
M
.
Q
o
m
a
r
u
d
d
i
n
,
A
.
R
i
a
n
s
y
a
h
,
a
n
d
H
.
M
.
H
e
r
maw
a
n
,
“
M
a
m
d
a
n
i
f
u
z
z
y
-
b
a
s
e
d
w
a
t
e
r
q
u
a
l
i
t
y
m
o
n
i
t
o
r
i
n
g
a
n
d
c
o
n
t
r
o
l
s
y
st
e
m
i
n
v
a
n
n
a
me
i
s
h
r
i
m
p
f
a
r
m
i
n
g
u
s
i
n
g
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
8
0
–
1
8
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
a
s.v
1
3
.
i
1
.
p
p
1
8
0
-
1
8
7
.
[
2
1
]
Z.
W
a
n
g
,
Q
.
W
a
n
g
,
a
n
d
T.
W
u
,
“
A
n
o
v
e
l
h
y
b
r
i
d
m
o
d
e
l
f
o
r
w
a
t
e
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
V
M
D
a
n
d
I
G
O
A
o
p
t
i
mi
z
e
d
f
o
r
LSTM
,
”
Fro
n
t
i
e
rs
o
f
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
7
,
n
o
.
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
7
8
3
-
0
2
3
-
1
6
8
8
-
y.
[
2
2
]
M
.
G
.
U
d
d
i
n
e
t
a
l
.
,
“
M
a
r
i
n
e
w
a
t
e
r
s
a
ssessme
n
t
u
s
i
n
g
i
mp
r
o
v
e
d
w
a
t
e
r
q
u
a
l
i
t
y
m
o
d
e
l
i
n
c
o
r
p
o
r
a
t
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
J
o
u
rn
a
l
o
f
En
v
i
r
o
n
m
e
n
t
a
l
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
3
4
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
n
v
man
.
2
0
2
3
.
1
1
8
3
6
8
.
[
2
3
]
P
.
L.
G
e
o
r
g
e
sc
u
e
t
a
l
.
,
“
A
ss
e
ssi
n
g
a
n
d
f
o
r
e
c
a
st
i
n
g
w
a
t
e
r
q
u
a
l
i
t
y
i
n
t
h
e
D
a
n
u
b
e
R
i
v
e
r
b
y
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
e
s
,
”
S
c
i
e
n
c
e
o
f
t
h
e
T
o
t
a
l
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
8
7
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sc
i
t
o
t
e
n
v
.
2
0
2
3
.
1
6
2
9
9
8
.
[
2
4
]
A
.
Y
.
S
u
n
a
n
d
B
.
R
.
S
c
a
n
l
o
n
,
“
H
o
w
c
a
n
b
i
g
d
a
t
a
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
b
e
n
e
f
i
t
e
n
v
i
r
o
n
me
n
t
a
n
d
w
a
t
e
r
m
a
n
a
g
e
men
t
:
A
s
u
r
v
e
y
o
f
met
h
o
d
s,
a
p
p
l
i
c
a
t
i
o
n
s
,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
,
”
En
v
i
r
o
n
m
e
n
t
a
l
Re
se
a
r
c
h
L
e
t
t
e
rs
,
v
o
l
.
1
4
,
n
o
.
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
8
-
9
3
2
6
/
a
b
1
b
7
d
.
[
2
5
]
W
.
L
i
u
,
T
.
L
i
u
,
Z
.
L
i
u
,
H
.
L
u
o
,
a
n
d
H
.
P
e
i
,
“
A
n
o
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
e
n
s
e
m
b
l
e
m
o
d
e
l
b
a
s
e
d
o
n
t
w
o
-
s
t
a
g
e
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
i
n
t
e
l
l
i
g
e
n
t
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
w
a
t
e
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
,
”
E
n
v
i
r
o
n
m
e
n
t
a
l
R
e
s
e
a
r
c
h
,
v
o
l
.
2
2
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
v
r
e
s
.
2
0
2
3
.
1
1
5
5
6
0
.
[
2
6
]
P
.
S
i
h
a
g
,
A
.
A
n
g
e
l
a
k
i
,
a
n
d
B
.
C
h
a
p
l
o
t
,
“
Es
t
i
m
a
t
i
o
n
o
f
t
h
e
r
e
c
h
a
r
g
i
n
g
r
a
t
e
o
f
g
r
o
u
n
d
w
a
t
e
r
u
si
n
g
r
a
n
d
o
m f
o
r
e
st
t
e
c
h
n
i
q
u
e
,
”
Ap
p
l
i
e
d
Wa
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
7
,
p
.
