I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
5
,
No
.
4
,
Dec
em
b
er
2
0
1
6
,
p
p
.
135
~
142
I
SS
N:
2252
-
8938
135
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
A
I
Ass
ess
ing
St
a
te
o
f
t
he
Art
on Ar
tif
i
cia
l Neural N
etw
o
rk
Para
dig
m
s
for Le
v
el of Eutrophi
ca
tion Es
ti
m
a
tion o
f
Water
Bo
dies
T
us
ha
r
Ant
hw
a
l
1
,
M
K
P
a
nd
ey
2
1
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Bh
a
g
wa
n
t
Un
iv
e
rsity
,
In
d
ia
2
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Am
r
a
p
a
li
In
stit
u
te
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
13
,
2
0
1
6
R
ev
i
s
ed
Oct
17
,
2
0
1
6
A
cc
ep
ted
No
v
2
0
,
2
0
1
6
W
it
h
g
ro
w
in
g
p
o
w
e
r
o
f
c
o
m
p
u
ter
a
n
d
b
len
d
o
f
in
tell
ig
e
n
t
so
f
t
w
a
r
e
s,
th
e
in
terp
re
tatio
n
a
n
d
a
n
a
ly
ti
c
a
l
c
a
p
a
b
il
it
ies
o
f
s
y
ste
m
h
a
d
sh
o
w
n
a
n
e
x
c
e
ll
e
n
t
g
ro
w
th
,
p
ro
v
id
i
n
g
in
tel
li
g
e
n
c
e
so
lu
ti
o
n
s
t
o
a
lm
o
st
e
v
e
r
y
c
o
m
p
u
ti
n
g
p
ro
b
lem
.
In
th
is
d
irec
ti
o
n
h
e
re
w
e
a
re
tr
y
in
g
to
id
e
n
ti
fy
h
o
w
d
i
ff
e
re
n
t
g
e
o
c
o
m
p
u
tatio
n
tec
h
n
iq
u
e
s
h
a
d
b
e
e
n
im
p
le
m
e
n
t
e
d
f
o
r
e
sti
m
a
ti
o
n
o
f
p
a
ra
m
e
ters
o
n
w
a
ter
b
o
d
ies
so
a
s
to
id
e
n
ti
fy
th
e
lev
e
l
o
f
c
o
n
ta
m
in
a
ti
o
n
lea
d
in
g
to
d
if
fe
re
n
t
lev
e
l
o
f
e
u
tro
p
h
ica
ti
o
n
.
T
h
e
m
a
in
m
issi
o
n
o
f
th
is
p
a
p
e
r
is
t
o
id
e
n
t
ify
sta
t
e
-
of
-
a
rt
in
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
p
a
ra
d
ig
m
s
th
a
t
a
re
p
re
v
a
il
in
g
a
n
d
e
ff
e
c
ti
v
e
in
m
o
d
e
li
n
g
a
n
d
c
o
m
b
in
in
g
sp
a
ti
a
l
d
a
ta
f
o
r
a
n
ti
c
ip
a
ti
o
n
.
Am
o
n
g
th
is
o
u
r
in
tere
st
is
to
id
e
n
t
ify
d
iffere
n
t
a
n
a
l
y
sis
tec
h
n
iq
u
e
s
a
n
d
th
e
ir
p
a
ra
m
e
ters
th
a
t
a
re
m
a
in
ly
u
se
d
f
o
r
q
u
a
li
ty
in
sp
e
c
ti
o
n
o
f
lak
e
s
a
n
d
e
sti
m
a
ti
o
n
o
f
n
u
tri
e
n
t
p
o
ll
u
tan
t
c
o
n
ten
t
i
n
it
,
a
n
d
d
if
f
e
r
e
n
t
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
ls
th
a
t
o
ff
e
r
e
d
th
e
f
o
re
c
a
stin
g
o
f
le
v
e
l
o
f
e
u
tro
p
h
ica
ti
o
n
i
n
th
e
w
a
ter
b
o
d
ies
.
Diffe
re
n
t
tec
h
n
iq
u
e
s
a
re
a
n
a
l
y
z
e
d
o
v
e
r
th
e
m
a
in
ste
p
s;
-
as
si
m
il
a
ti
o
n
o
f
sp
a
ti
a
l
d
a
ta,
sta
ti
stica
l
in
terp
re
tatio
n
tec
h
n
iq
u
e
,
o
b
se
rv
e
d
p
a
ra
m
e
ters
u
se
d
f
o
r
e
u
tro
p
h
ica
ti
o
n
e
stim
a
ti
o
n
a
n
d
a
c
c
u
ra
c
y
o
f
re
su
lt
a
n
t
d
a
ta.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
E
u
tr
o
p
h
icatio
n
Geo
co
m
p
u
ti
n
g
Sp
atial
i
m
a
g
er
y
d
ata
W
ater
q
u
alit
y
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
u
s
h
ar
An
t
h
w
al,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
A
p
p
licatio
n
s
,
Am
r
ap
ali
I
n
s
tit
u
te
o
f
Ma
n
ag
e
m
en
t &
C
o
m
p
u
ter
A
p
p
licatio
n
,
Sh
i
k
s
h
a
Na
g
ar
,
Hald
w
a
n
i,
Utt
ar
ak
h
a
n
d
,
I
n
d
ia.
E
m
ail: a
n
t
h
w
al.
tu
s
h
ar
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
u
tr
o
p
h
icatio
n
is
a
p
r
o
ce
s
s
o
f
in
cr
ea
s
e
o
f
n
u
tr
ie
n
t
co
n
te
n
t
i
n
w
ater
b
o
d
ies,
s
u
ch
as
la
k
e
s
,
estu
ar
ie
s
,
r
iv
er
s
,
o
r
s
lo
w
-
m
o
v
in
g
s
tr
ea
m
s
th
at
ac
ce
ler
ates
t
h
e
p
lan
t
g
r
o
w
t
h
s
u
c
h
as
al
g
ae
,
p
er
ip
h
y
to
n
an
d
p
lan
t
w
ee
d
s
in
ex
ce
s
s
.
T
h
is
en
h
an
ce
d
g
r
o
w
t
h
o
f
p
lan
t
s
is
k
n
o
w
n
as
a
n
alg
al
b
lo
o
m
,
w
h
ich
i
n
t
u
r
n
r
esu
lt
s
w
it
h
a
lo
w
co
n
ce
n
tr
atio
n
o
f
d
is
s
o
l
v
ed
o
x
y
g
e
n
a
s
tate
k
n
o
w
n
as
h
y
p
o
x
i
c
an
d
d
ec
ay
i
n
g
o
f
ce
r
tain
f
ee
b
le
p
lan
t
s
p
ec
ies
o
v
e
r
o
th
er
s
w
er
e
f
a
v
o
r
ed
,
an
d
is
l
i
k
el
y
to
ca
u
s
e
s
ev
er
e
r
ed
u
c
tio
n
s
in
w
ater
q
u
ali
t
y
.
T
h
e
n
u
tr
i
en
ts
co
n
te
n
t
w
o
u
ld
r
ea
ch
w
ater
b
o
d
ies
f
r
o
m
m
a
n
y
s
o
u
r
ce
s
,
s
u
ch
a
s
f
er
ti
lizer
s
a
p
p
lied
to
ag
r
icu
ltu
r
al
f
ield
s
,
l
an
d
f
il
ls
n
ea
r
r
iv
er
s
;
d
ep
o
s
itio
n
o
f
n
itro
g
e
n
f
r
o
m
th
e
at
m
o
s
p
h
er
e;
er
o
s
io
n
o
f
s
o
il;
s
e
w
a
g
e
tr
ea
t
m
en
t
p
la
n
t
d
is
c
h
ar
g
es
etc.
E
u
tr
o
p
h
icatio
n
d
ec
r
ea
s
es
t
h
e
r
eso
u
r
ce
v
al
u
e
o
f
r
iv
er
s
,
la
k
e
s
,
an
d
estu
ar
ie
s
h
a
v
i
n
g
ad
v
er
s
e
af
f
ec
t
o
n
w
ater
u
s
a
g
e
f
o
r
ir
r
ig
atio
n
,
f
i
s
h
in
g
,
aq
u
atic
lif
e
o
f
p
lan
t
s
an
d
an
i
m
a
ls
th
u
s
m
a
k
i
n
g
w
ater
ec
o
s
y
s
te
m
u
n
b
alan
ce
.
Sev
er
h
ea
lt
h
p
r
o
b
lem
s
e
m
er
g
e
w
h
er
e
eu
tr
o
p
h
ic
co
n
d
itio
n
s
in
ter
f
e
r
e
w
ith
d
r
in
k
i
n
g
w
ater
tr
ea
t
m
en
t.
As
p
er
ar
ticle
p
u
b
lis
h
ed
i
n
b
y
J
in
[
1
]
s
h
o
w
e
d
th
at
all
lak
e
s
s
t
u
d
ied
w
er
e
u
n
d
er
g
o
in
g
t
h
e
e
u
tr
o
p
h
icatio
n
p
r
o
ce
s
s
.
I
n
th
e
y
ea
r
1
9
7
0
’
s
,
m
o
s
t
o
f
th
e
la
k
es
wer
e
w
it
h
9
1
.
8
%
w
a
ter
ac
co
u
n
ts
,
m
eso
tr
o
p
h
ic
s
ta
g
e.
I
n
th
e
n
ex
t
d
ec
ad
e
th
e
p
er
ce
n
tag
e
o
f
la
k
es
w
ith
o
lig
o
tr
o
p
h
ic
s
ta
t
u
s
d
ec
r
ea
s
ed
b
y
ap
p
r
o
x
i
m
ate
3
%
-
0
.
5
%
a
n
d
eu
tr
o
p
h
icatio
n
in
cr
ea
s
e
s
b
y
5
%
-
5
5
%.
B
y
th
e
y
ea
r
2
0
0
8
ab
o
u
t
6
0
%
o
f
lak
es
in
c
h
i
n
a
w
er
e
i
n
eu
tr
o
p
h
ic
a
n
d
h
y
p
er
tr
o
p
h
ic
co
n
d
itio
n
an
d
f
u
r
t
h
er
p
r
ed
icted
th
at
b
y
2
0
3
0
all
u
r
b
an
la
k
es
w
o
u
ld
s
h
ar
e
th
e
s
a
m
e
s
ta
tu
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
4
,
Dec
em
b
er
2
0
1
6
:
1
5
3
–
142
136
E
u
tr
o
p
h
icatio
n
i
s
o
n
e
o
f
t
h
e
l
ar
g
el
y
g
r
o
w
in
g
p
o
llu
tio
n
p
r
o
b
le
m
s
i
n
i
n
la
n
d
w
ater
b
o
d
ies
a
r
o
u
n
d
th
e
g
lo
b
e,
th
u
s
r
e
s
to
r
atio
n
o
f
w
at
er
b
o
d
ies
n
ee
d
to
h
a
v
e
i
n
t
elli
g
en
t
co
m
p
u
tatio
n
tech
n
iq
u
es
in
o
r
d
er
to
an
al
y
ze
o
v
er
th
e
cu
r
r
en
t
s
tatu
s
o
f
aq
u
atic
ec
o
s
y
s
te
m
alo
n
g
w
it
h
alar
m
i
n
g
ab
o
u
t
t
h
e
f
u
t
u
r
e
ch
ar
ac
ter
is
tics
b
y
ti
m
e
s
er
ies
f
o
r
ec
asti
n
g
.
W
ith
th
i
s
f
ast
co
m
p
u
t
in
g
w
o
r
ld
an
d
e
m
er
g
i
n
g
tech
n
o
lo
g
y
d
ata
an
al
y
ze
r
n
ee
d
to
b
e
p
o
w
er
ed
b
y
ar
tific
ial
in
telli
g
e
n
t
tech
n
iq
u
es.
A
s
t
h
e
in
ter
p
r
et
er
,
m
o
d
u
lato
r
an
d
p
r
ed
icto
r
n
eu
r
al
n
et
w
o
r
k
s
h
ad
e
m
er
g
ed
as
a
ca
p
ab
le
tec
h
n
iq
u
e
th
a
t
g
e
n
er
ates
ap
p
r
o
x
i
m
at
e
ac
cu
r
atel
y
co
m
p
licated
n
o
n
-
li
n
ea
r
in
p
u
t
-
o
u
tp
u
t
r
elatio
n
s
h
ip
s
.
A
n
e
u
r
al
n
et
wo
r
k
is
p
ar
a
llel
-
d
is
tr
ib
u
ted
p
r
o
ce
s
s
o
r
th
at
p
o
s
s
es
p
r
o
p
er
ty
in
s
p
ir
ed
b
y
h
u
m
a
n
co
g
n
itio
n
s
y
s
te
m
.
A
N
N
h
a
v
e
th
e
ab
ilit
y
o
f
co
m
p
u
ti
n
g
,
p
r
o
c
ess
i
n
g
,
p
r
ed
ictio
n
a
n
d
class
i
f
i
ca
tio
n
o
f
d
ata
an
d
h
ad
ad
v
an
ta
g
es o
f
n
o
n
lin
ea
r
i
t
y
,
in
p
u
t
-
o
u
tp
u
t
m
ap
p
in
g
,
ad
ap
tiv
el
y
,
g
e
n
er
aliza
tio
n
a
n
d
f
ai
lu
r
e
r
esis
tiv
e
[
2
]
.
I
n
t
h
is
d
ir
ec
tio
n
,
w
e
ar
e
g
o
i
n
g
to
d
is
c
u
s
s
s
o
m
e
co
m
p
u
tin
g
tech
n
iq
u
e
s
u
s
ed
f
o
r
i
n
ter
p
r
etatio
n
a
n
d
esti
m
atio
n
o
f
w
ater
b
o
d
ies’
s
t
atu
s
o
n
eu
tr
o
p
h
ica
tio
n
le
v
el
ta
k
in
g
i
n
ac
co
u
n
t
s
p
atial
an
d
te
m
p
o
r
al
d
ata
as
in
p
u
t
p
ar
am
eter
s
.
T
h
is
p
ap
er
is
f
u
r
th
er
d
iv
id
ed
in
to
Sect
io
n
I
I
w
h
ic
h
b
r
ief
s
ab
o
u
t
g
eo
co
m
p
u
tatio
n
w
it
h
m
aj
o
r
tech
n
iq
u
es
as
p
atter
n
r
ec
o
g
n
it
io
n
,
s
p
atial
d
ata
an
al
y
s
i
s
an
d
ar
tif
icial
i
n
telli
g
e
n
ce
tech
n
iq
u
es.
I
n
th
e
n
ex
t
p
ar
t;
Sectio
n
I
I
I
,
r
elate
d
p
ap
er
s
ar
e
s
u
r
v
e
y
ed
a
n
d
co
m
p
ar
es
t
h
e
id
en
ti
f
icatio
n
o
f
tec
h
n
iq
u
es
u
s
e
d
b
y
t
h
e
r
esear
c
h
er
s
in
co
m
p
u
ti
n
g
s
p
atial
d
ata
a
n
d
g
e
n
er
atio
n
o
f
d
e
s
ir
ed
r
es
u
lts
.
Sectio
n
I
V
co
n
c
lu
d
es
w
it
h
th
e
m
o
d
el
o
r
ar
ch
itect
u
r
e
f
o
r
th
e
f
o
r
m
u
latio
n
o
f
a
s
y
s
te
m
f
o
r
en
h
a
n
ce
d
in
f
er
en
ce
s
o
n
eu
tr
o
p
h
icatio
n
es
ti
m
atio
n
.
2.
T
AXO
NO
M
Y
O
F
G
E
O
CO
M
P
UT
AT
I
O
N
Geo
co
m
p
u
tatio
n
i
s
an
e
m
er
g
i
n
g
f
ield
w
it
h
a
w
id
e
s
co
p
e
o
f
r
esear
ch
,
th
at
p
r
o
p
o
n
en
t
th
e
i
n
v
o
lv
e
m
e
n
t
o
f
co
m
p
u
tatio
n
b
ased
ap
p
r
o
a
ch
es
s
u
c
h
as
n
e
u
r
al
n
et
w
o
r
k
s
,
h
eu
r
i
s
tic
s
ea
r
ch
a
n
d
co
m
p
u
tatio
n
a
l
au
to
m
ata
d
esig
n
f
o
r
s
p
atial
d
ata
a
n
al
y
s
is
.
T
h
is
n
e
w
in
ter
d
is
cip
lin
ar
y
f
ield
b
e
y
o
n
d
j
u
s
t
i
m
p
le
m
e
n
t
atio
n
o
f
s
tatis
tical
tech
n
iq
u
es
f
o
r
s
p
atia
l
d
ata
with
b
asic
es
s
en
ce
o
f
co
g
n
it
io
n
i
n
t
h
e
m
t
h
u
s
co
i
n
ed
as
"
g
eo
co
m
p
u
tatio
n
"
b
y
Op
en
s
h
a
w
a
n
d
A
b
r
ah
ar
t,
[
3
]
an
d
ex
p
a
n
d
ed
b
y
L
o
n
g
le
y
an
d
B
r
o
o
k
s
[
4
]
,
th
at
d
escr
ib
es
t
h
e
u
s
e
o
f
co
m
p
u
ter
-
in
te
n
s
i
v
e
m
et
h
o
d
s
f
o
r
k
n
o
w
l
ed
g
e
d
is
co
v
er
y
i
n
g
eo
g
r
ap
h
y
,
esp
ec
iall
y
th
o
s
e
th
at
e
m
p
lo
y
n
o
n
-
co
n
v
en
t
io
n
a
l
d
ata
clu
s
ter
in
g
a
n
d
a
n
al
y
s
i
s
tech
n
iq
u
es
an
d
f
u
r
t
h
er
elab
o
r
ated
to
in
cl
u
d
e
s
p
atial
d
ata
an
al
y
s
i
s
,
d
y
n
a
m
ic
m
o
d
eli
n
g
,
v
i
s
u
a
liza
tio
n
a
n
d
s
p
ac
e
-
ti
m
e
d
y
n
a
m
ics.
T
h
e
m
aj
o
r
g
eo
co
m
p
u
ta
tio
n
ev
o
lu
tio
n
f
ac
to
r
s
w
er
e:
co
m
p
u
ter
ized
d
ata
-
r
ich
e
n
v
ir
o
n
m
en
ts
a
n
d
ca
p
ab
ilit
y
o
f
co
m
p
u
ter
to
r
ec
o
r
d
an
d
p
r
o
ce
s
s
o
v
er
b
ig
d
ata,
af
f
o
r
d
ab
le
co
m
p
u
tat
io
n
al
p
o
wer
;
w
it
h
e
m
er
g
e
o
f
v
ir
tu
a
lizatio
n
a
n
d
cu
r
r
en
tl
y
c
lo
u
d
co
m
p
u
ti
n
g
i
m
p
le
m
e
n
tati
o
n
s
w
h
ich
p
r
o
v
id
es
h
ig
h
co
m
p
u
tat
io
n
at
lo
w
er
co
s
ts
,
an
d
last
l
y
all
th
e
r
esear
ch
ef
f
o
r
ts
to
w
ar
d
s
s
tatis
tical
t
ec
h
n
iq
u
es
a
n
d
m
i
n
in
g
al
g
o
r
ith
m
s
a
n
d
ar
ch
itect
u
r
e
th
at
s
p
atial
d
ata
a
n
al
y
s
is
a
n
d
m
i
n
in
g
tech
n
iq
u
es
to
o
k
t
h
is
a
h
ea
d
.
Fo
r
f
u
r
t
h
er
en
h
a
n
ce
m
en
t
in
t
h
is
ar
ea
m
o
r
e
co
m
p
u
tatio
n
al
r
esear
ch
s
h
o
u
l
d
b
e
en
d
o
r
s
e
w
it
h
co
m
p
u
ter
-
b
ased
p
atter
n
s
ea
r
c
h
,
ex
p
lo
r
ato
r
y
s
p
atial
d
ata
an
al
y
s
is
tec
h
n
iq
u
es,
ar
t
if
ic
ial
in
tel
lig
e
n
ce
ap
p
r
o
ac
h
es
w
it
h
m
o
r
e
p
o
w
er
f
u
l
h
eu
r
i
s
tic
s
ea
r
ch
es
al
g
o
r
ith
m
s
,
k
n
o
w
led
g
e
p
r
o
ce
s
s
i
n
g
s
y
s
te
m
s
an
d
d
y
n
a
m
ic
m
o
d
eli
n
g
t
h
at
co
u
ld
lev
er
a
g
e
r
ea
l
-
ti
m
e
s
ce
n
ar
io
o
f
p
h
y
s
ica
l
lan
d
s
ca
p
es a
n
d
o
th
er
attr
ib
u
te
s
.
W
e
h
ad
in
v
esti
g
ated
o
n
l
y
t
h
e
m
aj
o
r
tech
n
iq
u
e
s
t
h
at
e
n
co
u
n
ter
ed
i
n
th
e
an
al
y
s
is
o
f
i
m
a
g
er
y
g
eo
s
p
atial
d
ata
f
o
r
co
m
p
u
ti
n
g
ch
ar
ac
ter
is
t
ic
s
o
f
la
k
e
w
ater
co
n
d
itio
n
s
a
n
d
th
ese
ar
e
as
f
o
ll
o
w
s
:
2
.
1
.
Sp
a
t
ia
l D
a
t
a
Ana
ly
s
is
a
nd
M
ini
ng
T
ec
hn
iq
ues
Geo
g
r
ap
h
ical
I
n
f
o
r
m
atio
n
S
y
s
te
m
s
(
GI
S)
ar
e
lar
g
e
d
o
m
ai
n
co
m
p
u
ti
n
g
s
y
s
te
m
s
t
h
at
f
ac
il
itate
ca
p
tu
r
in
g
,
s
to
r
ag
e,
r
etr
ie
v
al,
m
an
a
g
i
n
g
an
d
a
n
al
y
s
e
s
o
f
s
p
atial
d
ata
th
a
t
h
ad
g
eo
g
r
ap
h
ic
al
co
n
ten
t
i
n
t
h
e
m
.
T
h
ese
s
y
s
te
m
s
u
til
ize
d
if
f
er
e
n
t
g
eo
s
p
atial
a
n
al
y
zi
n
g
tech
n
iq
u
es
to
i
m
p
ar
t
ac
c
u
r
ate
a
n
d
m
e
an
in
g
f
u
l
r
es
u
lt
s
o
u
t
o
f
ac
ce
s
s
i
n
g
s
tr
u
c
tu
r
ed
i
m
a
g
er
y
d
ata
r
ec
eiv
ed
f
r
o
m
t
h
e
i
m
ag
er
y
s
atellite
s
.
As
d
ef
i
n
ed
b
y
B
w
o
zo
u
g
h
,
cited
in
[
5
]
,
s
p
atial
an
al
y
s
is
i
n
GI
S
i
n
v
o
l
v
es
m
ai
n
l
y
th
r
ee
t
y
p
es
o
f
o
p
er
atio
n
s
:
1
)
A
ttr
ib
u
te
Qu
ery
w
h
ic
h
is
also
k
n
o
w
n
as
non
-
s
p
a
tia
l
(
o
r
s
p
a
tia
l
)
q
u
ery
,
2
)
S
p
a
tia
l
Qu
ery
a
n
d
3
)
Gen
era
tio
n
o
f
n
ew
d
a
t
a
s
ets
f
r
o
m
t
h
e
o
r
ig
in
al
d
atab
ase.
C
o
m
b
in
i
n
g
all
th
r
ee
s
tep
s
th
e
wh
o
le
p
r
o
ce
s
s
s
tar
ts
w
it
h
s
i
m
p
le
attr
ib
u
te
q
u
er
y
ab
o
u
t
s
p
atial
d
ata
an
d
n
e
x
t
co
m
es
t
h
e
p
r
o
ce
s
s
i
n
g
o
f
s
p
atial
q
u
er
y
a
n
d
la
s
tl
y
,
t
h
e
n
e
w
d
ata
s
et
i
s
g
e
n
er
ated
f
r
o
m
t
h
ese
q
u
er
ies
t
h
at
s
er
v
e
a
s
an
alter
n
ati
v
e
d
ata
s
o
u
r
ce
o
r
in
f
o
r
m
atio
n
.
E
v
er
y
s
p
atial
d
ata
b
ef
o
r
e
a
n
al
y
s
i
s
u
n
d
er
g
o
es
f
o
r
s
p
a
tia
l
a
u
to
co
r
r
ela
tio
n
,
w
h
ich
is
a
v
alu
e
ad
d
itiv
e
s
tep
r
ec
o
g
n
ized
as
an
e
s
s
e
n
tial
f
ea
t
u
r
e
in
s
p
at
ial
d
ata
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
an
d
f
o
llo
w
i
n
g
m
ea
s
u
r
e
s
s
u
ch
as
th
e
co
r
r
ela
tio
n
co
efficien
t,
Mo
r
a
n
in
d
ex
,
jo
in
co
u
n
t
s
ta
tis
tic,
Gea
r
y’
s
C
,
G
etis
-
Ord
G
s
ta
ti
s
tic
an
d
th
e
s
emi
-
va
r
io
g
r
a
m
p
lo
t
h
av
e
b
ee
n
e
m
p
lo
y
ed
to
ass
e
s
s
th
e
g
lo
b
al
a
s
s
o
ciatio
n
o
f
t
h
e
d
ata
s
ets [
6
]
.
2
.
2
.
G
eo
v
is
ua
liza
t
io
n/
Co
m
p
ute
r
B
a
s
ed
P
a
t
t
er
n Re
co
g
nit
io
n
Geo
v
is
u
aliza
tio
n
i
s
o
n
e
o
f
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
asp
ec
ts
as
i
t
s
m
o
o
th
es
t
h
e
p
r
o
g
r
es
s
o
f
a
n
al
y
s
i
s
b
y
co
n
v
er
s
io
n
o
f
i
m
a
g
er
y
d
ata
i
n
to
t
h
e
tab
u
lar
f
o
r
m
w
h
er
e
d
if
f
er
e
n
t
s
t
ati
s
tical
an
al
y
s
is
t
ec
h
n
iq
u
es
co
u
ld
b
e
i
m
p
le
m
en
ted
.
A
p
ar
t
f
r
o
m
t
wo
an
d
th
r
ee
-
d
i
m
e
n
s
io
n
al
m
ap
p
in
g
,
t
h
at
in
cl
u
d
es
an
a
l
y
zi
n
g
o
v
er
th
e
p
h
y
s
ical
s
u
r
f
ac
e
an
d
co
n
n
ec
tio
n
a
m
o
n
g
d
if
f
er
en
t
ter
r
ain
s
n
at
u
r
al
as
w
ell
as
m
an
-
m
ad
e.
Ma
cE
ac
h
r
en
&
Kr
aa
k
[
7
]
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
A
s
s
es
s
in
g
S
ta
te
o
f th
e
A
r
t o
n
A
r
tifi
cia
l Neu
r
a
l Net
w
o
r
k
P
a
r
a
d
ig
ms fo
r
Leve
l o
f
… (
Tu
s
h
a
r
A
n
th
w
a
l
)
137
ch
ar
ac
ter
ized
th
e
m
aj
o
r
asp
ec
ts
o
f
Geo
v
is
u
aliza
t
io
n
a
n
d
ass
e
m
b
led
th
e
m
i
n
a
p
r
o
ce
s
s
r
ep
r
e
s
en
ted
b
y
a
t
h
r
ee
-
d
i
m
en
s
io
n
al
c
u
b
e
w
it
h
ex
p
lo
r
e
,
a
n
a
lyze,
s
yn
th
esiz
e
an
d
p
r
esen
t
as
m
aj
o
r
task
s
.