1
8
2
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
0
1
-
020
-
0
1
2
6
7
-
3.
[
2
7
]
N
.
B
o
u
r
n
a
s
,
A
.
G
a
l
d
e
a
n
o
,
M
.
H
a
m
o
u
d
i
,
a
n
d
H
.
B
a
k
e
r
,
“
I
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
t
h
e
a
e
r
o
m
a
g
n
e
t
i
c
ma
p
o
f
E
a
st
e
r
n
H
o
g
g
a
r
(
A
l
g
e
r
i
a
)
u
s
i
n
g
t
h
e
E
u
l
e
r
d
e
c
o
n
v
o
l
u
t
i
o
n
,
a
n
a
l
y
t
i
c
si
g
n
a
l
a
n
d
l
o
c
a
l
w
a
v
e
n
u
m
b
e
r
m
e
t
h
o
d
s,
”
J
o
u
r
n
a
l
o
f
A
f
ri
c
a
n
Ea
r
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
3
7
,
n
o
.
3
–
4
,
p
p
.
1
9
1
–
2
0
5
,
O
c
t
.
2
0
0
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
f
r
e
a
r
sc
i
.
2
0
0
2
.
1
2
.
0
0
1
.
[
2
8
]
T.
P
h
a
m,
T.
Tr
a
n
,
D
.
P
h
u
n
g
,
a
n
d
S
.
V
e
n
k
a
t
e
sh
,
“
P
r
e
d
i
c
t
i
n
g
h
e
a
l
t
h
c
a
r
e
t
r
a
j
e
c
t
o
r
i
e
s
f
r
o
m
me
d
i
c
a
l
r
e
c
o
r
d
s
:
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
J
o
u
rn
a
l
o
f
B
i
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
9
,
p
p
.
2
1
8
–
2
2
9
,
M
a
y
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
7
.
0
4
.
0
0
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ale
e
fia
K
h
u
r
shi
d
re
c
e
iv
e
d
th
e
P
h
.
D
.
d
e
g
re
e
i
n
e
lec
tro
n
ics
e
n
g
in
e
e
rin
g
fr
o
m
Visv
e
sv
a
ra
y
a
Na
ti
o
n
a
l
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Na
g
p
u
r
,
I
n
d
ia
i
n
t
h
e
y
e
a
r
2
0
1
1
.
S
h
e
is
a
li
f
e
m
e
m
b
e
r
o
f
IET
E
,
IS
TE
,
a
n
d
IE
.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
-
d
r
iv
e
n
sy
ste
m
id
e
n
ti
fica
ti
o
n
,
m
o
d
e
li
n
g
,
a
n
d
im
a
g
e
p
r
o
c
e
ss
in
g
.
S
h
e
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
a
t
S
h
ri
Ra
m
d
e
o
b
a
b
a
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t,
Na
g
p
u
r
,
In
d
ia
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
u
rsh
i
d
a
a
@rk
n
e
c
.
e
d
u
.
S
a
m
r
u
d
d
h
i
K
o
r
k
e
is
a
re
c
e
n
t
g
ra
d
u
a
te
with
a
B
.
Tec
h
.
d
e
g
re
e
in
e
lec
tro
n
ics
e
n
g
in
e
e
rin
g
fro
m
S
h
ri
Ra
m
d
e
o
b
a
b
a
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t,
Na
g
p
u
r.
S
a
m
ru
d
d
h
i
is
c
u
ri
o
u
s
a
b
o
u
t
th
e
e
m
e
rg
in
g
tec
h
n
o
l
o
g
y
in
th
e
fiel
d
o
f
VLS
I
a
n
d
AIML
.
He
r
d
e
d
ica
ti
o
n
to
i
n
terd
isc
ip
l
in
a
ry
i
n
n
o
v
a
t
io
n
u
n
d
e
rsc
o
re
s
th
e
sig
n
ifi
c
a
n
c
e
o
f
h
e
r
c
o
n
tri
b
u
ti
o
n
s
t
o
th
is
re
se
a
rc
h
,
p
ro
m
isi
n
g
to
a
d
v
a
n
c
e
th
e
fiel
d
o
f
wa
ter
q
u
a
li
ty
m
o
n
i
to
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
o
rk
e
sd
@r
k
n
e
c
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.