T
h
e
in
itial
s
tep
o
f
Geo
v
is
u
ali
za
tio
n
is
ab
o
u
t
ex
p
lo
r
in
g
a
n
d
an
al
y
zi
n
g
g
eo
g
r
ap
h
ical
d
at
a
w
h
ic
h
is
a
s
p
atial
d
ata
ca
p
tu
r
ed
f
r
o
m
h
ig
h
l
y
p
r
ec
is
e
an
d
p
o
w
er
f
u
l
s
en
s
o
r
s
o
f
v
ar
io
u
s
s
atel
lite
s
an
d
s
to
r
ed
in
to
co
m
p
u
tatio
n
al
d
ev
ices
f
o
r
f
u
r
th
er
r
ef
er
e
n
ce
s
.
I
t
s
tar
t
s
w
it
h
p
r
o
ce
s
s
in
g
o
f
s
atell
ite
i
m
a
g
er
y
d
ata
u
s
i
n
g
d
i
g
ita
l
i
m
a
g
e
p
r
o
ce
s
s
in
g
to
o
ls
w
h
ic
h
t
h
e
n
g
et
co
n
v
er
ted
in
to
th
e
tab
u
lar
f
o
r
m
th
at
co
u
ld
ea
s
il
y
in
ter
p
r
et
u
s
i
n
g
d
if
f
er
e
n
t
s
tati
s
tical
tech
n
iq
u
e
s
.
T
h
e
s
p
atial
d
ata
co
llected
is
f
u
r
t
h
er
p
u
t
i
n
to
f
o
r
au
to
-
co
r
r
ec
tio
n
,
i
n
ter
p
o
latio
n
,
p
r
u
n
i
n
g
,
n
o
r
m
a
lizatio
n
an
d
s
to
r
ed
in
a
m
ea
n
i
n
g
f
u
l
f
o
r
m
at.
S
y
n
t
h
es
ize
is
all
ab
o
u
t
d
eliv
er
in
g
t
h
e
n
e
w
o
u
tco
m
es
o
u
t
o
f
r
a
w
d
ata
i
n
m
o
r
e
m
ea
n
i
n
g
f
u
l
a
n
d
af
ter
i
m
p
le
m
en
ta
tio
n
o
f
s
er
ie
s
o
f
s
tati
s
tical
tec
h
n
iq
u
es
an
d
m
et
h
o
d
s
.
T
h
e
last
s
tep
o
f
p
r
es
en
tatio
n
is
b
asicall
y
to
r
ep
r
ese
n
t t
h
e
i
n
f
o
r
m
atio
n
i
n
to
m
o
r
e
a
g
e
n
er
alize
d
f
o
r
m
at
k
n
o
w
n
as
k
n
o
w
led
g
e
w
h
ic
h
a
ls
o
in
co
r
p
o
r
ates
th
e
v
i
s
u
al
izat
io
n
o
f
g
eo
g
r
ap
h
ica
l
i
m
ag
e
s
o
n
g
lo
b
al
m
ap
s
lik
e
Go
o
g
le
m
ap
o
r
an
y
o
t
h
er
GI
S
to
o
ls
w
h
ic
h
co
u
ld
r
es
u
lt
in
p
r
ed
ictio
n
s
o
f
d
i
f
f
er
e
n
t a
s
p
ec
t a
n
d
s
tatu
s
o
f
p
h
y
s
ical
asp
ec
ts
o
f
t
h
e
ea
r
th
.
W
h
ile
i
m
p
le
m
en
tati
o
n
o
f
g
e
o
s
tatis
tical
tec
h
n
iq
u
es,
s
o
m
e
o
f
th
ese
co
m
m
o
n
l
y
u
s
ed
m
u
lti
v
ar
iate
tech
n
iq
u
es
ar
e
clu
s
ter
a
n
al
y
s
is
(
C
A
)
,
f
ac
to
r
a
n
al
y
s
i
s
/p
r
in
cip
al
co
m
p
o
n
e
n
t
s
(
F
A
/P
C
A)
an
d
d
is
cr
i
m
in
a
n
t
an
al
y
s
is
(
D
A
)
w
h
ic
h
r
es
u
lt
s
i
n
to
an
e
f
f
ec
t
iv
e
d
ata
m
an
a
g
e
m
en
t
n
et
w
o
r
k
,
m
o
n
ito
r
in
g
s
y
s
te
m
f
o
r
s
p
atial
d
ata
r
ed
u
cin
g
t
h
e
o
n
g
r
o
u
n
d
s
a
m
p
lin
g
co
s
t,
lab
o
r
a
n
d
ef
f
o
r
t
t
h
at
r
es
u
lt
s
m
o
r
e
ac
c
u
r
ate
p
i
ctu
r
e
o
f
la
n
d
s
ca
p
e
v
ar
iatio
n
s
.
T
h
e
au
t
h
o
r
in
h
is
w
o
r
k
[
8
]
d
e
m
o
n
s
tr
ated
t
h
at
w
a
ter
s
a
m
p
l
es
f
r
o
m
m
aj
o
r
s
a
m
p
l
in
g
s
tati
o
n
s
w
er
e
co
llected
in
d
u
e
ti
m
e
s
p
an
a
n
d
ex
p
lo
r
ato
r
y
a
n
al
y
s
i
s
o
f
d
ata
w
as
m
ad
e
b
y
b
o
x
p
lo
t
s
,
A
NOV
A
,
d
is
p
la
y
m
et
h
o
d
s
(
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
)
a
n
d
u
n
s
u
p
er
v
is
ed
p
atter
n
r
ec
o
g
n
itio
n
(
clu
s
ter
an
al
y
s
i
s
)
to
an
al
y
s
is
o
v
er
th
e
s
o
u
r
ce
o
f
v
ar
iatio
n
s
o
f
w
ater
q
u
ali
t
y
.
P
o
in
t
s
o
u
r
ce
an
al
y
s
i
s
f
o
r
p
o
llu
t
io
n
id
e
n
ti
f
icatio
n
,
n
u
tr
ien
t
o
r
ig
in
atio
n
s
o
u
r
ce
s
li
k
e
m
u
n
icip
al
w
a
s
te
w
ater
w
er
e
d
e
m
o
n
s
tr
ated
an
d
t
h
u
s
clas
s
i
f
icat
io
n
o
f
r
iv
er
w
ater
s
a
m
p
les
w
as a
ch
iev
ed
u
s
i
n
g
P
C
A
an
d
cl
u
s
ter
an
a
l
y
s
is
.
I
n
th
e
s
tu
d
ie
s
p
r
esen
ted
b
y
Alb
er
to
et
al.
,
[
9
]
an
d
Sin
g
h
et
al
.
,
[
1
0
]
,
b
o
th
s
p
atial
an
d
te
m
p
o
r
al
d
ata
f
o
r
r
iv
er
s
ar
e
ev
a
lu
ated
f
o
r
q
u
alit
y
a
n
al
y
s
i
s
,
w
h
er
e
d
i
f
f
er
en
t
p
ar
am
eter
s
f
r
o
m
s
ca
tter
ed
s
ta
tio
n
s
ar
e
co
llected
f
o
r
m
u
lati
n
g
a
co
m
p
le
x
d
ata
m
atr
ix
,
an
d
th
e
n
tr
ea
ted
u
s
i
n
g
t
h
e
clu
s
ter
an
al
y
s
i
s
(
C
A
)
th
at
r
en
d
er
s
g
o
o
d
r
e
s
u
lts
as
a
f
ir
s
t
ex
p
lo
r
ato
r
y
m
et
h
o
d
to
ev
alu
ate
b
o
th
s
p
atial
an
d
tem
p
o
r
al
d
if
f
er
e
n
ce
s
,
f
ac
to
r
an
al
y
s
i
s
/p
r
in
cip
al
co
m
p
o
n
e
n
t
s
(
F
A
/P
C
A
)
w
h
ic
h
w
er
e
h
elp
s
i
n
id
e
n
ti
f
y
i
n
g
g
r
o
u
p
co
m
p
o
n
en
t
s
a
n
d
d
is
cr
i
m
i
n
an
t
an
al
y
s
is
(
D
A
)
th
at
s
h
o
w
ed
b
es
t
r
es
u
lts
f
o
r
r
ed
u
ce
d
d
ata
d
i
m
e
n
s
io
n
s
in
lar
g
e
d
ataset
s
.
T
h
is
s
t
u
d
y
p
r
ese
n
ts
i
n
ev
itab
ilit
y
a
n
d
u
s
e
f
u
ln
e
s
s
o
f
m
u
lti
v
ar
iate
s
t
atis
tical
tec
h
n
iq
u
e
s
f
o
r
ev
al
u
atio
n
an
d
i
n
ter
p
r
etatio
n
o
f
t
h
e
lar
g
e
n
u
m
b
er
o
f
co
m
p
le
x
d
ata
o
n
w
ater
q
u
al
it
y
w
i
th
a
s
ig
h
t
to
ac
ce
s
s
b
ette
r
in
f
o
r
m
atio
n
a
n
d
f
u
r
t
h
e
r
d
es
ig
n
in
g
a
n
ef
f
ec
ti
v
e
m
o
n
ito
r
i
n
g
a
n
d
m
a
n
a
g
e
m
e
n
t
n
et
w
o
r
k
f
o
r
w
a
ter
r
eso
u
r
ce
s
.
Geo
g
r
ap
h
ical
I
n
f
o
r
m
atio
n
S
y
s
te
m
(
GI
S)
ar
e
m
ea
n
t
f
o
r
r
e
s
o
u
r
ce
m
an
a
g
e
m
e
n
t
a
n
d
is
a
n
e
f
f
icie
n
t
d
ec
is
io
n
-
m
a
k
i
n
g
to
o
l h
o
w
e
v
er
,
p
o
w
er
ed
w
i
th
lo
ts
o
f
s
o
p
h
i
s
ti
ca
ted
tech
n
o
lo
g
y
it is
n
o
t r
ea
d
y
u
s
ed
b
y
co
m
m
o
n
p
eo
p
les
b
ec
au
s
e
o
f
lac
k
o
f
f
a
cilit
y
to
d
is
tr
ib
u
te
t
h
e
a
n
al
y
z
ed
in
f
o
r
m
atio
n
i
n
a
n
e
f
f
icie
n
t
m
a
n
n
er
.
I
n
f
u
r
th
er
ad
v
an
ce
m
en
t,
C
aq
u
ar
d
et
al.
,
[
1
1
]
,
p
r
o
p
o
s
ed
th
e
ca
r
to
g
r
ap
h
ic
r
ep
r
esen
tatio
n
o
f
w
ate
r
q
u
alit
y
m
ap
p
i
n
g
in
f
o
r
m
atio
n
w
h
ic
h
ca
n
p
r
o
p
ag
ate
th
e
c
u
s
to
m
ized
r
esu
l
t
o
n
b
ases
o
f
v
ar
iatio
n
i
n
clie
n
tel
e.
W
ith
th
e
u
s
e
o
f
in
ter
p
o
latio
n
an
d
e
x
tr
ap
o
latio
n
tech
n
iq
u
e,
v
is
u
al
d
ata
is
p
u
t
in
to
f
o
r
co
r
r
elatio
n
a
n
d
clu
s
te
r
in
g
a
n
al
y
s
i
s
,
alo
n
g
w
it
h
th
e
s
a
m
e
g
r
ad
atio
n
o
f
co
lo
r
s
ar
e
u
s
ed
to
r
ep
r
ese
n
t
t
h
e
lev
el
o
f
w
ater
q
u
alit
y
f
r
o
m
lo
w
er
to
h
i
g
h
er
.
T
h
e
p
atter
n
r
ec
o
g
n
itio
n
u
s
i
n
g
s
o
m
e
p
o
w
er
f
u
l
lear
n
in
g
tech
n
iq
u
e
s
ar
e
ad
d
iti
v
es
th
a
t
m
ak
in
g
th
e
g
eo
g
r
ap
h
ical
v
ie
w
m
o
r
e
r
ea
l
i
s
tic
to
t
h
e
h
u
m
a
n
e
y
es.
F
u
r
t
h
er
to
i
m
p
ar
t
t
h
e
h
ig
h
er
r
eso
l
u
tio
n
a
n
d
m
o
v
i
n
g
ah
ea
d
o
n
ad
d
in
g
d
i
m
en
s
io
n
s
to
th
e
p
er
s
p
ec
ti
v
e
v
ie
w
s
,
an
i
m
at
io
n
tech
n
i
q
u
es
h
ad
also
en
h
a
n
ce
d
th
e
g
eo
v
is
u
aliza
tio
n
ex
p
er
ien
ce
.
2
.
3
.
M
a
chine Lea
rning
T
ec
h
niq
ue
s
A
r
ti
f
icial
I
n
telli
g
e
n
ce
ex
p
lo
r
ed
a
n
e
w
h
o
r
izo
n
o
f
in
tel
li
g
en
t
m
ac
h
i
n
es
t
h
at
ar
e
en
a
b
led
w
ith
co
g
n
itio
n
p
o
w
er
w
ith
t
h
e
h
u
g
e
d
atab
ase
to
s
to
r
e
an
d
p
r
o
ce
s
s
in
f
o
r
m
at
io
n
s
o
as
to
i
m
p
ar
t
k
n
o
w
led
g
e
an
d
f
ac
ilit
ate
s
in
t
h
e
d
a
y
to
d
a
y
w
o
r
k
in
g
en
v
ir
o
n
m
e
n
t.
Un
l
ik
e
s
ta
tis
tical
tec
h
n
iq
u
es
w
h
ic
h
ar
e
ex
p
er
t
in
p
r
ed
ictin
g
s
en
s
e
o
u
t
o
f
li
n
ea
r
d
ata,
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
s
w
o
u
ld
s
ta
n
d
f
o
r
a
n
al
y
zi
n
g
o
v
er
n
o
n
-
li
n
ea
r
d
ata
s
et
w
h
ic
h
ac
t
u
all
y
p
r
ev
ail
r
ea
l
w
o
r
ld
r
ep
r
esen
tatio
n
.
C
â
m
ar
a
et
al,
[
1
2
]
in
th
e
i
n
itia
l
p
h
a
s
e
o
f
e
m
er
g
e
n
ce
o
f
g
eo
co
m
p
u
tat
io
n
ad
v
o
ca
ted
t
o
w
ar
d
s
th
e
e
x
p
lo
it
o
f
co
m
p
u
tatio
n
al
-
i
n
te
n
s
i
v
e
tec
h
n
iq
u
es
s
u
c
h
as
n
eu
r
al
n
et
w
o
r
k
s
,
h
e
u
r
is
tic
s
ea
r
c
h
an
d
ce
llu
lar
au
to
m
ata
f
o
r
s
p
atial
d
ata
an
al
y
s
is
.
W
ith
t
h
e
e
v
o
lu
t
io
n
o
f
tec
h
n
iq
u
es
lik
e
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
s
(
A
NN
s
)
,
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
es
(
SVMs)
an
d
C
ell
u
lar
A
u
to
m
at
a
(
m
ai
n
l
y
f
o
r
s
i
m
u
latio
n
o
f
m
ac
h
in
e
s
b
eh
a
v
io
r
)
,
th
ese
ap
p
r
o
ac
h
es
m
ar
k
ed
th
eir
i
m
p
o
r
tan
ce
i
n
an
a
l
y
zi
n
g
s
p
at
ial
an
d
te
m
p
o
r
al
d
ata
b
ec
au
s
e
o
f
t
h
eir
n
a
tiv
e
ab
il
it
y
to
w
ar
d
s
m
o
d
elin
g
o
f
co
m
p
le
x
n
o
n
l
in
ea
r
d
atase
ts
.
A
N
Ns
ar
e
e
n
ab
led
w
it
h
t
h
e
ab
ilit
y
f
o
r
s
u
p
er
v
i
s
ed
as
well
as
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
elin
g
f
o
r
b
asic
task
s
li
k
e
clas
s
i
f
icatio
n
,
cl
u
s
ter
in
g
,
a
n
d
p
r
o
p
h
ec
y
th
a
t
ca
n
b
e
d
r
a
w
n
o
u
t
o
f
r
eg
r
ess
io
n
an
al
y
s
i
s
o
f
e
m
p
ir
ical
d
ata
s
ets.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
4
,
Dec
em
b
er
2
0
1
6
:
1
5
3
–
142
138
An
o
th
er
m
ac
h
in
e
lear
n
i
n
g
m
e
th
o
d
i.e
.
Ker
n
el
m
et
h
o
d
s
m
e
n
tio
n
ed
b
y
B
o
s
er
et
al.
,
[
1
3
]
,
w
it
h
k
er
n
e
l
ac
tio
n
s
u
s
ag
e
s
f
o
r
m
ap
p
in
g
w
it
h
h
ig
h
er
d
i
m
en
s
io
n
a
l
f
ea
t
u
r
es
s
p
ac
e
w
i
th
o
u
t
ex
p
licit
c
o
m
p
u
tatio
n
o
f
m
ap
s
.
R
esear
ch
in
g
eo
s
p
atial
d
ata
m
o
d
eli
n
g
is
m
o
ld
i
n
g
to
w
ar
d
s
in
te
lli
g
en
t
s
o
f
t
w
ar
e
to
o
ls
d
ev
elo
p
ed
th
at
ar
e
d
ev
elo
p
e
d
u
n
d
er
th
e
f
r
a
m
e
w
o
r
k
o
f
Ma
ch
i
n
e
L
ea
r
n
in
g
O
f
f
ice,
an
d
f
e
w
to
m
e
n
tio
n
ar
e
to
p
o
-
cli
m
atic
m
o
d
eli
n
g
,
n
atu
r
al
h
az
ar
d
ass
ess
m
e
n
ts
,
w
h
ic
h
in
cl
u
d
es;
h
ea
v
y
r
ai
n
f
a
ll
r
esu
lti
n
g
in
lan
d
s
lid
es,
av
alan
ch
e
s
in
h
ig
h
er
altitu
d
es,
p
o
llu
tio
n
m
ap
p
in
g
;
air
an
d
s
o
il
p
o
ll
u
tio
n
a
lo
n
g
w
it
h
i
n
d
o
o
r
r
ad
o
n
an
d
h
ea
v
y
m
etal
s
p
r
ese
n
ce
,
n
atu
r
al
r
eso
u
r
ce
s
ass
e
s
s
m
e
n
ts
,
r
em
o
te
s
e
n
s
in
g
i
m
ag
er
y
d
ata
class
i
f
icatio
n
,
s
o
cio
-
ec
o
n
o
m
ic
d
ata
an
al
y
s
i
s
an
d
g
eo
v
i
s
u
al
is
atio
n
,
etc.
[
1
4
]
.
T
h
e
Fig
u
r
e
1
s
h
o
w
n
b
elo
w
d
ep
icted
a
b
r
o
a
d
tax
o
n
o
m
ical
b
r
ea
k
d
o
w
n
w
it
h
m
aj
o
r
tech
n
o
lo
g
y
th
a
t
co
v
er
s
th
e
w
h
o
le
asp
ec
t o
f
g
e
o
co
m
p
u
tatio
n
.
Fig
u
r
e
1
.
T
ax
o
n
o
m
y
o
f
Geo
co
m
p
u
tat
io
n
T
ec
h
n
iq
u
es
3.
ST
A
T
E
O
F
T
H
E
ART
I
n
th
i
s
s
ec
tio
n
t
h
e
d
if
f
er
en
t
t
ec
h
n
iq
u
es
o
n
eu
tr
o
p
h
icatio
n
ev
alu
a
tio
n
ar
e
d
is
c
u
s
s
ed
w
i
th
th
e
m
ai
n
f
o
cu
s
o
n
t
h
e
tr
ad
itio
n
m
eth
o
d
s
an
d
t
h
eir
m
e
th
o
d
o
lo
g
ies
w
h
ic
h
s
t
ill
ar
e
t
h
e
b
asic
b
u
il
d
in
g
b
lo
ck
o
f
e
v
er
y
g
eo
co
m
p
u
ti
n
g
s
y
s
te
m
th
at
d
e
als
w
i
th
t
h
e
s
i
m
ilar
t
y
p
e
o
f
p
r
o
b
lem
ap
p
r
aisal.
T
h
e
tw
o
m
ain
s
ec
tio
n
s
ex
p
lai
n
th
e
d
ata
e
s
s
i
m
i
latio
n
f
r
o
m
e
u
tr
o
p
h
icate
d
w
ater
b
o
d
y
an
d
m
a
n
a
g
e
m
e
n
t
o
f
th
e
s
e
d
ata
f
o
r
f
u
r
t
h
er
d
ec
is
io
n
m
ak
in
g
o
r
in
r
esto
r
atio
n
m
ec
h
an
is
m
s
.
T
h
e
n
ex
t
s
u
b
s
ec
tio
n
p
r
esen
ts
t
h
e
s
tate
o
f
th
e
ar
t
in
n
eu
r
al
n
e
t
w
o
r
k
f
o
r
v
ar
io
u
s
s
i
m
ilar
w
ater
q
u
alit
y
ex
a
m
in
at
io
n
p
r
o
b
lem
s
w
h
er
e
th
e
p
r
i
m
ar
y
d
ata
ar
e
s
p
atial
d
ata
f
r
o
m
d
if
f
er
e
n
t
s
atellite
s
e
n
s
o
r
s
w
ith
v
ar
ian
t m
etad
ata
an
d
o
f
v
ar
ian
t t
y
p
e
o
f
s
o
u
r
ce
s
lik
e
la
k
e,
o
ce
an
,
s
ea
etc.
3
.
1
.
Da
t
a
f
o
r
E
utr
o
ph
ica
t
io
n
M
a
na
g
em
e
nt
a
nd
Co
ntr
o
l
W
ater
is
th
e
m
ai
n
s
tr
ea
m
o
f
li
f
e
o
n
ea
r
t
h
a
n
d
p
r
esen
tl
y
alo
n
g
w
it
h
t
h
e
s
ca
r
ci
t
y
o
f
w
ater
,
it
s
q
u
alit
y
i
s
also
a
p
r
o
m
i
n
e
n
t
is
s
u
e
to
d
ea
l
w
i
th
t
h
u
s
w
e
h
ad
p
r
ef
er
r
ed
th
e
p
r
o
b
lem
o
f
e
u
tr
o
p
h
icatio
n
o
f
w
ater
b
o
d
ies
f
o
r
w
h
ic
h
w
e
ar
e
tr
y
i
n
g
to
id
en
t
if
y
th
e
g
eo
co
m
p
u
tatio
n
tec
h
n
iq
u
es
i
m
p
le
m
en
ted
to
m
ea
s
u
r
e
th
e
cu
r
r
en
t
s
ce
n
ar
i
o
o
n
q
u
alit
y
a
n
d
f
u
t
u
r
is
tic
m
et
h
o
d
o
lo
g
ies.
As
m
e
n
tio
n
ed
i
n
th
e
p
u
b
licatio
n
(
h
ttp
://
www.
u
n
ep
.
o
r
.
j
p
)
[
3
1
]
,
d
if
f
er
e
n
t
w
a
y
s
o
f
m
o
n
i
to
r
in
g
f
o
r
th
e
i
m
p
ac
ts
o
f
eu
tr
o
p
h
ica
t
io
n
an
d
to
estab
lis
h
m
a
n
ag
e
m
en
t
o
p
tio
n
s
ar
e:
1
)
ch
emic
a
l
mo
n
ito
r
in
g
:
th
at
f
o
c
u
s
o
n
to
tal
p
h
o
s
p
h
o
r
u
s
co
n
ten
t
m
ea
s
u
r
e
m
e
n
t
h
o
w
ev
er
,
i
t
is
Nitr
o
g
en
w
h
ich
h
ad
m
o
r
e
s
i
g
n
i
f
ican
ce
o
v
er
n
u
tr
ie
n
t
co
n
ten
t
v
al
u
atio
n
f
o
r
e
u
tr
o
p
h
icatio
n
esti
m
atio
n
,
a
ls
o
c
h
e
m
ical
m
o
n
ito
r
in
g
is
m
o
r
e
d
if
f
ic
u
lt
i
n
a
la
ke
or
r
eser
v
o
ir
en
v
ir
o
n
m
e
n
t.;
2
)
b
io
-
a
s
s
ess
men
t
:
w
h
ic
h
ac
co
u
n
ts
o
v
e
r
m
ai
n
r
esu
ltan
t
o
f
eu
tr
o
p
h
icatio
n
i.e
.
ab
u
n
d
a
n
t
g
r
o
w
t
h
in
b
io
m
a
s
s
,
w
h
ic
h
in
tu
r
n
m
ea
s
u
r
e
f
o
r
ch
lo
r
o
p
h
y
ll
-
a
an
d
also
co
n
ce
n
tr
atio
n
o
f
p
ar
ticu
late
o
r
g
an
ic
ca
r
b
o
n
(
P
OC
)
co
n
te
n
t,
h
o
w
e
v
er
n
o
t
v
er
y
ap
t
f
o
r
r
o
u
tin
e
m
o
n
ito
r
i
n
g
s
y
s
te
m
.
;
a
n
d
3
)
esti
ma
ted
tech
n
iq
u
es
:
w
h
ic
h
in
c
lu
d
es
p
o
in
t
s
o
u
r
ce
an
d
n
o
n
-
p
o
in
t
s
o
u
r
ce
esti
ma
tio
n
tech
n
iq
u
es
th
at
f
o
u
n
d
m
o
s
t
ap
t
f
o
r
eu
tr
o
p
h
icat
io
n
m
o
n
it
o
r
in
g
s
y
s
te
m
w
h
ic
h
i
n
cl
u
d
es
p
h
o
s
p
h
o
r
o
u
s
d
ata
to
g
eth
er
w
i
th
o
th
er
k
n
o
w
led
g
e
o
n
lan
d
,
d
e
m
o
g
r
ap
h
y
etc
.
,
th
at
co
u
ld
ea
s
il
y
i
n
te
g
r
ate
d
f
o
r
elu
cid
atio
n
.
Ho
w
e
v
er
th
ese
m
a
y
v
ar
y
o
v
er
r
esu
lt
s
b
ec
au
s
e
o
f
v
ar
io
u
s
f
ac
to
r
s
lik
e;
s
p
atial
f
ac
to
r
s
,
au
to
-
co
r
r
ec
tio
n
,
class
i
f
icatio
n
an
d
o
th
er
tec
h
n
i
q
u
es
t
h
at
ar
e
u
s
ed
f
o
r
an
al
y
s
i
s
an
d
th
i
s
is
m
o
r
e
ab
o
u
t
ac
cu
r
a
c
y
in
co
m
p
u
tat
io
n
tech
n
iq
u
es.
Geo
s
p
atial
d
ata
f
r
o
m
s
atel
lit
es
ar
e
ea
s
il
y
av
ailab
le
a
m
o
n
g
w
h
ic
h
L
a
n
d
s
at
i
m
a
g
er
y
b
ein
g
w
id
el
y
u
s
ed
w
it
h
d
ata
f
r
o
m
th
r
ee
m
aj
o
r
s
en
s
o
r
s
:
M
u
lti
-
s
p
ec
tr
al
Sca
n
n
er
(
MS
S),
T
M
(
T
h
em
at
ic
Ma
p
p
er
)
an
d
E
T
M+
G
E
O
C
O
M
P
U
T
A
T
I
O
N
S
p
a
t
i
a
l
D
a
t
a
A
n
a
l
y
s
i
s
a
n
d
M
i
n
i
n
g
T
e
c
h
n
i
q
u
e
s
S
t
at
i
s
t
i
c
al
T
e
c
h
n
i
q
u
e
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s
S
p
at
i
al
A
u
t
oc
or
r
e
l
at
i
on
G
e
o
v
i
s
u
a
l
i
z
a
t
i
o
n
/
C
o
m
p
u
t
e
r
B
a
s
e
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
C
l
as
s
i
f
i
c
at
i
on
an
d
C
l
u
s
t
e
r
i
n
g
S
i
m
u
l
at
i
on
an
d
D
yn
am
i
c
M
od
e
l
i
n
g
A
r
t
i
f
i
c
i
al
N
e
u
r
al
N
e
t
w
or
k
S
u
p
p
or
t
V
e
c
t
or
M
ac
h
i
n
e
G
e
oS
t
at
i
s
t
i
c
s
an
d
P
r
e
d
i
c
t
i
on
E
x
p
l
or
at
or
y
D
at
a
A
n
al
ys
i
s
R
u
l
e
B
as
e
d
T
e
c
h
n
i
q
u
e
s
C
ar
t
og
r
ap
h
i
c
V
i
s
u
al
i
z
at
i
on
A
n
i
m
at
i
on
T
e
c
h
n
i
q
u
e
s
G
e
og
r
ap
h
i
c
K
n
ow
l
e
d
ge
D
i
s
c
ov
e
r
y
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
A
s
s
es
s
in
g
S
ta
te
o
f th
e
A
r
t o
n
A
r
tifi
cia
l Neu
r
a
l Net
w
o
r
k
P
a
r
a
d
ig
ms fo
r
Leve
l o
f
… (
Tu
s
h
a
r
A
n
th
w
a
l
)
139
(
E
n
h
a
n
ce
r
T
h
e
m
at
ic
Ma
p
p
er
P
lu
s
)
w
h
er
e
B
ar
u
h
a
et
al.
,
[
1
5
]
,
Su
d
h
ee
r
et
al.
,
[
1
6
]
,
C
an
zian
i
et
al.
,
[
1
7
]
,
an
d
Gu
a
n
et
al.
,
[
1
8
]
,
m
a
k
e
u
s
es
o
f
th
e
s
e
i
m
ag
er
y
s
p
atial
d
at
a
f
o
r
an
al
y
s
i
s
o
f
w
a
ter
q
u
ali
t
y
u
s
i
n
g
d
i
f
f
er
en
t
g
eo
co
m
p
u
tat
io
n
tech
n
iq
u
e
s
.
A
l
s
o
s
o
m
e
d
ata
f
r
o
m
SP
OT
s
atelli
te
i
m
a
g
es,
MO
DI
S
i
m
ag
er
y
a
n
d
I
R
S
P
6
s
en
s
o
r
s
i
m
a
g
er
y
w
er
e
e
x
p
lo
ited
to
s
tu
d
y
th
e
s
ed
i
m
e
n
t
a
n
d
n
u
tr
ie
n
t
le
v
el
i
n
w
ater
b
o
d
ie
s
,
Mo
h
a
m
ed
et
al.
,
[
1
9
]
,
Xu
e
et
al.
,
[
2
0
]
,
an
d
Sh
e
ela
et
al,
[
2
1
]
r
esp
ec
tiv
el
y
.
3
.
2
.
Art
if
icia
l N
eura
l N
et
w
o
r
k
M
o
dels
L
i
m
ited
w
a
ter
q
u
ali
t
y
d
ata
an
d
t
h
e
h
ig
h
co
s
t
o
f
w
ater
q
u
alit
y
m
o
n
ito
r
in
g
o
f
ten
p
o
s
e
s
er
io
u
s
p
r
o
b
lem
s
f
o
r
p
r
o
ce
s
s
-
b
ased
m
o
d
eli
n
g
ap
p
r
o
ac
h
es
to
m
o
d
u
late
t
h
e
s
a
m
e
f
o
r
ti
m
e
s
er
ies
f
o
r
ec
ast.
A
NN
s
p
r
o
v
id
e
r
ea
s
o
n
ab
le
i
m
p
le
m
e
n
tatio
n
o
p
tio
n
s
,
b
ec
au
s
e
t
h
e
y
ar
e
co
m
p
u
tatio
n
all
y
v
er
y
f
a
s
t
an
d
r
eq
u
ir
e
m
a
n
y
f
e
w
er
in
p
u
ts
p
ar
a
m
e
ter
an
d
in
p
u
t
s
co
n
d
itio
n
s
t
h
an
d
eter
m
i
n
is
t
ic
m
o
d
els.
O
n
th
e
o
t
h
er
h
an
d
to
b
eh
av
e
co
g
n
iti
v
el
y
th
e
y
d
o
r
eq
u
is
ite
f
o
r
a
lar
g
e
p
o
o
l
o
f
r
ep
r
esen
tati
v
e
d
ata
s
ets
f
o
r
tr
ain
i
n
g
a
n
d
ap
p
r
o
p
r
iate
lear
n
in
g
alg
o
r
ith
m
s
.
A
N
Ns
ar
e
e
x
p
er
i
m
e
n
ted
f
o
r
i
ts
u
s
e
f
u
ln
e
s
s
in
w
ater
q
u
al
it
y
p
r
ed
ictio
n
;
n
e
v
er
t
h
eles
s
SV
M
h
ad
al
s
o
d
em
o
n
s
tr
ated
g
o
o
d
r
esu
lt
s
f
o
r
s
a
m
e.
A
co
m
p
ar
ati
v
e
s
tu
d
y
o
n
A
NN
a
n
d
SV
M
i
n
[
2
2
]
,
s
h
o
w
ed
th
e
s
u
p
er
io
r
r
esu
lt
b
y
later
tech
n
iq
u
e
w
h
er
e
au
th
o
r
s
p
r
ed
icted
w
a
ter
q
u
alit
y
o
f
r
iv
er
s
b
y
es
ti
m
ati
n
g
to
ta
l
n
itro
g
e
n
an
d
to
tal
p
h
o
s
p
h
o
r
u
s
o
b
s
er
v
ed
.
I
n
a
n
o
th
er
r
esear
ch
b
y
L
iao
et
al.
,
[
2
3
]
,
w
ater
q
u
alit
y
i
s
a
s
s
es
s
e
d
u
s
i
n
g
SV
M
a
n
d
g
en
et
ic
alg
o
r
ith
m
w
h
ich
p
r
o
v
ed
to
d
eliv
er
ac
ce
p
tab
le
r
esu
lts
an
d
also
ef
f
icie
n
t
en
o
u
g
h
f
o
r
class
i
f
icatio
n
o
f
w
ater
q
u
alit
y
.
C
h
u
et
a
l.,
[
2
4
]
p
r
o
p
o
s
ed
a
ca
s
e
s
t
u
d
y
w
h
er
e
Ho
p
f
ield
n
e
u
r
al
n
et
w
o
r
k
i
s
e
m
b
ed
d
ed
w
it
h
Fac
to
r
An
al
y
s
i
s
(
F
A
)
tech
n
iq
u
es
to
f
o
r
m
Facto
r
An
al
y
s
is
-
Ho
p
f
i
eld
Neu
r
al
Net
w
o
r
k
(
F
A
HN
N)
to
id
en
ti
f
y
th
e
ass
es
s
m
en
t
f
ac
to
r
s
f
o
r
w
ater
q
u
alit
y
m
ea
s
u
r
e
m
e
n
t
t
h
at
p
r
o
v
ed
to
p
r
o
v
id
e
m
o
r
e
r
eliab
le
j
u
d
g
m
e
n
t a
n
d
v
al
u
ab
le
in
f
o
r
m
atio
n
a
s
co
m
p
ar
ed
w
it
h
alik
e
tec
h
n
iq
u
es
.
T
h
e
r
esu
lt
i
m
p
ar
ted
b
y
th
e
m
o
d
els
also
d
ep
en
d
s
o
n
n
u
m
b
e
r
o
f
d
ata
s
et
an
d
u
s
ed
tr
ain
in
g
ap
p
r
o
ac
h
alo
n
g
w
it
h
t
h
e
lear
n
i
n
g
tech
n
iq
u
es
an
d
to
o
ls
w
h
ich
to
g
et
h
er
h
av
e
a
d
ir
ec
t
i
m
p
ac
t
o
n
t
h
e
q
u
alit
y
o
f
r
es
u
lt
s
an
n
o
u
n
ce
d
b
y
t
h
e
s
y
s
te
m
.
ANNs
ar
e
ab
le
to
ap
p
r
o
x
i
m
ate
ac
cu
r
atel
y
co
m
p
l
icate
d
n
o
n
-
lin
ea
r
i
n
p
u
t
-
o
u
tp
u
t
r
elatio
n
s
h
ip
s
.
First
l
y
A
N
Ns
is
r
eq
u
ir
in
g
tr
ai
n
i
n
g
o
r
ca
lib
r
atio
n
o
n
th
e
b
asi
s
o
f
lo
ts
o
f
s
ta
tis
tical
d
ata.
A
f
ter
tr
ain
i
n
g
,
ANN
i
s
b
ei
n
g
test
ed
o
r
v
er
if
ied
f
o
r
s
o
m
e
i
n
p
u
t
w
h
o
s
e
o
u
tp
u
t
is
alr
ea
d
y
k
n
o
w
n
.
T
h
e
A
N
N
tech
n
iq
u
es
ar
e
f
le
x
ib
le
en
o
u
g
h
to
ac
co
m
m
o
d
ate
ad
d
itio
n
a
l
co
n
s
tr
ain
ts
t
h
at
m
a
y
co
m
e
u
p
in
t
h
e
ap
p
licatio
n
.
Mo
r
eo
v
er
,
A
NN
m
o
d
el
ca
n
r
ev
ea
l
h
id
d
en
r
elat
io
n
s
h
ip
s
i
n
t
h
e
c
h
r
o
n
o
lo
g
ical
d
ata,
t
h
u
s
a
i
d
in
g
th
e
es
ti
m
atio
n
o
f
n
u
tr
ien
t
p
o
llu
ta
n
t.
T
h
er
e
ar
e
m
o
r
e
ap
p
licatio
n
s
o
f
p
r
ed
ictio
n
b
ased
i
m
p
licat
io
n
s
o
f
n
eu
r
al
n
et
w
o
r
k
li
k
e
f
o
r
est
co
v
er
ed
ar
ea
,
lan
d
u
s
a
g
e
m
o
d
eli
n
g
,
n
at
u
r
al
r
eso
u
r
ce
esti
m
atio
n
,
n
at
u
r
al
ca
la
m
it
y
(
f
lo
o
d
,
lan
d
s
lid
e,
c
y
clo
n
e
etc.
)
ef
f
ec
ted
ar
ea
an
al
y
s
is
a
n
d
m
u
ch
m
o
r
e
w
h
ich
h
ad
a
d
ir
ec
t
im
p
ac
t
o
n
n
at
u
r
al
r
eso
u
r
ce
m
an
a
g
e
m
e
n
t a
n
d
p
lan
n
i
n
g
s
y
s
te
m
s
.
Am
o
n
g
th
e
in
itial
ap
p
licatio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
m
o
d
eli
n
g
i
n
e
v
alu
at
io
n
o
f
i
m
a
g
er
y
d
ata
f
r
o
m
s
atellite
s
e
n
s
o
r
s
(
u
s
i
n
g
L
a
n
d
s
atT
M)
b
y
B
ar
u
h
a
et
al.
[
1
5
]
an
d
P
an
d
a
et
al.
[
2
5
]
,
th
e
r
esea
r
ch
co
m
e
s
o
u
t
w
it
h
s
o
m
e
p
r
o
m
i
s
i
n
g
r
es
u
lts
w
h
ic
h
e
f
f
ec
ti
v
e
a
n
d
s
i
m
p
le
i
m
p
le
m
en
tatio
n
o
n
th
e
est
i
m
a
tio
n
o
f
la
k
e
w
ater
q
u
ali
t
y
m
ai
n
l
y
co
n
ce
n
tr
atio
n
o
f
ch
lo
r
o
p
h
y
ll
an
d
s
o
lid
s
ed
i
m
e
n
t
s
.
Un
li
k
e
th
e
f
o
r
m
er
w
h
ic
h
u
s
e
s
th
e
m
o
s
t
co
m
m
o
n
m
o
d
el
B
ac
k
P
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
m
o
d
el,
later
i
m
p
le
m
e
n
ted
R
ad
ial
b
asis
f
u
n
c
ti
o
n
n
e
u
r
al
(
R
B
FN)
n
et
w
o
r
k
.
T
h
e
y
w
er
e
f
o
u
n
d
to
b
e
b
etter
o
v
er
tr
a
d
itio
n
al
r
eg
r
ess
io
n
an
al
y
s
i
s
an
d
w
er
e
q
u
ite
u
s
e
f
u
l
in
t
h
e
m
an
if
e
s
ti
n
g
b
asic
ch
ar
ac
ter
i
s
t
ic
m
o
d
el
o
f
v
ar
ian
t
s
ized
w
at
er
b
o
d
ies.
A
n
al
y
zi
n
g
o
v
er
o
p
tical
d
is
ti
n
cti
v
en
e
s
s
o
f
s
elec
tiv
e
b
an
d
s
f
r
o
m
L
an
d
Sat5
T
M
an
d
L
an
d
Sat7
E
T
M+
i
m
a
g
er
y
d
ata,
a
m
et
h
o
d
o
lo
g
y
w
a
s
p
r
ese
n
ted
b
y
C
an
zia
n
i
e
t
al.
[
1
7
]
,
to
in
f
er
th
e
tr
o
p
ical
s
ta
te
i
n
d
ex
o
f
la
k
es.
A
NN
m
o
d
el
w
it
h
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
an
d
b
ac
k
p
r
o
p
ag
atio
n
tr
ai
n
i
n
g
al
g
o
r
ith
m
w
er
e
i
m
p
le
m
en
ted
to
d
eter
m
i
n
e
c
h
lo
r
o
p
h
y
ll
-
a
a
n
d
to
t
al
s
u
s
p
en
d
ed
s
o
lid
s
co
n
ce
n
tr
atio
n
s
w
h
ich
p
r
o
v
e
to
b
e
ap
t in
u
n
d
er
s
ta
n
d
in
g
th
e
co
m
p
lex
d
y
n
a
m
ic
b
eh
a
v
io
r
o
f
wate
r
b
o
d
ies.
T
h
e
latest
w
o
r
k
p
r
esen
ted
i
n
b
y
Mo
h
a
m
ed
et
al.
[
1
9
]
,
w
a
s
in
s
p
ir
ed
b
y
r
esear
ch
er
s
Mo
s
es
et
al.
[
2
6
]
an
d
Gh
o
la
m
ali
f
ar
d
et
al.
[
2
7
]
u
s
i
n
g
Mu
ltil
a
y
er
ed
P
er
ce
p
tr
o
n
(
ML
P
)
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
o
n
s
a
telli
te
i
m
ag
e
s
I
R
S
P
6
L
I
S
S
I
I
I
an
d
L
an
d
s
a
t
r
esp
ec
tiv
el
y
,
t
h
at
co
n
tr
ib
u
te
s
to
w
ar
d
s
d
etec
tio
n
o
f
L
a
k
e
B
ath
y
m
etr
y
u
s
i
n
g
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
m
o
d
elin
g
o
n
r
ef
lec
tan
ce
o
f
g
r
ee
n
,
r
ed
,
b
o
th
an
d
f
o
u
r
b
a
n
d
co
m
b
in
atio
n
s
o
f
SP
OT
i
m
a
g
e,
as
co
m
p
ar
ed
w
it
h
p
o
ly
n
o
m
ial
co
r
r
elatio
n
alg
o
r
it
h
m
w
it
h
r
ef
lec
tan
ce
f
r
o
m
g
r
ee
n
b
an
d
a
n
d
Gen
er
alize
d
L
i
n
ea
r
Mo
d
el
(
GL
M)
w
it
h
r
e
f
lecta
n
ce
f
r
o
m
g
r
ee
n
a
n
d
r
ed
b
an
d
.
I
t
d
e
m
o
n
s
tr
ates
th
at
A
N
Ns
i
m
p
ar
t
m
o
r
e
ac
cu
r
ate
r
es
u
lts
i
n
ter
m
s
o
f
le
ast
v
alu
e
o
f
r
o
o
t
m
ea
n
s
q
u
ar
e
th
an
o
th
er
co
n
v
e
n
tio
n
al
m
et
h
o
d
s
f
o
r
b
ath
y
m
etr
ic
ap
p
licatio
n
,
also
th
e
A
NN
u
s
i
n
g
all
b
a
n
d
s
h
a
v
i
n
g
p
r
ec
ed
en
c
e
to
th
e
o
th
er
w
ith
s
in
g
le
b
an
d
u
s
a
g
e.
I
n
o
r
d
er
to
r
ea
ch
to
th
e
p
er
s
p
ec
tiv
e
o
u
tlo
o
k
t
h
e
p
o
w
er
o
f
a
r
tif
icial
n
e
u
r
al
n
e
t
w
o
r
k
w
a
s
a
s
s
es
s
ed
f
o
r
w
ater
q
u
a
li
t
y
es
ti
m
atio
n
o
n
i
n
lan
d
w
ater
b
o
d
ies,
as
to
r
ec
o
g
n
ize
t
h
e
s
tat
u
s
o
f
al
g
al
b
lo
o
m
i
n
w
ater
b
o
d
y
i
s
also
an
ess
e
n
tia
l
p
ar
t
w
h
ich
f
u
r
th
er
f
ac
ilit
ate
s
t
h
e
r
esto
r
atio
n
o
f
p
r
o
ce
s
s
.
W
it
h
t
h
e
s
a
m
e
f
o
cu
s
,
X
u
e
e
t
al.
[
2
0
]
ap
p
lied
th
e
al
g
al
b
lo
o
m
i
n
d
ex
to
in
s
i
tu
re
m
o
te
s
e
n
s
i
n
g
r
e
f
lecta
n
ce
a
n
d
MO
DI
S
R
a
y
le
ig
h
-
co
r
r
ec
ted
r
ef
lecta
n
ce
alo
n
g
w
it
h
th
e
s
p
ee
d
o
f
lo
ca
l
w
i
n
d
.
T
h
e
s
i
m
p
le
s
tatis
tical
tec
h
n
iq
u
e,
C
lass
if
icat
io
n
an
d
R
e
g
r
ess
io
n
(
C
A
R
T
)
Mo
d
el
is
ap
p
lied
to
th
e
ab
o
v
e
d
ata
in
o
r
d
er
to
id
en
tify
t
h
e
v
er
tical
p
r
o
f
ile
d
is
tr
i
b
u
tio
n
o
f
p
h
y
to
p
lan
k
to
n
b
io
m
a
s
s
.
T
h
e
s
tu
d
y
co
n
clu
d
es
t
h
at
s
i
m
ilar
d
ec
is
io
n
tr
ee
ap
p
r
o
ac
h
co
u
ld
b
e
u
s
ed
w
it
h
o
th
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
4
,
Dec
em
b
er
2
0
1
6
:
1
5
3
–
142
140
s
atellite
i
m
ag
er
y
d
ata
f
o
r
m
o
n
ito
r
in
g
a
n
d
co
n
ti
n
u
es
a
s
s
e
s
s
m
en
t
o
f
th
e
l
e
v
el
o
f
e
u
tr
o
p
h
icatio
n
to
o
th
er
h
y
d
r
o
b
o
d
ies.
I
R
S
P
6
L
I
SS
I
I
I
i
m
ag
e
r
y
d
ata
f
r
o
m
i
s
b
ein
g
a
n
al
y
ze
d
to
p
r
ed
ict
Secc
h
i
d
is
k
d
ep
th
(
SDD
)
o
f
a
lak
e
w
it
h
t
h
e
u
s
a
g
e
o
f
Mu
ltil
i
n
ea
r
R
eg
r
ess
io
n
(
ML
R
)
m
o
d
el
u
s
in
g
all
f
o
u
r
b
an
d
s
(
g
r
ee
n
,
r
ed
,
NI
R
an
d
MI
R
)
as
in
d
ep
en
d
en
t
v
ar
iab
le
an
d
SD
D
d
ep
en
d
en
t
v
ar
iab
le
[
2
1
]
.
T
h
e
co
m
p
u
ted
r
es
u
lts
ar
e
f
o
u
n
d
to
b
e
s
u
p
er
io
r
to
r
eg
r
ess
io
n
m
o
d
el
o
n
s
p
ec
t
r
al
r
atio
n
an
d
i
n
d
iv
id
u
al
b
an
d
an
al
y
s
i
s
an
d
w
a
ter
f
o
u
n
d
to
b
e
at
h
y
p
er
eu
tr
o
p
h
ic
lev
el.
I
n
t
h
e
w
o
r
k
o
f
C
h
e
n
et
a
l.
i
n
[
2
8
]
,
th
r
ee
n
eu
r
al
n
e
t
w
o
r
k
m
o
d
els
R
ad
ial
B
asis
F
u
n
ct
i
o
n
Ne
u
r
al
Net
w
o
r
k
(
R
B
FN)
,
A
d
ap
tiv
e
Net
w
o
r
k
b
ased
F
u
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
(
A
N
FIS)
an
d
M
u
ltil
i
n
ea
r
R
eg
r
es
s
io
n
(
ML
R
)
w
er
e
d
ev
elo
p
ed
an
d
c
o
m
p
ar
ed
to
e
x
a
m
in
e
o
v
er
m
e
an
ab
s
o
l
u
te
er
r
o
r
,
th
e
r
o
o
t
m
e
an
s
q
u
ar
e
er
r
o
r
an
d
th
e
co
r
r
elatio
n
co
ef
f
icie
n
t.
T
h
ese
m
o
d
els
w
er
e
d
ev
elo
p
ed
m
ai
n
l
y
to
p
r
ed
ict
o
v
er
d
is
s
o
lv
ed
o
x
y
g
e
n
,
to
ta
l
p
h
o
s
p
h
o
r
u
s
,
ch
lo
r
o
p
h
y
ll
-
a
a
n
d
Secc
h
i
d
is
k
d
ep
th
i
n
t
h
e
r
eser
v
o
ir
a
m
o
n
g
w
h
ic
h
n
eu
r
al
n
et
w
o
r
k
ANFI
S
s
h
o
w
ed
to
b
e
m
o
s
t
s
u
i
tab
le
f
o
r
s
i
m
u
la
tin
g
t
h
e
w
ater
q
u
alit
y
p
ar
a
m
eter
s
w
it
h
r
ea
s
o
n
ab
le
ac
cu
r
ac
y
.
A
s
h
o
r
t
o
u
tco
m
e
o
f
t
h
e
as
s
ess
m
e
n
t is
d
ep
ic
ted
in
th
e
tab
u
latio
n
f
o
r
m
at
m
en
t
io
n
ed
as t
h
e
T
ab
le
1
.
T
ab
le
1
.
A
r
tif
icial
Ne
u
r
al
Net
w
o
r
k
i
n
A
s
s
es
s
m
e
n
t
o
f
o
v
er
D
if
f
er
en
t P
ar
a
m
eter
s
o
f
w
ater
b
o
d
ies
C
i
t
a
t
i
o
n
s
I
n
p
u
t
P
a
r
a
me
t
e
r
s
(
I
mag
e
r
y
/
S
t
a
t
i
st
i
c
a
l
D
a
t
a
S
o
u
r
c
e
)
A
N
N
M
o
d
e
l
a
n
d
T
r
a
i
n
i
n
g
A
p
p
r
o
a
c
h
M
a
j
o
r
F
u
n
c
t
i
o
n
a
l
i
t
y
K
e
y
f
a
c
e
t
s
B
a
r
u
h
a
e
t
a
l
.
,
2
0
0
1
[
1
5
]
L
a
n
d
sat
T
M
I
mag
e
r
y
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
w
i
t
h
si
n
g
l
e
h
i
d
d
e
n
l
a
y
e
r
T
o
e
st
i
mat
e
c
h
l
o
r
o
p
h
y
l
l
c
o
n
c
e
n
t
r
a
t
i
o
n
a
n
d
se
d
i
me
n
t
s o
f
w
a
t
e
r
b
o
d
i
e
s
L
a
n
d
sat
T
M
p
r
e
f
e
r
r
e
d
o
v
e
r
M
O
D
I
S
a
n
d
S
e
a
W
i
F
s
se
n
so
r
c
a
u
se
o
f
l
o
w
sp
a
t
i
a
l
r
e
so
l
u
t
i
o
n
P
a
n
d
a
e
t
a
l
.
,
2
0
0
4
[
2
5
]
L
a
n
d
sat
T
M
I
mag
e
r
y
L
i
n
e
a
r
R
e
g
r
e
ssi
o
n
st
a
t
i
st
i
c
a
l
mo
d
e
l
(
L
M
R
)
R
a
d
i
a
l
b
a
s
i
s f
u
n
c
t
i
o
n
n
e
u
r
a
l
(
R
B
F
N
)
n
e
t
w
o
r
k
T
o
d
e
t
e
r
mi
n
i
n
g
t
h
e
c
o
n
c
e
n
t
r
a
t
i
o
n
s
o
f
c
h
l
o
r
o
p
h
y
l
l
-
a
(
c
h
l
-
a
)
a
n
d
su
sp
e
n
d
e
d
m
a
t
t
e
r
(
S
M
)
C
o
st
-
e
f
f
e
c
t
i
v
e
,
q
u
i
c
k
,
a
n
d
f
e
a
si
b
l
e
w
i
t
h
a
c
c
u
r
a
c
y
i
n
p
r
e
d
i
c
t
e
d
a
n
d
a
c
t
u
a
l
r
e
su
l
t
s.
I
n
f
o
r
mat
i
o
n
f
o
r
a
l
l
b
a
n
d
s
p
r
e
f
e
r
r
e
d
o
v
e
r
si
n
g
l
e
b
a
n
d
.
R
B
N
F
t
o
b
e
mo
r
e
r
o
b
u
s
t
t
h
a
n
L
M
R
C
a
n
z
i
a
n
i
e
t
a
l
.
,
2
0
0
8
[
1
7
]
L
a
n
d
S
a
t
5
T
M
a
n
d
L
a
n
d
S
a
t
7
ET
M
+
I
mag
e
r
y
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
w
i
t
h
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
L
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
T
o
d
e
t
e
r
mi
n
e
c
h
l
o
r
o
p
h
y
l
l
-
a
a
n
d
t
o
t
a
l
s
u
sp
e
n
d
e
d
so
l
i
d
s
c
o
n
c
e
n
t
r
a
t
i
o
n
s
f
o
r
u
n
d
e
r
st
a
n
d
i
n
g
t
h
e
c
o
m
p
l
e
x
d
y
n
a
mi
c
b
e
h
a
v
i
o
r
o
f
w
a
t
e
r
b
o
d
i
e
s.
R
e
mo
t
e
se
n
so
r
s d
a
t
a
p
r
o
c
e
sse
d
b
y
A
N
N
a
r
e
u
se
f
u
l
f
o
r
mo
n
i
t
o
r
i
n
g
t
h
e
t
r
a
n
sf
o
r
ma
t
i
o
n
s
i
n
sh
a
l
l
o
w
l
a
k
e
s
G
h
o
l
a
mal
i
f
a
r
d
e
t
a
l
.
,
2
0
1
3
[
2
7
]
L
a
n
d
sat
5
T
M
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
u
se
d
w
i
t
h
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
L
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
T
o
e
x
t
r
a
c
t
t
h
e
b
a
t
h
y
me
t
r
y
i
n
f
o
r
mat
i
o
n
o
f
so
u
t
h
e
a
st
e
r
n
C
a
s
p
i
a
n
S
e
a
A
N
N
e
st
i
mat
e
d
d
e
p
t
h
w
i
t
h
g
o
o
d
a
c
c
u
r
a
c
y
e
v
e
n
w
i
t
h
r
e
l
a
t
i
v
e
l
y
l
e
ss
i
n
s
i
t
u
d
a
t
a
se
t
s
a
n
d
f
a
i
r
l
y
p
o
o
r
se
n
so
r
i
mag
e
r
y
.
M
o
se
s e
t
a
l
.
,
2
0
1
3
[
2
6
]
I
R
S
P
6
L
I
S
S
I
I
I
i
mag
e
r
y
T
h
r
e
e
-
l
a
y
e
r
e
d
f
e
e
d
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
t
r
a
i
n
i
n
g
a
l
g
o
r
i
t
h
m
T
o
e
st
i
mat
e
L
a
k
e
b
a
t
h
y
me
t
r
y
a
l
so
e
st
i
mat
i
n
g
S
e
c
c
h
i
D
i
sk
T
r
a
n
sp
a
r
e
n
c
y
(
S
D
T
)
A
l
l
f
o
u
r
b
a
n
d
d
a
t
a
se
t
u
se
d
a
n
d
sy
st
e
m i
mp
a
r
t
s
i
m
p
r
o
v
e
d
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
X
u
e
e
t
a
l
.
,
2
0
1
5
[
2
0
]
M
O
D
I
S
I
mag
e
r
y
C
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
R
e
g
r
e
ssi
o
n
T
r
e
e
M
o
d
e
l
(
C
A
R
T
)
S
t
a
t
i
st
i
c
a
l
T
e
c
h
n
i
q
u
e
s
T
o
i
d
e
n
t
i
f
y
v
e
r
t
i
c
a
l
d
i
st
r
i
b
u
t
i
o
n
p
r
o
f
i
l
e
o
f
p
h
y
t
o
p
l
a
n
k
t
o
n
b
a
se
d
o
n
a
l
g
a
l
b
l
o
o
m i
n
d
e
x
o
f
L
a
k
e
C
h
a
o
h
u
.
S
a
me
a
p
p
r
o
a
c
h
w
i
t
h
o
t
h
e
r
sat
e
l
l
i
t
e
d
a
t
a
c
o
u
l
d
b
e
a
p
p
l
i
c
a
b
l
e
f
o
r
mo
n
i
t
o
r
i
n
g
o
f
a
l
g
a
l
b
i
o
mass
i
n
o
t
h
e
r
si
m
i
l
a
r
h
y
d
r
o
l
o
g
y
.
4.
F
UT
UR
E
SCO
P
E
A
ND
CO
NCLUS
I
O
NS
Fro
m
o
u
r
s
t
u
d
y
w
e
h
ad
id
en
t
i
f
ied
th
a
t
u
s
ag
e
o
f
i
m
ag
er
y
d
ata;
m
ai
n
l
y
L
an
d
s
a
t
T
M,
f
o
r
s
ec
ch
i
d
is
k
d
ep
th
(
SDD)
a
n
d
tr
o
p
ical
s
ta
te
in
d
e
x
(
T
SI)
ar
e
k
n
o
w
n
to
b
e
esti
m
ated
f
o
r
i
n
la
n
d
la
k
e
s
i
n
o
u
r
r
eg
io
n
b
y
r
esear
ch
er
s
,
[
2
9
]
an
d
[
3
0
]
.
No
w
f
o
r
o
u
r
f
u
t
u
r
e
r
esear
ch
d
ir
ec
tio
n
w
e
ar
e
in
te
n
d
ed
to
d
ev
elo
p
a
o
v
er
all
g
eo
co
m
p
u
ti
n
g
s
y
s
te
m
w
h
ic
h
w
o
u
ld
an
al
y
ze
i
m
ag
er
y
d
ata,
ex
tr
ac
t
t
h
e
SDD,
T
SI,
ch
lo
r
o
p
h
y
ll
-
a,
d
is
s
o
l
v
ed
o
x
y
g
en
an
d
o
t
h
er
p
ar
a
m
eter
s
,
tr
ain
th
e
n
e
u
r
al
n
et
w
o
r
k
w
it
h
f
o
llo
w
i
n
g
s
o
a
s
to
lear
n
t
h
e
b
asic
c
h
ar
ac
ter
is
tic
s
o
f
s
elec
ted
w
ater
b
o
d
y
a
n
d
p
r
ed
ict
th
e
cu
r
r
en
t
an
d
f
u
t
u
r
e
s
t
atu
s
o
f
eu
tr
o
p
h
icat
io
n
u
s
i
n
g
t
i
m
e
s
er
ies
p
r
ed
ictio
n
s
o
as to
f
ac
ilit
ate
t
h
e
r
esto
r
atio
n
p
h
e
n
o
m
e
n
o
n
.
I
n
th
is
as
s
es
s
m
en
t,
w
e
r
ev
ie
wed
o
v
er
th
e
ty
p
e
o
f
i
m
a
g
er
y
d
ata
ex
er
cises
b
y
d
if
f
er
en
t
s
y
s
te
m
s
a
n
d
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
an
d
th
er
e
lear
n
i
n
g
tec
h
n
iq
u
es.
T
h
e
m
ain
o
b
j
ec
tiv
e
w
as
to
ex
p
lo
r
e
t
h
e
p
o
w
er
o
f
v
ar
io
u
s
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
in
g
eo
co
m
p
u
tatio
n
a
n
d
to
d
r
a
w
a
r
o
ad
m
ap
f
o
r
s
o
m
e
m
o
r
e
tech
n
o
lo
g
ical
l
y
ad
v
an
ce
d
s
y
s
te
m
s
th
at
w
o
u
ld
b
e
co
g
n
iza
n
t
an
d
if
d
ep
lo
y
ed
co
u
ld
b
e
ea
s
y
to
p
r
ed
ict
th
e
f
u
tu
r
is
tic
b
eh
a
v
io
r
o
f
w
ater
b
o
d
ies u
lti
m
ate
l
y
e
n
v
is
a
g
e
th
e
q
u
a
lit
y
o
f
w
ater
in
t
h
e
s
y
s
te
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
A
s
s
es
s
in
g
S
ta
te
o
f th
e
A
r
t o
n
A
r
tifi
cia
l Neu
r
a
l Net
w
o
r
k
P
a
r
a
d
ig
ms fo
r
Leve
l o
f
… (
Tu
s
h
a
r
A
n
th
w
a
l
)
141
RE
F
E
R
E
NC
E
S
[1
]
Jin
X,
X
u
Q,
H
u
a
n
g
C.
Cu
rre
n
t
S
tatu
s
a
n
d
F
u
t
u
re
T
e
n
d
e
n
c
y
o
f
L
a
k
e
Eu
tro
p
h
ica
ti
o
n
in
C
h
in
a
.
S
c
ien
c
e
in
Ch
in
a
S
e
rie
s C
L
if
e
S
c
ien
c
e
s
.
2
0
0
5
;
4
8
:
9
4
8
–
5
4
.
[2
]
Ha
y
k
in
S
.
N
e
u
ra
l
Ne
t
w
o
rk
s
A
C
o
m
p
re
h
e
n
siv
e
F
o
u
n
d
a
ti
o
n
,
2
n
d
E
d
it
io
n
e
d
;
P
re
n
ti
c
e
Ha
ll
In
c
.
:
Up
p
e
r
S
a
d
d
le
Riv
e
r,
NJ
,
USA
,
1
9
9
9
.
[3
]
A
b
ra
h
a
rt
RJ,
S
e
e
L
M
.
E
d
it
o
rs
.
Ge
o
c
o
m
p
u
tatio
n
.
L
o
n
d
o
n
:
T
a
y
lo
r
&
F
ra
n
c
is;
2
0
1
4
Ju
n
2
2
.
[4
]
L
o
n
g
le
y
P
,
Br
o
o
k
s
S
,
M
a
c
M
il
lan
B,
P
a
u
l
A
L
o
n
g
le
y
.
.
.
[
e
t
a
l
.
]
.
G
e
o
c
o
m
p
u
tatio
n
:
A
P
rim
e
r.
Un
it
e
d
S
tate
s:
Jo
h
n
W
il
e
y
;
2
0
1
4
M
a
y
1
4
.
[5
]
Ra
ju
P
L
N.
S
p
a
ti
a
l
Da
ta
A
n
a
l
y
si
s.
S
a
telli
te
Re
m
o
te
S
e
n
sin
g
a
n
d
G
IS
A
p
p
li
c
a
ti
o
n
s
in
A
g
ricu
lt
u
ra
l
M
e
teo
ro
lo
g
y
.
2
0
0
3
:
1
5
1
–
7
4
.
[6
]
Ba
il
e
y
T
Ga
tt
re
ll
,
(1
9
9
5
)
,
In
S
p
a
ti
a
l
Da
ta A
n
a
l
y
sis b
y
E
x
a
m
p
le L
o
n
d
o
n
:
L
o
n
g
m
a
n
.
[7
]
M
a
c
Eac
h
re
n
A
M
,
Kra
a
k
M
-
J.
R
e
se
a
rc
h
c
h
a
ll
e
n
g
e
s
in
Ge
o
v
isu
a
li
z
a
ti
o
n
.
Ca
rt
o
g
r
a
p
h
y
a
n
d
Ge
o
g
ra
p
h
ic
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
.
2
0
0
1
;
2
8
(1
)
:
3
–
1
2
.
[8
]
V
e
g
a
M
,
P
a
rd
o
R,
Ba
rra
d
o
E,
De
b
á
n
L
.
A
ss
e
ss
m
e
n
t
o
f
s
e
a
so
n
a
l
a
n
d
p
o
ll
u
ti
n
g
e
ffe
c
ts
o
n
th
e
q
u
a
li
ty
o
f
riv
e
r
w
a
ter
b
y
e
x
p
lo
ra
to
ry
d
a
ta an
a
l
y
sis.
W
a
ter
Res
e
a
rc
h
.
1
9
9
8
;
3
2
(1
2
):
3
5
8
1
–
92.
[9
]
l
b
e
r
t
o
,
a
r
a
d
e
l
i
l
a
r
,
a
r
a
a
l
e
r
i
a
,
a
b
i
a
n
a
,
e
c
i
l
i
a
,
a
r
a
d
e
l
o
s
n
g
e
l
e
s
B.
P
a
tt
e
rn
re
c
o
g
n
it
io
n
tec
h
n
i
q
u
e
s
f
o
r
t
h
e
e
v
a
lu
a
ti
o
n
o
f
sp
a
ti
a
l
a
n
d
tem
p
o
ra
l
v
a
riatio
n
s
in
w
a
ter
q
u
a
li
ty
.
A
c
a
se
stu
d
y
:
W
a
ter
Res
e
a
rc
h
.
2
0
0
1
;
3
5
(1
2
):
2
8
8
1
–
94.
[1
0
]
S
in
g
h
K
P
,
M
a
li
k
A
,
S
in
h
a
S
.
W
a
ter
q
u
a
li
t
y
a
ss
e
ss
m
e
n
t
a
n
d
a
p
p
o
rti
o
n
m
e
n
t
o
f
p
o
ll
u
ti
o
n
so
u
rc
e
s
o
f
G
o
m
ti
riv
e
r
(In
d
ia)
u
sin
g
m
u
lt
iv
a
riate
sta
ti
stica
l
tec
h
n
iq
u
e
s
—
a
c
a
se
stu
d
y
.
An
a
l
y
ti
c
a
Ch
imica
Acta
.
2
0
0
5
;
5
3
8
(1
-
2
):
3
5
5
–
7
4
.
[1
1
]
Ca
q
u
a
rd
S
.
W
a
ter q
u
a
li
ty
m
a
p
p
in
g
f
o
r
w
a
ter
m
a
n
a
g
e
m
e
n
t.
Ca
rto
g
r
a
p
h
ic P
e
rs
p
e
c
ti
v
e
s
.
1
9
9
9
M
a
r
1
;
(
3
2
):
2
9
–
4
3
.
[1
2
]
Câ
m
a
ra
G
,
M
o
n
teir
o
A
M
V
.
G
e
o
c
o
m
p
u
tatio
n
tec
h
n
iq
u
e
s
f
o
r
sp
a
ti
a
l
a
n
a
ly
sis:
A
re
th
e
y
re
lev
a
n
t
to
h
e
a
lt
h
d
a
ta?
Ca
d
e
rn
o
s d
e
S
a
ú
d
e
P
ú
b
li
c
a
.
2
0
0
1
Oc
t;
1
7
(
5
).
[1
3
]
Bo
se
r
BE,
G
u
y
o
n
IM
,
V
a
p
n
ik
VN
.
A
tra
i
n
in
g
a
l
g
o
ri
th
m
f
o
r
o
p
ti
ma
l
ma
rg
i
n
c
la
ss
if
ier
s
.
I
n
P
ro
c
e
e
d
in
g
s
o
f
th
e
5
t
h
a
n
n
u
a
l
A
CM
w
o
rk
sh
o
p
o
n
c
o
m
p
u
tatio
n
a
l
lea
rn
in
g
th
e
o
ry
.
1
9
9
2
:
1
4
4
–
5
2
.
[1
4
]
Ka
n
e
v
sk
i
M
,
P
a
rk
in
R,
P
o
z
d
n
u
k
h
o
v
A
,
T
i
m
o
n
in
V
,
M
a
ig
n
a
n
M
,
D
e
m
y
a
n
o
v
V
,
Ca
n
u
S
.
En
v
iro
n
m
e
n
tal
d
a
ta
m
in
in
g
a
n
d
m
o
d
e
li
n
g
b
a
se
d
o
n
m
a
c
h
in
e
l
e
a
rn
in
g
a
lg
o
rit
h
m
s
a
n
d
g
e
o
sta
ti
stics
.
En
v
iro
n
m
e
n
ta
l
M
o
d
e
ll
i
n
g
&
S
o
f
tw
a
r
e
.
2
0
04
;
1
9
(
9
):
8
4
5
–
5
5
.
[1
5
]
Ba
ru
h
a
P
J,
T
a
m
u
ra
M
,
Ok
i
K,
Nish
im
u
ra
H.
Ne
u
ra
l
Ne
tw
o
rk
M
o
d
e
li
n
g
o
f
L
a
k
e
S
u
rf
a
c
e
Ch
l
o
ro
p
h
y
ll
a
n
d
S
e
d
ime
n
t
c
o
n
ten
t
fr
o
m
L
ANDS
A
T
T
M
Ima
g
e
ry
.
P
a
p
e
r
p
re
se
n
ted
a
t:
2
2
n
d
A
sia
n
Co
n
f
e
r
e
n
c
e
o
n
Re
m
o
te
S
e
n
sin
g
.
[
P
lac
e
u
n
k
n
o
w
n
:
p
u
b
li
sh
e
r
u
n
k
n
o
w
n
]
;
2
0
0
1
No
v
.
[1
6
]
S
u
d
h
e
e
r
KP
,
Ch
a
u
b
e
y
I,
Ga
rg
V
.
L
a
k
e
Wate
r
Qu
a
li
t
y
As
se
ss
m
e
n
t
f
ro
m
L
a
n
d
sa
t
T
h
e
m
a
ti
c
M
a
p
p
e
r
Da
ta
Us
in
g
Ne
u
ra
l
Ne
tw
o
rk
:
A
n
A
p
p
ro
a
c
h
to
Op
ti
m
a
l
Ba
n
d
C
o
m
b
in
a
ti
o
n
S
e
l
e
c
ti
o
n
.
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
W
a
ter
Res
o
u
rc
e
s
Asso
c
ia
ti
o
n
.
2
0
0
6
De
c
;
4
2
(
6
):
1
6
8
3
–
9
5
.
[1
7
]
Ca
n
z
ian
i
G
,
F
e
rra
ti
R,
M
a
rin
e
ll
i
C,
Du
k
a
tz
F
.
A
rti
f
ici
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
a
n
d
re
m
o
te
se
n
sin
g
in
th
e
a
n
a
l
y
sis
o
f
th
e
h
ig
h
ly
v
a
riab
le P
a
m
p
e
a
n
sh
a
ll
o
w
lak
e
s.
M
a
th
e
ma
ti
c
a
l
Bi
o
sc
ien
c
e
s a
n
d
En
g
i
n
e
e
rin
g
.
2
0
0
8
;
5
(
4
):
6
9
1
–
7
1
1
.
[1
8
]
G
u
a
n
X
,
L
i
J,
Bo
o
ty
WG
.
M
o
n
i
to
rin
g
L
a
k
e
S
i
m
c
o
e
w
a
ter
c
larity
u
sin
g
L
a
n
d
sa
t
-
5
T
M
ima
g
e
s.
W
a
ter
Re
so
u
rc
e
s
M
a
n
a
g
e
m
e
n
t.
2
0
1
1
M
a
r
2
;
2
5
(
8
):
2
0
1
5
–
3
3
.
[1
9
]
M
o
h
a
m
e
d
H,
Ne
g
m
A
,
Z
a
h
ra
n
M
,
S
a
a
v
e
d
ra
OC.
Ba
th
y
m
e
tr
y
d
e
term
in
a
ti
o
n
f
ro
m
h
ig
h
re
so
lu
ti
o
n
sa
telli
te
i
m
a
g
e
r
y
u
sin
g
e
n
se
m
b
le
le
a
rn
in
g
A
l
g
o
rit
h
m
s
in
sh
a
ll
o
w
la
k
e
s:
C
a
se
st
u
d
y
El
-
Bu
ru
ll
u
s
lak
e
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
v
iro
n
me
n
ta
l
S
c
ien
c
e
a
n
d
De
v
e
l
o
p
me
n
t
.
2
0
1
6
;
7
(4
):
2
9
5
–
3
0
1
.
[2
0
]
X
u
e
K,
Z
h
a
n
g
Y,
Du
a
n
H,
M
a
R,
L
o
ise
ll
e
S
,
Zh
a
n
g
M
.
A
re
m
o
te
se
n
sin
g
a
p
p
ro
a
c
h
to
e
stim
a
te
v
e
rti
c
a
l
p
ro
f
il
e
c
las
se
s o
f
P
h
y
to
p
lan
k
to
n
in
a
E
u
tr
o
p
h
ic l
a
k
e
.
Re
m
o
te S
e
n
sin
g
.
2
0
1
5
Oc
t
3
0
;
7
(1
1
):
1
4
4
0
3
–
27.
[2
1
]
S
h
e
e
la
A
M
,
L
e
th
a
J,
Jo
se
p
h
S
,
R
a
m
a
c
h
a
n
d
ra
n
KK
,
S
.
P
.
S
.
T
ro
p
h
i
c
st
a
te
in
d
e
x
o
f
a
lak
e
s
y
ste
m
u
sin
g
IRS
(
P
6
-
L
IS
S
III)
sa
telli
te i
m
a
g
e
r
y
.
En
v
iro
n
m
e
n
tal
M
o
n
it
o
ri
n
g
a
n
d
A
ss
e
ss
m
e
n
t.
2
0
1
0
S
e
p
1
4
;
1
7
7
(1
-
4
):
5
7
5
–
9
2
.
[2
2
]
L
iu
,
L
u
J.
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
―a
n
a
lt
e
rn
a
ti
v
e
to
a
rti
f
icia
l
n
e
u
ro
n
n
e
tw
o
rk
f
o
r
w
a
ter
q
u
a
li
t
y
f
o
re
c
a
stin
g
in
a
n
a
g
ricu
lt
u
ra
l
n
o
n
p
o
i
n
t
s
o
u
rc
e
p
o
ll
u
ted
riv
e
r?
En
v
ir
o
n
me
n
t
a
l
S
c
ien
c
e
a
n
d
Po
l
lu
ti
o
n
Res
e
a
rc
h
.
2
0
1
4
Ju
n
5
;
2
1
(
1
8
):
1
1
0
3
6
–
5
3
.
[2
3
]
L
iao
Y,
X
u
J,
W
a
n
g
Z.
A
p
p
li
c
a
ti
o
n
o
f
b
io
m
o
n
it
o
r
in
g
a
n
d
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
in
w
a
ter
q
u
a
li
ty
a
ss
e
ss
m
e
n
t.
J
o
u
rn
a
l
o
f
Z
h
e
ji
a
n
g
U
n
ive
r
sity S
CIENCE
B
.
2
0
1
2
;
1
3
(4
):
3
2
7
–
3
4
.
[2
4
]
Ch
u
HB
,
L
u
W
X
,
Z
h
a
n
g
L
.
A
p
p
l
ica
ti
o
n
o
f
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
two
rk
in
En
v
ir
o
n
m
e
n
tal
W
a
ter
Qu
a
li
ty
A
ss
e
ss
m
e
n
t.
J
o
u
rn
a
l
o
f
A
g
ric
u
lt
u
ra
l
S
c
ien
c
e
s a
n
d
T
e
c
h
n
o
l
o
g
y
.
2
0
1
3
;
1
5
:
3
4
3
–
5
6
.
[2
5
]
P
a
n
d
a
S
S
.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
a
p
p
li
c
a
ti
o
n
in
lak
e
wa
ter
q
u
a
li
ty
e
sti
m
a
ti
o
n
u
sin
g
sa
telli
te
i
m
a
g
e
r
y
.
J
o
u
rn
a
l
o
f
En
v
iro
n
me
n
ta
l
I
n
f
o
rm
a
ti
c
s
.
2
0
0
4
;
4
(2
):
65
–
74.
[2
6
]
M
o
se
s
S
A
,
J
a
n
a
k
i
L
,
Jo
se
p
h
S
,
G
o
m
a
th
i
JP
,
Jo
se
p
h
J.
L
a
k
e
b
a
th
y
m
e
tr
y
f
ro
m
In
d
ian
re
m
o
te
se
n
si
n
g
(P
6
-
L
IS
S
III)
sa
telli
te
i
m
a
g
e
r
y
u
sin
g
a
rt
i
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l.
L
a
k
e
s
&
R
e
se
rv
o
irs:
Re
se
a
rc
h
&
M
a
n
a
g
e
m
e
n
t.
2
0
1
3
;
1
8
(
2
):
145
–
5
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
4
,
Dec
em
b
er
2
0
1
6
:
1
5
3
–
142
142
[2
7
]
G
h
o
la
m
a
li
f
a
rd
M
,
Ku
tse
r
T
,
Es
m
a
il
i
-
S
a
ri
A
,
A
b
k
a
r
A
,
Na
i
m
i
B.
Re
m
o
tel
y
se
n
se
d
e
m
p
iri
c
a
l
m
o
d
e
li
n
g
o
f
Ba
th
y
m
e
tr
y
in
t
h
e
so
u
t
h
e
a
ste
rn
Ca
sp
ian
se
a
.
Re
m
o
te S
e
n
sin
g
.
2
0
1
3
M
a
y
3
0
;
5
(6
):
2
7
4
6
–
6
2
.
[2
8
]
Ch
e
n
W
-
B,
L
iu
W
-
C.
W
a
ter
q
u
a
li
ty
m
o
d
e
li
n
g
in
re
se
rv
o
irs
u
sin
g
M
u
lt
iv
a
riate
li
n
e
a
r
re
g
re
s
sio
n
a
n
d
tw
o
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
ls.
A
d
v
a
n
c
e
s in
A
rt
if
icia
l
Ne
u
ra
l
S
y
ste
m
s.
2
0
1
5
;
2
0
1
5
:
1
–
1
2
.
[2
9
]
[2
9
]
M
ish
ra
A
K,
Ga
rg
N.
A
n
a
l
y
sis
o
f
T
ro
p
h
ic
sta
te
in
d
e
x
o
f
N
a
in
it
a
l
L
a
k
e
f
ro
m
Lan
d
sa
t
−
7
ET
d
a
ta.
J
o
u
rn
a
l
o
f
th
e
In
d
ia
n
S
o
c
iety
o
f
Rem
o
te S
e
n
sin
g
.
2
0
1
1
Ju
n
1
0
;
3
9
(
4
):
4
6
3
–
7
1
.
[3
0
]
Dh
il
lo
n
JK
,
M
is
h
ra
A
K.
Esti
m
a
ti
o
n
o
f
T
ro
p
h
ic sta
te i
n
d
e
x
o
f
S
u
k
h
n
a
L
a
k
e
u
sin
g
re
m
o
te se
n
sin
g
a
n
d
G
IS
.
J
o
u
rn
a
l
o
f
th
e
In
d
ia
n
S
o
c
iety
o
f
Rem
o
te S
e
n
sin
g
.
2
0
1
3
De
c
1
1
;
4
2
(2
):
4
6
9
–
7
4
.
[3
1
]
P
la
n
n
i
n
g
a
n
d
m
a
n
a
g
e
m
e
n
t
o
f
lak
e
s
a
n
d
re
se
rv
o
irs:
A
n
in
teg
ra
ted
a
p
p
ro
a
c
h
t
o
E
u
tro
p
h
ica
ti
o
n
[
c
it
e
d
2
0
1
6
A
u
g
1
0
].
Av
a
il
a
b
le f
ro
m
:
h
tt
p
:/
/w
ww
.
u
n
e
p
.
o
r.
jp
/i
e
tc/
P
u
b
li
c
a
ti
o
n
s/T
e
c
h
P
u
b
li
c
a
ti
o
n
s/T
e
c
h
P
u
b
-
1
1
/6
-
1
0
.
a
sp
.
BI
O
G
RAP
H
Y
O
F
AUTHO
R
T
u
sh
a
r
A
n
th
wa
l
is
a
n
A
ss
istan
t
P
r
o
f
e
ss
o
r
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
a
t
Am
ra
p
a
li
In
stit
u
te
o
f
M
a
n
a
g
e
m
e
n
t
a
n
d
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
,
a
f
f
il
iate
d
to
Uttara
k
h
a
n
d
T
e
c
h
n
ica
l
Un
iv
e
rsity
.
He
re
c
e
iv
e
d
h
is
M
a
ste
rs
in
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
f
ro
m
H
e
m
w
a
ti
Na
n
d
a
n
G
a
rh
w
a
l
Un
iv
e
rsit
y
(n
o
w
Ce
n
tral
Un
iv
e
rsity
),
S
rin
a
g
a
r
G
a
r
h
w
a
l.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
st
in
c
l
u
d
e
s
c
o
m
p
u
ter
g
ra
p
h
ics
,
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,
g
e
o
g
r
a
p
h
ica
l
in
f
o
rm
a
ti
o
n
sy
ste
m
s
a
n
d
a
lg
o
rit
h
m
s.
He
h
a
d
a
b
o
u
t
1
0
y
e
a
rs
o
f
e
x
p
e
rien
c
e
a
s
fa
c
u
lt
y
in
c
lu
d
in
g
i
n
d
u
strial
e
x
p
o
su
re
.
H
e
h
a
d
se
v
e
ra
l
p
u
b
li
c
a
ti
o
n
s
i
n
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
c
o
n
f
e
re
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.